CN111243274A - Road collision early warning system and method for non-internet traffic individuals - Google Patents
Road collision early warning system and method for non-internet traffic individuals Download PDFInfo
- Publication number
- CN111243274A CN111243274A CN202010064872.XA CN202010064872A CN111243274A CN 111243274 A CN111243274 A CN 111243274A CN 202010064872 A CN202010064872 A CN 202010064872A CN 111243274 A CN111243274 A CN 111243274A
- Authority
- CN
- China
- Prior art keywords
- traffic
- collision
- road
- target
- early warning
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 230000008447 perception Effects 0.000 claims abstract description 15
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000006855 networking Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 9
- 241000283070 Equus zebra Species 0.000 description 8
- 230000004913 activation Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000011176 pooling Methods 0.000 description 6
- 238000012806 monitoring device Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a road collision early warning system and method for non-internet traffic individuals, wherein the system comprises the following steps: the collision prediction analysis unit comprises a sensing unit, a collision prediction analysis unit and a warning unit; the perception unit is used for acquiring dynamic data of traffic individuals in a road in real time and sending the acquired dynamic data to the prediction analysis unit; the prediction analysis unit is used for carrying out collision prediction analysis on the traffic individuals in the road sections with different driving directions according to the received dynamic data to generate a collision prediction result; sending the collision prediction result to the warning unit; and the warning unit generates a collision early warning prompt according to the collision prediction result. The invention can reduce the collision risk of motor vehicles/non-motor vehicles/pedestrians on the road and improve the traffic safety of traffic individuals in the road under the condition of sensing the blind area.
Description
Technical Field
The invention relates to a road collision early warning system and method for non-internet traffic individuals, and belongs to the technical field of road traffic safety control.
Background
As vehicles gradually increase, road traffic problems become increasingly prominent. In order to alleviate the current traffic problem, an Internet of Vehicles (IoV) technology is developed, which aims to realize interconnection and intercommunication between Vehicles and roadside equipment and other Vehicles through V2X, so as to finally achieve the purpose of cooperative driving.
The car networking technology realizes interconnection and intercommunication between vehicles and road side equipment through V2V and V2I, thereby perfecting a plurality of applications under the car networking environment, such as: service navigation, path guidance, road environment early warning, rear-end collision early warning, curve blind area early warning, road collision early warning and the like. The road anti-collision early warning is an important application of vehicle-road cooperation in the vehicle networking technology, and aims to sense potential collision risks when a vehicle passes through road sections and send warning information to the vehicle in advance so that a driver can respond in advance, and therefore driving safety of the sections with multiple accidents is greatly improved.
However, the existing car networking technology is applied based on the fact that a vehicle road cooperation information vehicle-mounted terminal installed on a vehicle and a roadside device installed on the roadside communicate with each other. For example: the Chinese patent application No. CN201610587252.8 entitled vehicle-mounted binocular camera-based vehicle front collision early warning method discloses that a vehicle-mounted front binocular camera is used for obtaining the distance and motion information between an object in front of a vehicle and the vehicle, a rainfall sensor and a temperature sensor are used for estimating the road adhesion coefficient under the current weather, so that a safe vehicle distance threshold value corresponding to the current vehicle speed and the pre-collision time between the vehicle and the object in front are accurately calculated, two important vehicle running parameters of the safe vehicle distance and the pre-collision time are comprehensively considered, and emergency and non-emergency grading early warning is carried out according to different conditions to remind a vehicle driver of taking corresponding measures in time. The Chinese patent application number of CN201610228081.X entitled "a road intersection anti-collision early warning method, roadside equipment and anti-collision system" discloses that the roadside equipment arranged at an intersection receives GPS information sent by each vehicle through specific vehicle-mounted equipment, and performs collision prediction analysis on the GPS information data to generate early warning information, and forwards the early warning information to vehicles with potential collision risks.
The early warning difficulty for realizing the collision risk through the technical scheme is very high, so that the popularization of the car networking technology cannot be realized in a short time, and the early warning technology cannot be applied to the road collision early warning technology; in addition, the road collision early warning system based on the vehicle networking technology is not suitable for non-networked traffic individuals such as non-motor vehicles, pedestrians and the like.
