CN113888564B - Tourism product advertising image display method, system, device and storage medium - Google Patents
Tourism product advertising image display method, system, device and storage medium Download PDFInfo
- Publication number
- CN113888564B CN113888564B CN202111392295.8A CN202111392295A CN113888564B CN 113888564 B CN113888564 B CN 113888564B CN 202111392295 A CN202111392295 A CN 202111392295A CN 113888564 B CN113888564 B CN 113888564B
- Authority
- CN
- China
- Prior art keywords
- image
- picture
- advertisement
- travel
- template image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0252—Targeted advertisements based on events or environment, e.g. weather or festivals
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/08—Projecting images onto non-planar surfaces, e.g. geodetic screens
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Environmental & Geological Engineering (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明提供了旅游产品的广告图像展示方法、系统、设备及存储介质，该方法包括：接收旅游产品的预订信息；基于在图片库中根据关键字、地点信息以及与未来旅游时段同时段作为拍摄时间作为筛选条件，收集图片形成图片样本库；根据图片样本库的照片进行第一次图片分割识别，获得分割后各区域对应的样板图像标签；对预设为可迁移的样板图像标签���图片进行������学习，获得特征蒙版；对广告影像进行第二次图片分割识别，获得分割后各区域对应的广告影像标签；当局部区域的广告影像标签与样板图像标签相同，则将特征蒙版与广告影像的局部区域进行图像混合后展示。本发明能够基于用户的预订信息自动更新相关景点的广告图像，增强用户预期的准确性。
The present invention provides a method, system, device and storage medium for displaying advertising images of tourism products, the method comprising: receiving reservation information of tourism products; collecting pictures to form a picture sample library based on the keywords, location information and the shooting time in the same period as the future travel period in the picture library as screening conditions; performing a first picture segmentation and recognition based on the pictures in the picture sample library to obtain the sample image labels corresponding to each area after segmentation; performing machine learning on the pictures preset as the transferable sample image labels to obtain the feature mask; performing a second picture segmentation and recognition on the advertising image to obtain the advertising image labels corresponding to each area after segmentation; when the advertising image label of the local area is the same as the sample image label, the feature mask is mixed with the local area of the advertising image and then displayed. The present invention can automatically update the advertising images of relevant attractions based on the user's reservation information, and enhance the accuracy of user expectations.
Description
Technical Field
The invention relates to the field of image processing, in particular to a method, a system, equipment and a storage medium for displaying advertisement images of tourist products.
Background
In the current internet environment, video is an important information medium. Video production is divided into a variety of types, including video generated from a single picture. The OTA platform (OTA: collectively called Online TRAVEL AGENCY, chinese translated into "Online travel agency", i.e. Online hotel, travel, ticketing etc. reservation system platform is collectively called.) has a huge number of pictures of each scenic spot, however, in practical situations, there is a problem that even if there is a huge number of pictures uploaded by users under one scenic spot, there is a lack of diversity among pictures, for example, scenic spots of some masses, the relevant pictures are concentrated on a certain weather or season, because there are only a lot of tourists in the weather and season, and thus some pictures uploaded by users are brought. The convergence of seasons or weather for different pictures can result in less comprehensive presentations to the attraction, thereby reducing the attractiveness of the attraction.
Moreover, when a user subscribes to a tourist product, the user cannot predict the actual feeling of traveling at a future destination (usually the influence of weather and seasons on scenic spots) so that the user only subscribes to advertisement photos of the scenic spots, and when the subsequent traveling experience is poor, bad comments are left on an OTA platform and the scenic spots, and the misleading of the scenic spots photos is caused, so that the user experience is greatly reduced.
The current method for generating weather special effect video by a single picture in the industry mainly depends on GAN (GENERATIVE ADVERSARIAL Networks, an countermeasure generation network, a machine learning architecture proposed by the university of montreal, ian, good and in 2014, unlike the neural network introduced before, GAN is initially used as an unsupervised machine learning model), and mainly comprises the steps of inputting a picture and a reference picture to perform style migration, so that effects in the reference picture are generated in certain areas in the picture, such as a sunny picture and a rainy picture, the original sunny picture is darkened after style migration, and the effect of overcast and rainy days is achieved. However, the method has two problems, namely that the GAN based on style migration is an unsupervised network at present, the area for generating weather effect is uncontrollable, and the second problem is that some weather special effects need to be adjusted to the tone of the original picture, certain target areas of the original picture need to be generated with special effects, such as a rainy effect on a sunny picture of a city street, a moist effect on the road surface and eave of the street, and the existing GAN can not migrate only to a specific area.
Accordingly, the present invention provides a method, system, apparatus and storage medium for displaying advertisement images of travel products.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide the advertisement image display method, the system, the equipment and the storage medium for the tourist products, which overcome the difficulties in the prior art, and can automatically update the advertisement images of the related sceneries based on the reservation information of the user, so that the user can more accurately predict the sceneries in future tourists, the expected accuracy of the user is enhanced, and the user experience is improved.