Therefore, it is necessary to design a road collision early warning system and method for non-internet traffic individuals to early warn the collision which may be caused by the traffic individuals on the road being in the perception blind area.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a road collision early warning system and method for non-networked traffic individuals, and aims to solve the problem that the road collision early warning system based on the internet of vehicles technology in the prior art is not suitable for non-networked traffic individuals such as non-networked motor vehicles, non-motor vehicles and pedestrians. The invention can reduce the possibility of collision between the motor vehicles on the road and pedestrians/non-motor vehicles/motor vehicles, and greatly improves the driving safety of the communicating individuals on the road under the perception blind area.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention relates to a road collision early warning system facing non-internet traffic individuals, which comprises: the device comprises a sensing unit, a prediction analysis unit and a warning unit;
the perception unit is used for acquiring dynamic data of traffic individuals in a road in real time and sending the acquired dynamic data to the prediction analysis unit;
the prediction analysis unit is used for carrying out collision prediction analysis on the traffic individuals in the road sections with different driving directions according to the dynamic data to generate a collision prediction result; sending the collision prediction result to the warning unit;
and the warning unit generates a collision early warning prompt according to the collision prediction result and sends an early warning prompt to the traffic individuals possibly suffering from the collision risk.
Further, the sensing unit is one or a combination of a camera arranged on the road side, a laser radar and a millimeter wave radar.
Further, the traffic individuals include: automotive, non-automotive, pedestrian.
Further, the different driving direction sections include: the intersection motor vehicle lane, the intersection motor vehicle lane and the non-motor vehicle lane, the intersection motor vehicle lane and the crosswalk, the intersection non-motor vehicle lane and the crosswalk, the sharp turn road section, and the road section with the entrance and the exit in the lane.
Further, the dynamic data of the traffic individuals comprises: the real-time position information and the real-time speed information of the motor vehicle, the real-time position information and the real-time speed information of the non-motor vehicle, and the real-time position information and the real-time speed information of the pedestrian.
Further, the prediction analysis unit acquires real-time traffic signal lamp state information of each road section.
Further, the collision prediction analysis of the traffic individuals in the road sections with different driving directions by the prediction analysis unit specifically includes: (1) fusing traffic environment information and a high-precision map; (2) predicting the track of the traffic individual; (3) and predicting the collision of the traffic individuals in the target scene.
Further, the method for fusing the traffic environment information and the high-precision map specifically comprises the following steps:
marking a plurality of calibration points in a target area, wherein the calibration points can be fixed objects such as street lamps, zebra stripes, fences and the like, finding out the corresponding positions of the calibration points in an environment perception coordinate system and a high-precision map, finally obtaining an affine transformation matrix through the following formula (1), and fusing traffic environment information with the high-precision map through affine transformation;
wherein, X and Y are coordinates of a calibration point in a high-precision map, X and Y are coordinates of a calibration point in an environment perception coordinate system, and a1～a4，tx，tyThe matrix parameters are affine transformed.
Further, the traffic individual trajectory prediction method specifically comprises the following steps:
(21) synchronizing the position information of each moment of traffic individuals (pedestrians, non-motor vehicles, motor vehicles and the like) to a high-precision map;
(22) recording the position information of each target in the traffic environment at different moments, and providing a target speed equation as follows:
Vx＝αx1t+αx2t2+...+αxntn+δ (2)
Vy＝αy1t+αy2t2+...+αyntn+δ (3)
wherein, αx1,αx2,...,αxnAnd αy1,αy2,...,αynParameter, V, representing the equation of speedx,VyRepresenting the speed of the target in the x and y directions in a vehicle coordinate system at the moment t, wherein n represents the order of the equation and is a positive integer greater than 0;
(23) solving an object velocity equation, and providing a solving formula according to the position information and the velocity equation of each object at different moments as follows:
in the formula, i represents a time sequence, and m represents a statistical time length;
(24) and further obtaining a velocity equation parameter calculation formula by the solving formula:
ω＝(XTX)-1XTY
in the formula, ω represents
tiFor different momentsY represents the speed V of the target on the x and Y coordinate axes at different times0,V1,…Vi](ii) a And substituting the time and the speed V of each target by a formula to obtain a speed equation parameter, and substituting the parameters into the formulas (2) and (3) to obtain the speed equation.
Further, the method for predicting the collision of the traffic individuals in the target scene comprises the following specific steps:
(31) obtaining a speed equation of each target according to the step (2), and obtaining a target motion track, X, according to the following iterative equationi-1,Yi-1For the origin position, X, of the vehicle coordinate systemi,YiIs the post-iteration position; wherein, the track is divided into a front segment real motion track and a subsequent prediction track, and the latest moment T is recorded0Then T follows1，T2，T3···TnTo predict time of day (T)n-Tn-1) Smaller and more accurate; the iteration equation is as follows:
Xi＝Xi-1+Vx,i-1*(Ti-Ti-1)
Yi＝Yi-1+Vy,i-1*(Ti-Ti-1)
(32) obtaining a bounding box of each traffic target, and regarding the targets as rectangles to obtain the positions of the targets at the time to be predicted; namely, the position of each target boundary box and each target is known to judge whether the target is possible to collide.
Further, the warning unit includes: the alarm and the controller are electrically connected; the controller receives a collision prediction result sent by the prediction analysis unit and generates a control instruction for controlling the warning device to send out a warning prompt; and the warning indicator sends out a warning prompt according to the control instruction.
Furthermore, the prediction analysis unit generates a collision prediction result which contains the specific position information of the possible collision, and the controller analyzes the specific position information of the possible collision to obtain the alarm corresponding to the position and generates a control instruction for controlling the alarm.
Furthermore, the early warning prompt mode is one or a combination of multiple of light, characters and voice.
Furthermore, the warning indicator is a warning lamp or a warning screen arranged on the traffic signal lamp holder.
Furthermore, the warning device is a luminous spike arranged at two sides of the zebra crossing.
The invention relates to a road collision early warning method for non-internet traffic individuals, which comprises the following steps:
1) acquiring dynamic data of traffic individuals in a road in real time;
2) carrying out collision prediction analysis on the traffic individuals in the road sections in different driving directions according to the obtained dynamic data to generate a collision prediction result;
3) judging whether an early warning prompt needs to be sent or not according to a collision prediction result, and if so, generating a control instruction for controlling the alarm to send the early warning prompt; if not, repeating the step 3);
4) and carrying out collision early warning prompt.
Further, the step 1) specifically includes: acquiring dynamic data of each individual traffic in a road through one or a combination of a camera and a laser radar arranged on the road side, wherein the dynamic data comprises motor vehicle information, non-motor vehicle information and pedestrian information of the road surface; the collected information further includes: street lamps, zebra crossings, fences, buildings and the like.
Further, the step 2) specifically includes:
21) fusing traffic environment information and a high-precision map;
22) predicting the track of the traffic individual;
23) and predicting the collision of the traffic individuals in the target scene.
Further, the step 21) comprises the following specific steps:
marking a plurality of calibration points in a target area, wherein the calibration points can be fixed objects such as street lamps, zebra stripes, fences and the like, finding out the corresponding positions of the calibration points in an environment perception coordinate system and a high-precision map, finally obtaining an affine transformation matrix through the following formula (1), and fusing traffic environment information with the high-precision map through affine transformation;
wherein, X and Y are coordinates of a calibration point in a high-precision map, X and Y are coordinates of a calibration point in an environment perception coordinate system, and a1～a4，tx，tyThe matrix parameters are affine transformed.