The embodiment of the invention provides an advertisement image display method of a travel product, which comprises the following steps:
S110, receiving reservation information of the travel products, wherein the reservation information at least comprises keywords of names of the travel products, location information and future travel time periods;
S120, collecting pictures to form a picture sample library based on taking the same time period as the future travel time period as a shooting time as a screening condition at least according to the keywords and the place information in the picture library;
S130, performing first picture segmentation recognition according to the pictures of the picture sample library to obtain template image labels corresponding to the segmented areas, wherein the template image labels are preset to be mobilizable template image labels and non-mobilizable template image labels;
s140, performing machine learning on the picture preset as the transferable template image label to obtain a characteristic mask;
s150, carrying out second picture segmentation recognition on at least one advertisement image related to the travel product to obtain advertisement image labels corresponding to the segmented areas;
And S160, when the advertisement image label of the local area of the advertisement image is the same as the template image label preset as the movable template image label, mixing the characteristic mask corresponding to the movable template image label with the local area of the advertisement image and displaying the mixed image.
Preferably, the step S120 includes collecting, in a picture library, pictures satisfying the screening conditions, with the keyword as the picture title screening condition, the location information as the shooting location screening condition, and the future travel period and the same period as the shooting time screening condition, to form a picture sample library.
Preferably, in step S120, sorting and screening of the interaction indexes are performed on each photo according to praise and/or message leaving of the user in the photo sample library, and only N photos with top sorting are reserved as the photo sample library according to a preset threshold.
Preferably, in the step S130, the portable template image tag includes at least sky, road surface, snow, water accumulation and vegetation.
Preferably, the step S120 includes collecting, in a picture library, pictures meeting the screening conditions, with the keyword as a picture title screening condition, the location information as a shooting location screening condition, the future travel period and the same period as a shooting time screening condition, and weather prediction corresponding to the future travel period as a weather screening condition of the day of the shooting day, to form a picture sample library.
Preferably, the step S160 further includes,
When weather corresponding to the future travel time period is predicted to be rainy days, a second local area which is required to be projected and is right above a first local area of the advertisement image tag of the road surface is formed, and the second local area and the first local area are in mirror symmetry along the horizontal direction;
after mirror-turning the second local area along the horizontal direction, generating a mask image through a soft light algorithm;
at least the mask image is superimposed with the first partial region.
Preferably, in the step S150, the advertisement image includes an advertisement image and an advertisement video;
In step S160, when the advertisement image is an advertisement image, the advertisement image is split into video frames, and when the advertisement image label of the local area of each video frame is the same as the template image label preset to be movable, the feature mask corresponding to the movable template image label is mixed with the local area of the advertisement image, and then each video frame is split into the expected advertisement image according to the time sequence and displayed.
The embodiment of the invention also provides an advertisement image display system of the tourist product, which is used for realizing the advertisement image display method of the tourist product, and comprises the following steps:
the picture sample module is used for collecting pictures to form a picture sample library based on taking the same time period as the future travel time period as a shooting time according to at least the keywords and the place information in the picture library as a screening condition;
The image label module is used for carrying out first image segmentation recognition according to the photos of the image sample library to obtain template image labels corresponding to the segmented areas, wherein the template image labels are preset into mobilizable template image labels and non-mobilizable template image labels;
The feature mask module is used for performing machine learning on pictures preset as transferable template image labels to obtain a feature mask;
the image tag module is used for carrying out second image segmentation identification on at least one advertisement image related to the travel product to obtain advertisement image tags corresponding to the segmented areas;
And the image mixing module is used for mixing the characteristic mask corresponding to the movable template image label with the local area of the advertisement image and displaying the mixed image when the advertisement image label of the local area of the advertisement image is the same as the template image label preset as the movable template image label.
The embodiment of the invention also provides advertisement image display equipment of the travel product, which comprises:
A processor;
A memory having stored therein executable instructions of the processor;
Wherein the processor is configured to perform the steps of the advertisement image presentation method of the travel product described above via execution of the executable instructions.
Embodiments of the present invention also provide a computer-readable storage medium storing a program that, when executed, implements the steps of the advertisement image presentation method of a travel product described above.
The invention aims to provide an advertisement image display method, system, equipment and storage medium for tourist products, which can automatically update advertisement images of related sceneries based on reservation information of users, so that the users can more accurately predict sceneries in future tourists, the accuracy of user expectation is enhanced, and the user experience is improved.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings.
FIG. 1 is a flow chart of an advertising image display method of the travel product of the present invention.
Fig. 2 to 5 are schematic views showing the implementation process of the advertisement image display method of the travel product according to the present invention.
FIG. 6 is a block diagram of an advertising image display system for travel products of the present invention.
Fig. 7 is a schematic structural view of an advertising image display apparatus of a travel product according to the present invention.
Fig. 8 is a schematic structural view of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
Other advantages and effects of the present application will be readily apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present application by way of specific examples. The application may be practiced or carried out in other embodiments and with various details, and various modifications and alterations may be made to the details of the application from various points of view and applications without departing from the spirit of the application. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
The embodiments of the present application will be described in detail below with reference to the attached drawings so that those skilled in the art to which the present application pertains can easily implement the present application. This application may be embodied in many different forms and is not limited to the embodiments described herein.