Further, the step 22) comprises the following specific steps:
(221) synchronizing the position information of each moment of traffic individuals (pedestrians, non-motor vehicles, motor vehicles and the like) to a high-precision map;
(222) recording the position information of each target in the traffic environment at different moments, and providing a target speed equation as follows:
Vx＝αx1t+αx2t2+...+αxntn+δ (2)
Vy＝αy1t+αy2t2+...+αyntn+δ (3)
wherein, αx1,αx2,...,αxnAnd αy1,αy2,...,αynParameter, V, representing the equation of speedx,VyRepresenting the speed of the target in the x and y directions in a vehicle coordinate system at the moment t, wherein n represents the order of the equation and is a positive integer greater than 0;
(223) solving an object velocity equation, and providing a solving formula according to the position information and the velocity equation of each object at different moments as follows:
in the formula, i represents a time sequence, and m represents a statistical time length;
(224) and further obtaining a velocity equation parameter calculation formula by the solving formula:
ω＝(XTX)-1XTY
in the formula, ω represents
tiFor different time, Y represents the speed V of the target on the x and Y coordinate axes at different times0,V1,…Vi](ii) a And substituting the time and the speed V of each target by a formula to obtain a speed equation parameter, and substituting the parameters into the formulas (2) and (3) to obtain the speed equation.
Further, the step 23) comprises the following specific steps:
(231) obtaining a velocity equation of each target according to the step 22), and obtaining a motion trajectory of the target according to the following iterative equation, Xi-1,Yi-1For the origin position, X, of the vehicle coordinate systemi,YiIs the post-iteration position; wherein, the track is divided into a front segment real motion track and a subsequent prediction track, and the latest moment T is recorded0Then T follows1，T2，T3···TnIs a predicted time; the iteration equation is as follows:
Xi＝Xi-1+Vx,i-1*(Ti-Ti-1)
Yi＝Yi-1+Vy,i-1*(Ti-Ti-1)
(232) obtaining a bounding box of each traffic target, and regarding the targets as rectangles to obtain the positions of the targets at the time to be predicted; namely, knowing the boundary frame of each target and the position of each target, whether the target is possible to collide can be judged.
The invention has the beneficial effects that:
1. the method introduces methods such as deep learning image detection, image coordinate transformation, target track prediction and the like, can identify objects of the target area image, complete the fusion of the monitoring image and the high-precision map, accurately predict the running track of the target and the position of the target at each moment, and simultaneously predict the possibility of collision of each target.
2. The invention collects motor vehicle information, non-motor vehicle information and pedestrian information in real time, sends out early warning prompt after collision prediction, warns traffic individuals in a risk state in time, achieves early prediction of collision risk, and can early warn risk objects (pedestrians, motor vehicle drivers and non-motor vehicle drivers in a non-internet state) in the modes of character display, light warning, voice prompt and the like.
3. The method and the system can predict the collision and early warn for the non-internet traffic individuals, improve the driving safety of the road, reduce the frequency of traffic accidents of the traffic individuals in the road under the condition of perception blind areas, and are easy to popularize.
Drawings
Fig. 1 is a schematic view of a monitoring device installation and a scene.
Fig. 2 is a graph of target trace points and a fitted graph.
FIG. 3 is a flow chart illustrating single collision prediction.
Fig. 4 is a scene diagram before early warning in example one.
Fig. 5 is a scene diagram after the early warning in example one.
Fig. 6 is a scene diagram in example two.
Fig. 7 is a scene diagram in example three.
Fig. 8 is a scene diagram in example four.
Fig. 9 is a schematic diagram of the system of the present invention.
Detailed Description
In order to facilitate understanding of those skilled in the art, the present invention will be further described with reference to the following examples and drawings, which are not intended to limit the present invention.
Referring to fig. 9, the road collision early warning system for non-internet traffic individuals of the present invention includes: the device comprises a sensing unit, a prediction analysis unit and a warning unit;
the perception unit is used for acquiring dynamic data of traffic individuals in a road in real time and sending the acquired dynamic data to the prediction analysis unit; the perception unit is for locating one or its combination in the camera of roadside, the lidar, gathers the dynamic data of moving target on the road surface and includes: motor vehicle information, non-motor vehicle information, pedestrian information of the road surface; further comprising: street lamps, zebra crossings, fences, buildings, etc.;
the prediction analysis unit is used for carrying out collision prediction analysis on the traffic individuals in the road sections with different driving directions according to the received dynamic data to generate a collision prediction result; sending the collision prediction result to the warning unit;
the different driving direction road sections comprise: the intersection motor vehicle lane, the intersection motor vehicle lane and the non-motor vehicle lane, the intersection motor vehicle lane and the crosswalk, the intersection non-motor vehicle lane and the crosswalk, the sharp turn road section, and the road section with the entrance and the exit in the lane.
The specific collision prediction process includes: (1) fusing traffic environment information and a high-precision map; (2) predicting the track of the traffic individual; (3) and predicting the collision of the traffic individuals in the target scene.
The warning unit generates a collision early warning prompt according to the collision prediction result and sends an early warning prompt to traffic individuals possibly suffering from collision risks;
the warning unit includes: the alarm and the controller are electrically connected; the controller receives a collision prediction result sent by the prediction analysis unit and generates a control instruction for controlling the warning device to send out a warning prompt; and the warning indicator sends out a warning prompt according to the control instruction.
And (3) fusion of traffic environment information and a high-precision map:
marking some calibration points which can be fixed objects such as street lamps, zebra stripes, fences and the like in a target area, finding out corresponding positions of the calibration points in an environment perception coordinate system and a high-precision map, finally obtaining an affine transformation matrix through the following formula (1), and fusing traffic environment information with the high-precision map through affine transformation;
wherein X and Y are coordinates of the calibration point in the high-precision map, and X and Y are environmentThe coordinates of the index points in the perceptual coordinate system, a1～a4，tx，tyThe matrix parameters are affine transformed.
Predicting the track of the traffic individual:
(21) synchronizing the position information of each moment of the traffic individuals 2 (pedestrians, non-motor vehicles, motor vehicles and the like) to a high-precision map; as shown in fig. 1;
(22) recording the position information of each target in the traffic environment at different moments, and providing a target speed equation (in a vehicle coordinate system) as follows:
Vx＝αx1t+αx2t2+...+αxntn+δ (2)
Vy＝αy1t+αy2t2+...+αyntn+δ (3)
wherein, αx1,αx2,...,αxnAnd αy1,αy2,...,αynParameter, V, representing the equation of speedx,VyRepresenting the speed of the target in the x and y directions in a vehicle coordinate system at the moment t, wherein n represents the order of the equation and is a positive integer greater than 0;
(23) referring to fig. 2, 5 is a sampling point of each frame; solving an object velocity equation, and providing a solving formula according to the position information and the velocity equation of each object at different moments as follows:
in the formula, i represents a time sequence, and m represents a statistical time length;
(24) and further obtaining a velocity equation parameter calculation formula by the solving formula:
ω＝(XTX)-1XTY
in the formula, ω represents
tiFor different time, Y represents the speed V of the target on the x and Y coordinate axes at different times0,V1,…Vi](ii) a And substituting the time and the speed V of each target by a formula to obtain a speed equation parameter, and substituting the parameters into the formulas (2) and (3) to obtain the speed equation.
Predicting the collision of the traffic individuals in the target scene:
(31) obtaining a speed equation of each target according to the step (2), and obtaining a target motion track, X, according to the following iterative equationi-1,Yi-1For the origin position, X, of the vehicle coordinate systemi,YiIs the post-iteration position; wherein, the track is divided into a front segment real motion track 4 and a subsequent prediction track 6, and the latest moment T is recorded0Then T follows1，T2，T3···TnIs a predicted time; the iteration equation is as follows:
Xi＝Xi-1+Vx,i-1*(Ti-Ti-1)
Yi＝Yi-1+Vy,i-1*(Ti-Ti-1)
(32) in the example, monitoring equipment 1 (sensing unit) is installed around the road surface through a support 3, a camera is selected, and the image of the road surface is obtained at a certain frame rate. The monitoring device can also be fixed above the traffic light support or at the position of the street light, the distance from the ground is 3-5 meters, the wide angle of the monitoring device is larger than 120 degrees, the resolution is 1920 x 1080, and the image of the road surface is acquired in real time at the frame rate of 25-30 frames/second, as shown in fig. 1.