In the context of the present description, reference to the terms "one embodiment," "some embodiments," "examples," "particular examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples, as well as features of various embodiments or examples, presented herein may be combined and combined by those skilled in the art without conflict.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the context of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
For the purpose of clarity of explanation of the present application, components that are not related to the explanation are omitted, and the same or similar components are given the same reference numerals throughout the description.
Throughout the specification, when a device is said to be "connected" to another device, this includes not only the case of "direct connection" but also the case of "indirect connection" with other elements interposed therebetween. In addition, when a certain component is said to be "included" in a certain device, unless otherwise stated, other components are not excluded, but it means that other components may be included.
When a device is said to be "on" another device, this may be directly on the other device, but may also be accompanied by other devices therebetween. When a device is said to be "directly on" another device in contrast, there is no other device in between.
Although the terms first, second, etc. may be used herein to connote various elements in some instances, the elements should not be limited by the terms. These terms are only used to distinguish one element from another element. For example, a first interface, a second interface, etc. Furthermore, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes," and/or "including" specify the presence of stated features, steps, operations, elements, components, items, categories, and/or groups, but do not preclude the presence, presence or addition of one or more other features, steps, operations, elements, components, items, categories, and/or groups. The terms "or" and/or "as used herein are to be construed as inclusive, or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of A, B, C, A and B, A and C, B and C, A, B and C". An exception to this definition will occur only when a combination of elements, functions, steps or operations are in some way inherently mutually exclusive.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the language clearly indicates the contrary. The meaning of "comprising" in the specification is to specify the presence of stated features, regions, integers, steps, operations, elements, and/or components, but does not preclude the presence or addition of other features, regions, integers, steps, operations, elements, and/or components.
Although not differently defined, including technical and scientific terms used herein, all have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The term addition defined in the commonly used dictionary is interpreted as having a meaning conforming to the contents of the related art document and the current hint, so long as no definition is made, it is not interpreted as an ideal or very formulaic meaning too much.
FIG. 1 is a flow chart of an advertising image display method of the travel product of the present invention. As shown in fig. 1, an embodiment of the present invention provides a method for displaying advertisement images of a travel product, including the following steps:
s110, receiving reservation information of the travel products, wherein the reservation information at least comprises keywords of names of the travel products, location information and future travel time periods.
S120, collecting pictures to form a picture sample library based on taking at least the keywords, the place information and the same time period as the future travel time period in the picture library as screening conditions.
S130, performing first picture segmentation recognition according to pictures in a picture sample library to obtain template image labels corresponding to the segmented areas, wherein the template image labels are preset into mobilizable template image labels and non-mobilizable template image labels.
And S140, performing machine learning on the picture preset as the transferable template image label to obtain the characteristic mask.
And S150, carrying out second picture segmentation recognition on at least one advertisement image related to the travel product, and obtaining advertisement image labels corresponding to the segmented areas. And
And S160, when the advertisement image label of the local area of the advertisement image is the same as the template image label preset as the movable template image label, mixing the characteristic mask corresponding to the movable template image label with the local area of the advertisement image, and displaying.
The invention discloses a weather special effect generation system based on image semantic segmentation, which automatically analyzes picture semantics of massive pictures in a scene of a travel product platform and can generate videos under two weather special effects of raining and snowing. In mass pictures in the scene of the current travel product platform, each picture has marked information such as related scenic spots, shooting time, shooting places, weather during shooting, seasons during shooting and the like through classification and arrangement of the pictures before, and machine learning after subsequent picture classification is performed, so that repeated description is omitted.
In a preferred embodiment, step S120 includes, but is not limited to, collecting pictures satisfying the screening conditions in a picture library to form a picture sample library, wherein the keywords are used as the picture title screening conditions, the location information is used as the shooting location screening conditions, and the future travel time period and the same period are used as the shooting time screening conditions.
In a preferred embodiment, step S120 further includes, in the picture sample library, sorting and screening the interactive indexes of each photo according to the praise and/or the message of the user, and only N photos with top sorting are reserved as the picture sample library according to a preset threshold, but not limited thereto.
In a preferred embodiment, in step S130, the movable template image tag includes at least sky, road surface, snow, water accumulation, vegetation, but not limited thereto.
In a preferred embodiment, step S120 includes, taking the keyword as a screening condition of the picture title, the location information as a screening condition of the shooting location, the future travel period and the same period as the screening condition of the shooting time, and the weather prediction corresponding to the future travel period as a screening condition of the weather on the day of shooting, collecting the pictures meeting the screening condition in the picture library to form a picture sample library, but not limited thereto.
In a preferred embodiment, step S160 further comprises,
When weather corresponding to a future travel period is predicted to be rainy days, a second local area which is required to be projected and is right above a first local area of the advertisement image tag with the road surface is mirror-symmetrical with the first local area along the horizontal direction;
after mirror-turning the second local area along the horizontal direction, generating a mask image through a soft light algorithm;
at least the mask image is superimposed on the first partial region, but not limited thereto.