Collecting a large number of road surface images, converting RGB color space { R: [0,255], G: [0,255], B: [0,255] } of the group of images into { R: [ -1.0,1.0], G: ] [ -1.0,1.0], B: [ -1.0,1.0] }, recording the converted images as an image set img, wherein the conversion formula is as follows:
and labeling the acquired image set img, wherein the labeling information is arranged as { whether the region is a background, the center coordinates of the bounding box, the length of the bounding box and the width of the bounding box }, and is marked as a label set label.
In order to identify the target of the road, the image set img and the label set label are put into a neural network model Y for training, wherein the neural network model is as follows:
Y(img)＝label
the neural network design is shown in table 1:
TABLE 1
| Sequence of events | Categories | Number of filters | Size of | Step size | Size of filling |
| 0 | Convolution with a bit line | 16 | 3 | 1 | 1 |
| 1 | |
||||
| 2 | |
2 | 2 | 0 | |
| 3 | Convolution with a |
32 | 3 | 1 | 1 |
| 4 | |
||||
| 5 | |
2 | 2 | 0 | |
| 6 | Convolution with a bit line | 64 | 3 | 1 | 1 |
| 7 | |
||||
| 8 | |
2 | 2 | 0 | |
| 9 | Convolution with a bit line | 128 | 3 | 1 | 1 |
| 10 | |
||||
| 11 | |
2 | 2 | 0 | |
| 12 | Convolution with a bit line | 256 | 3 | 1 | 1 |
| 13 | |
||||
| 14 | |
2 | 2 | 0 | |
| 15 | Convolution with a bit line | 512 | 3 | 1 | 1 |
| 16 | Activation | ||||
| 17 | |
2 | 2 | 0 | |
| 18 | Convolution with a bit line | 512 | 3 | 1 | 1 |
| 19 | Convolution with a bit line | 1024 | 3 | 1 | 1 |
| 20 | Convolution with a |
6 | 3 | 1 | 1 |
Wherein the loss function for determining whether the location is a background or a target is used is:
in the formula, m is the number of image sets img, and k is the number of types of targets.
The penalty function for regressing the target location bounding box is:
loss＝||Y(img)-label||2；
the image new _ img (shown in figure 1) of the target scene is placed into a trained neural network model Y after color space conversion processing, and the position label new _ label of the target to be recognized in the image of the target scene is obtained, so that the target is recognized; obtaining a bounding box of each traffic target, and regarding the targets as rectangles to obtain the positions of the targets at the time to be predicted; that is, knowing the boundary frame of each target and the position of each target can judge whether the target is likely to collide; predicted collisions are illustrated with reference to FIG. 3; and if collision is possible, sending out an early warning prompt.
Example one:
referring to fig. 4, at the intersection of the road, a camera 11 (sensing unit) installed on the road side collects image information of a vehicle A, C driving from south to north in real time on the corresponding road section; the camera 15 collects image information of a vehicle B running from west to east of the corresponding road section in real time; the prediction analysis unit is a computer arranged at the roadside and used for acquiring image information acquired by the camera in an optical fiber communication mode; and judging whether the vehicles A and B collide according to the image information of the vehicles A and B and the real-time state information of the traffic signal lamps at the intersection. If the vehicles A and B are judged to be likely to collide, an alarm 14 arranged on the traffic signal lamp 13 sends out an early warning prompt to inform a driver of the vehicle A; the driver of vehicle a may perform the deceleration and braking actions to avoid vehicle B, which is safe to pass through the intersection, as shown in fig. 5. In addition, the vehicle B can also check the early warning information on the road in the driving direction through the warning indicator installed on the traffic signal lamp 12.
Example two:
referring to fig. 6, at the intersection of roads, the laser radar 23 installed on the road side collects the motion state of the pedestrian 21 in real time, and the laser radar 22 collects the motion state of the vehicle A, B, C, D in real time. The pedestrian 21 walks on the zebra crossing in the west-east driving direction, and the prediction analysis unit (not shown in the figure) is a computer arranged on the road side and used for predicting the driving motion track of the pedestrian 21 and the vehicle A, and if the vehicle A and the pedestrian 21 are judged to possibly collide, a display device 26 