In a preferred embodiment, in step S150, the advertisement image includes an advertisement image and an advertisement video;
In step S160, when the advertisement image is an advertisement image, the advertisement image is split into video frames, and when the advertisement image label of the local area of each video frame is the same as the template image label preset to be movable, the feature mask corresponding to the template image label to be movable is mixed with the local area of the advertisement image, and then each video frame is split into the expected advertisement image according to the time sequence and displayed, but not limited to this.
According to the method and the system, a weather special effect video system for generating a single picture can be built based on the existing image data, the fact that the picture ensures that a special effect generation area is controllable can be rapidly ensured, snowing or raining video generation is achieved, the richness of OTA hotels or POI display videos can be improved, user experience is improved, and the brand image of OTA is built.
Moreover, the generation of the special effect of the picture at the present stage mainly depends on a countermeasure generation network (Style GAN) based on transfer learning, and the effect of the model depends on the quality of a sample because the network is unsupervised training, and the effect of each semantic region is uncontrollable during the generation. For the first difficulty, the invention adopts a semantic segmentation model to segment the sky, vegetation, ground, water surface areas and the like of the picture at the pixel level, so that the area is controllable when the subsequent special effect is generated. For the special effect of raining, a wet ponding effect is generated aiming at a pavement area based on a traditional image algorithm, and for the special effect of snowing, a snow accumulation effect is mainly generated aiming at a pavement and vegetation based on the traditional image algorithm. And scoring the special effects generated by the areas by using a self-trained two-class evaluation model for each generated area, wherein areas with low scores are not generated. Compared with Style GAN, the method and the device realize the controllability of each region by leading one segmentation model, and only need to apply the traditional image algorithm to operate different regions for different effects without affecting other regions, thereby realizing special effect generation based on image understanding.
The invention provides a weather special effect generation system based on image semantic segmentation, which comprises the following steps of firstly carrying out semantic segmentation on a picture to obtain semantic information of each pixel, and implementing the scheme aiming at a raining effect and a snowing effect:
for the raining special effect, according to the separated ground positions, the area above the ground is projected on the ground to form a water accumulation effect, a raining green curtain video mask is added to generate a raining video, and finally, a soft light algorithm is applied to each frame of the whole video to darken the whole tone.
For the special snowing effect, the brightness and saturation of the whole graph are adjusted to form a snow cover, and then the snow cover is overlapped on vegetation, ground and other areas with fixed transparency to generate a single graph with snow effect. And then, the vegetation, ground and other areas on the graph enter a self-training two-classification model, whether the area needs to retain snow effect or not is judged according to the score output by the model, and the higher the score is, the better the generated effect is. And finally, adding a snowing green curtain video template to generate a snowing video, and finally, applying a soft light algorithm to each frame of the whole video to darken the whole tone.
Fig. 2 to 5 are schematic views showing the implementation process of the advertisement image display method of the travel product according to the present invention. Referring to fig. 2 to 5, one embodiment of the present invention is as follows:
Referring to fig. 2, first, a user inputs a target tourist site at a mobile phone terminal, and an advertisement photo 10 of a related scenic spot is displayed on a mobile phone page. The advertising photograph 10 in this embodiment is a photograph of a tourist attraction in autumn.
Referring to fig. 3, reservation information of the travel product input by the user is then received, wherein the reservation information includes at least keywords of the name of the travel product, location information and future travel time period, in this embodiment, "20220101" is selected by the user, and it is obvious that the season when the user arrives at the target travel place is winter (autumn photo in advertisement photo has no reference value at all, but rather a certain misleading effect is generated for the user).
Referring to fig. 4, a keyword is used as a picture title screening condition, location information is used as a shooting location screening condition, a future travel period and a same period are used as a shooting time screening condition, weather prediction corresponding to the future travel period is used as a weather screening condition of the day of shooting, and pictures meeting the screening condition are collected in a picture library to form a picture sample library. In this embodiment, different weather is used as different labels to obtain different picture sets, for example, a picture set with a sunny road surface, a picture set with a rainy road surface, a picture set with a snowy road surface, a picture set with a sunny mountain, a picture set with a rainy mountain, a picture set with a snowy mountain, a picture set with sunny vegetation, a picture set with rainy vegetation, a picture set with snowy vegetation, and so on, which are not described again.
And sorting and screening the interactive indexes of each photo in the photo sample library according to praise and/or messages of the user, and only preserving N photos with front sorting as the photo sample library according to a preset threshold value, wherein N is a natural number. And performing a first picture segmentation recognition according to the pictures of the picture sample library to obtain template image labels corresponding to the segmented areas, wherein the template image labels are preset as mobilizable template image labels and non-mobilizable template image labels, and the preset mobilizable template image labels at least comprise sky, road surfaces, snow, vegetation and the like, but are not limited to the above. And performing machine learning on the picture preset as the transferable template image label to obtain the characteristic mask. In this embodiment, an existing image machine learning manner is adopted to learn from the pictures in the picture set to generate the relevant feature mask, which is not described herein. And carrying out second picture segmentation identification on at least one advertisement image related to the travel product to obtain advertisement image labels corresponding to the segmented areas. Different functional areas corresponding to the mountain tag 11, the sky tag 12, and the ground tag 13 are identified in the advertisement photograph 10. And the weather corresponding to the future travel period is predicted to be snowy, and the picture set corresponding to each relevant label of the snowy is called as the picture set of the movable template image label.
Referring to fig. 5, when the advertisement image label of the local area of the advertisement image is the same as the template image label preset as the movable template image label, the feature mask corresponding to the movable template image label is mixed with the local area of the advertisement image (the mountain label 11, the sky label 12 and the ground label 13) and displayed.
According to the method and the system, a weather special effect video system for generating a single picture can be built based on the existing image data, the fact that the picture ensures that a special effect generation area is controllable can be rapidly ensured, snowing or raining video generation is achieved, the richness of OTA hotels or POI display videos can be improved, user experience is improved, and the brand image of OTA is built.
Moreover, the generation of the special effect of the picture at the present stage mainly depends on a countermeasure generation network (Style GAN) based on transfer learning, and the effect of the model depends on the quality of a sample because the network is unsupervised training, and the effect of each semantic region is uncontrollable during the generation. For the first difficulty, the invention adopts a semantic segmentation model to segment the sky, vegetation, ground, water surface areas and the like of the picture at the pixel level, so that the area is controllable when the subsequent special effect is generated. For the special effect of raining, a wet ponding effect is generated aiming at a pavement area based on a traditional image algorithm, and for the special effect of snowing, a snow accumulation effect is mainly generated aiming at a pavement and vegetation based on the traditional image algorithm. And scoring the special effects generated by the areas by using a self-trained two-class evaluation model for each generated area, wherein areas with low scores are not generated. Compared with Style GAN, the method and the device realize the controllability of each region by leading one segmentation model, and only need to apply the traditional image algorithm to operate different regions for different effects without affecting other regions, thereby realizing special effect generation based on image understanding.
The invention provides a weather special effect generation system based on image semantic segmentation, which comprises the following steps of firstly carrying out semantic segmentation on a picture to obtain semantic information of each pixel, and implementing the scheme aiming at a raining effect and a snowing effect:
for the raining special effect, according to the separated ground positions, the area above the ground is projected on the ground to form a water accumulation effect, a raining green curtain video mask is added to generate a raining video, and finally, a soft light algorithm is applied to each frame of the whole video to darken the whole tone.
For the special snowing effect, the brightness and saturation of the whole graph are adjusted to form a snow cover, and then the snow cover is overlapped on vegetation, ground and other areas with fixed transparency to generate a single graph with snow effect. And then, the vegetation, ground and other areas on the graph enter a self-training two-classification model, whether the area needs to retain snow effect or not is judged according to the score output by the model, and the higher the score is, the better the generated effect is. And finally, adding a snowing green curtain video template to generate a snowing video, and finally, applying a soft light algorithm to each frame of the whole video to darken the whole tone.
Another embodiment of the present invention is as follows:
(1) A picture is input.
(2) Currently, an open source Swin-transducer (Swin-transducer is a transducer backbone which can be used as a backbone and is proposed by Microsoft in the task of dense image prediction) semantic segmentation model is adopted, and data on a travel product platform is retrained and used as a semantic segmentation model, wherein the semantic segmentation model comprises the categories of sky, ground, vegetation, water surface and the like.
(3) Generating a rainy special effect (generating a rainy viewing screen mask):
(3.1) if the ground area is included, executing (3.2), (3.3), (3.4), and superposing the rainscreen mask and generating the rainvideo, and if the ground area is not included, executing only the superposition of the rainscreen mask and generating the rainvideo.
(3.2) Generating a ponding and reflection effect, wherein the size of an original image is assumed to be W.H, and the specific generating steps are as follows:
Calculating the maximum circumscribed rectangle of the ground area, wherein as a map possibly has a plurality of ground areas at the same time, firstly, a connected domain extraction algorithm based on opencv is applied to extract pixel values of the plurality of ground areas, and the pixel values are marked as C= { C i|ci＝{(xik,yik),(xin,yin) }, wherein C i represents the ith ground area, (x in,yin) represents the coordinate value of the nth pixel point in the ith ground area
For each ground connected domain, calculating a region to be projected, namely P= { P i|pi＝[xi1,yi1,xi2,yi2 ] }, wherein P i represents a rectangular region to be projected calculated by an ith ground region, x i1,yi1,xi2,yi2 represents coordinate values of an upper left corner and a lower right corner of P i respectively, and the specific calculation mode is as follows:
xi1＝min(ci(x))
yi1=0
xi2＝max(ci(x))
yi2＝min(ci(y))
c i (x) represents all x values in c i, and c i (y) represents all y values in c i.
Image inversion based on the x axis is performed on p i, so that a ground mask image p ' i with the width of x i2-xi1 and the height of y i2-,yi1 is generated, the size of p ' ′ is known as (max (the size of c i(x))-min(ci(x)))*min(ci(y)),ci is (max (c i(x))-min(ci(x)))*(max(ci(y))-min(ci (y)), the pixel coordinates in p ' i need to be corresponding to the coordinates in the region of the original image c i, and then the coordinates are superimposed with the ground region of the original image through transparency as alpha, and the corresponding specific calculation is:
c i (x, y) corresponds to p' i(x-min(ci(x)),y-min(ci (y))
(3.3) Obtaining a mask with the same size based on the water accumulation reflection with the same size as the original image after the execution of the step (3.2), and fusing the original image and the mask through a soft light algorithm, wherein the soft light algorithm is specifically calculated as follows:
C=2AB+A2*(1-2B),B≤0.5
A is an original image, B is a mask image, and C is a fused image.
(4) Generating snowy special effects:
(4.1) mapping the original image P from RGB space to HSL space and adjusting the brightness to For adjusting saturation toWherein the method comprises the steps ofAnd (3) withRanging from-100 to 100, being an adjustable parameter. Generating snow cover image P'
(4.2) Performing a mask superimposing operation with transparency α on vegetation and ground, respectively, assuming that the ground area in P is
The vegetation area is
The pixel points in the known P' are in one-to-one correspondence with the P, and the specific calculation process is as follows:
(4.3) pair And (3) respectively entering the connected domains into a classification evaluation model M, calculating score values corresponding to the domains, setting a threshold value, and reserving when the score values are larger than the threshold value.
The invention is based on weather special effect video generation of a single picture in an OTA scene, and semantic segmentation is carried out on the image by utilizing a segmentation method to obtain the category of each pixel. And extracting connected domains from the segmented binary image, and generating special effects on each connected domain by combining the labels of the pixels. The method can quickly and accurately generate the target special effect under the condition of controllable area, can generate the video under the condition of ensuring that the generated area is independent and accurate, and effectively improves the user experience in the OTA scene.
FIG. 6 is a block diagram of an advertising image display system for travel products of the present invention. As shown in fig. 6, the advertisement image display system 5 of the travel product of the present invention includes:
the sample providing module 51 provides sentence training texts, and each training sentence in the sentence training texts has at least one text preset label;
The digital sequence module 52 carries out Chinese word segmentation on the sentence training text to obtain words, and sequentially converts the text of the words in the training sentences into corresponding numbers according to a preset index dictionary to obtain a digital sequence of the training sentences and copy and expand the digital sequence once;
The network pre-training module 53 converts the digital sequence into a corresponding word vector matrix, and the vector matrix is respectively input into a neural network classification model for pre-training to obtain sentence coding vectors of training sentences;
the total loss calculation module 54 obtains model prediction tags of training sentences through a neural network classification model, obtains cross entropy loss and KL divergence calculation loss of two identical sentences according to tag class probability distribution of text preset tags and model prediction tags, and obtains total loss according to the cross entropy loss and the KL divergence calculation loss;
the iterative training module 55 is used for obtaining a neural network classification model with minimum total loss as a trained neural network classification model through iterative training;
The feature extraction module 56 removes the classifier in the neural network classification model, and takes the rest modules of the neural network classification model as feature extractors;
the sentence coding module 57 inputs sentence training texts into the feature extractor in the trained neural network classification model to obtain sentence coding vectors corresponding to training sentences;
a center vector module 58 for obtaining a center vector corresponding to each tag based on the average value of all sentence code vectors corresponding to the respective tags, and
The core sentence module 59 normalizes the center vector of the same tag and each sentence code vector, and then obtains the similarity between the center vector and each sentence code vector, and extracts training sentences corresponding to f (x) sentence code vectors with the highest similarity for each tag as core sentences.
The advertisement image display system of the travel product can automatically update the advertisement image of the related scenic spot based on the reservation information of the user, so that the user can more accurately predict scenic spots in future travel, the expected accuracy of the user is enhanced, and the user experience is improved.
The above embodiments are only preferred embodiments of the present invention and are not intended to limit the present invention, and any equivalent substitutions, modifications and variations made within the principle of the present invention are within the scope of the present invention.
The embodiment of the invention also provides advertisement image display equipment of the travel product, which comprises a processor. A memory having stored therein executable instructions of a processor. Wherein the processor is configured to execute the steps of the advertisement image presentation method of the travel product via execution of the executable instructions.
As shown above, the advertisement image display system of the travel product can automatically update the advertisement image of the related scenic spot based on the reservation information of the user, so that the user can more accurately predict the scenic spot in future travel, the expected accuracy of the user is enhanced, and the user experience is improved.
Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects that may be referred to herein collectively as a "circuit," module, "or" platform.
Fig. 7 is a schematic structural view of an advertising image display apparatus of a travel product according to the present invention. An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 7. The electronic device 600 shown in fig. 7 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 7, the electronic device 600 is in the form of a general purpose computing device. The components of electronic device 600 may include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting the different platform components (including storage unit 620 and processing unit 610), a display unit 640, and the like.
Wherein the storage unit stores program code executable by the processing unit 610 such that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above-described electronic prescription flow processing method section of the present specification. For example, the processing unit 610 may perform the steps as shown in fig. 1.
The storage unit 620 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 6201 and/or cache memory unit 6202, and may further include Read Only Memory (ROM) 6203.
The storage unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 630 may be a local bus representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or using any of a variety of bus architectures.
The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 600, and/or any device (e.g., router, modem, etc.) that enables the electronic device 600 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 650. Also, electronic device 600 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 over the bus 630. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 600, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, among others.
The embodiment of the invention also provides a computer readable storage medium for storing a program, and the steps of the advertisement image display method of the travel product are realized when the program is executed. In some possible embodiments, the aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the electronic prescription stream processing method section of this specification, when the program product is run on the terminal device.
As shown above, the advertisement image display system of the travel product can automatically update the advertisement image of the related scenic spot based on the reservation information of the user, so that the user can more accurately predict the scenic spot in future travel, the expected accuracy of the user is enhanced, and the user experience is improved.
Fig. 8 is a schematic structural view of a computer-readable storage medium of the present invention. Referring to fig. 8, a program product 800 for implementing the above-described method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of a readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable storage medium may also be any readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
In summary, the invention aims to provide a method, a system, a device and a storage medium for displaying advertisement images of tourist products, which can automatically update advertisement images of related sceneries based on reservation information of users, so that the users can more accurately predict sceneries in future tourists, the accuracy of user expectation is enhanced, and the user experience is improved.
The foregoing is a further detailed description of the invention in connection with the preferred embodiments, and it is not intended that the invention be limited to the specific embodiments described. It will be apparent to those skilled in the art that several simple deductions or substitutions may be made without departing from the spirit of the invention, and these should be considered to be within the scope of the invention.
Claims (9)
1. The advertisement image display method of the travel product is characterized by comprising the following steps of:
S110, receiving reservation information of the travel products, wherein the reservation information at least comprises keywords of names of the travel products, location information and future travel time periods;
S120, collecting pictures to form a picture sample library based on taking the same time period as the future travel time period as a shooting time as a screening condition at least according to the keywords and the place information in the picture library;
S130, performing first picture segmentation recognition according to the pictures of the picture sample library to obtain template image labels corresponding to the segmented areas, wherein the template image labels are preset to be mobilizable template image labels and non-mobilizable template image labels;
s140, performing machine learning on the picture preset as the transferable template image label to obtain a characteristic mask;
s150, carrying out second picture segmentation recognition on at least one advertisement image related to the travel product to obtain advertisement image labels corresponding to the segmented areas;
And S160, when the advertisement image label of the local area of the advertisement image is the same as the template image label preset as the movable template image label, mixing the characteristic mask corresponding to the movable template image label with the local area of the advertisement image and displaying the mixed image.
2. The method according to claim 1, wherein the step S120 includes collecting pictures satisfying the screening condition in a picture library to form a picture sample library, wherein the keywords are used as picture title screening conditions, the location information is used as shooting location screening conditions, and the future travel time period and period are used as shooting time screening conditions.
3. The method for displaying advertisement images of tourist products according to claim 2, wherein the step S120 further comprises sorting and screening the interactive index of each photo according to the praise and/or the message of the user in the photo sample library, and only keeping the top N photos as the photo sample library according to a preset threshold.
4. The method for displaying advertisement images of tourist products according to claim 1, wherein in step S130, the movable template image tag comprises at least sky, road surface, snow, water and vegetation.
5. The method according to claim 4, wherein the step S120 includes collecting, in a picture library, pictures satisfying the screening conditions, as a picture title screening condition, the location information as a shooting location screening condition, the future travel period and period as a shooting time screening condition, and weather predictions corresponding to the future travel period as a weather screening condition of a day of shooting.
6. The method according to claim 1, wherein in the step S150, the advertisement image includes advertisement images and advertisement videos;
In step S160, when the advertisement image is an advertisement image, the advertisement image is split into video frames, and when the advertisement image label of the local area of each video frame is the same as the template image label preset to be movable, the feature mask corresponding to the movable template image label is mixed with the local area of the advertisement image, and then each video frame is split into the expected advertisement image according to the time sequence and displayed.
7. An advertising image display system for a travel product for implementing the advertising image display method for a travel product as claimed in claim 1, comprising:
the information receiving module is used for receiving reservation information of the travel products, wherein the reservation information at least comprises keywords of names of the travel products, location information and future travel time periods;
the picture sample module is used for collecting pictures to form a picture sample library based on taking the same time period as the future travel time period as a shooting time according to at least the keywords and the place information in the picture library as a screening condition;
The image label module is used for carrying out first image segmentation recognition according to the photos of the image sample library to obtain template image labels corresponding to the segmented areas, wherein the template image labels are preset into mobilizable template image labels and non-mobilizable template image labels;
The feature mask module is used for performing machine learning on pictures preset as transferable template image labels to obtain a feature mask;
the image tag module is used for carrying out second image segmentation identification on at least one advertisement image related to the travel product to obtain advertisement image tags corresponding to the segmented areas;
And the image mixing module is used for mixing the characteristic mask corresponding to the movable template image label with the local area of the advertisement image and displaying the mixed image when the advertisement image label of the local area of the advertisement image is the same as the template image label preset as the movable template image label.
8. An advertising image display device for travel products, comprising:
A processor;
A memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the advertisement image presentation method of the travel product of any one of claims 1 to 6 via execution of the executable instructions.
9. A computer-readable storage medium storing a program, wherein the program when executed by a processor implements the steps of the advertisement image presentation method of a travel product according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111392295.8A CN113888564B (en) | 2021-11-19 | 2021-11-19 | Tourism product advertising image display method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111392295.8A CN113888564B (en) | 2021-11-19 | 2021-11-19 | Tourism product advertising image display method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113888564A CN113888564A (en) | 2022-01-04 |
| CN113888564B true CN113888564B (en) | 2025-03-21 |
Family
ID=79015441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111392295.8A Active CN113888564B (en) | 2021-11-19 | 2021-11-19 | Tourism product advertising image display method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113888564B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116383524B (en) * | 2023-04-11 | 2025-07-18 | 携程旅游���������术（上海）有限公司 | Image cover generation method, system, equipment and storage medium based on interest points |
| CN116431853B (en) * | 2023-04-14 | 2025-06-03 | 上海携旅信息技术有限公司 | Cover generation method, system, device and storage medium based on travel photo album |
| CN117848369B (en) * | 2023-12-28 | 2024-07-26 | 四川九正鼎盛城乡建设集团有限公司 | Interactive tour guide method and system for tourist highway |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629747A (en) * | 2018-04-25 | 2018-10-09 | 腾讯科技（深圳）有限公司 | Image enchancing method, device, electronic equipment and storage medium |
| CN108848271A (en) * | 2018-07-27 | 2018-11-20 | 深圳众思科技有限公司 | Method and mobile terminal based on real-time weather situation control wallpaper weather masking-out |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001344333A (en) * | 2000-05-30 | 2001-12-14 | Casio Comput Co Ltd | Travel information providing system |
| US10984286B2 (en) * | 2018-02-02 | 2021-04-20 | Nvidia Corporation | Domain stylization using a neural network model |
| CN113160101B (en) * | 2021-04-14 | 2023-08-01 | 中山大学 | A method for synthesizing high-fidelity images |
-
2021
- 2021-11-19 CN CN202111392295.8A patent/CN113888564B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629747A (en) * | 2018-04-25 | 2018-10-09 | 腾讯科技（深圳）有限公司 | Image enchancing method, device, electronic equipment and storage medium |
| CN108848271A (en) * | 2018-07-27 | 2018-11-20 | 深圳众思科技有限公司 | Method and mobile terminal based on real-time weather situation control wallpaper weather masking-out |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113888564A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113888564B (en) | Tourism product advertising image display method, system, device and storage medium | |
| CN113673338B (en) | Method, system and medium for weakly supervised automatic annotation of character pixels in natural scene text images | |
| WO2022242352A1 (en) | Methods and apparatuses for building image semantic segmentation model and image processing, electronic device, and medium | |
| US20200364461A1 (en) | Method of obtaining mask frame data, computing device, and readable storage medium | |
| CN116982089A (en) | Methods and systems for image semantic enhancement | |
| CN111476284A (en) | Image recognition model training method, image recognition model training device, image recognition method, image recognition device and electronic equipment | |
| US11871086B2 (en) | Method of displaying comment information, computing device, and readable storage medium | |
| CN111563502A (en) | Image text recognition method and device, electronic equipment and computer storage medium | |
| CN111199541A (en) | Image quality evaluation method, image quality evaluation device, electronic device, and storage medium | |
| TWI707296B (en) | Smart teaching consultant generation method, system, equipment and storage medium | |
| CN113411550B (en) | Video coloring method, device, equipment and storage medium | |
| WO2025016121A1 (en) | Image processing method and apparatus, and electronic device and storage medium | |
| CN116389849A (en) | Video generation method, device, equipment and storage medium | |
| Akallouch et al. | ASAYAR: A dataset for Arabic-Latin scene text localization in highway traffic panels | |
| CN110517270A (en) | A kind of indoor scene semantic segmentation method based on super-pixel depth network | |
| CN112949649B (en) | Text image identification method and device and computing equipment | |
| CN110766645A (en) | Generation method of target person recurrence map based on person recognition and segmentation | |
| CN112070040A (en) | Text line detection method for video subtitles | |
| CN118051591B (en) | Poster generation method, device and product based on large model | |
| Ouali et al. | Text detection and recognition using augmented reality and deep learning | |
| CN118695042B (en) | A video editing method based on diffusion model correspondence | |
| CN116645675A (en) | Character recognition method, device, equipment and medium | |
| CN112989097A (en) | Model training and picture retrieval method and device | |
| CN113762260B (en) | A layout image processing method, device, equipment and storage medium | |
| Shi et al. | AdaFI-FCN: an adaptive feature integration fully convolutional network for predicting driver’s visual attention |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |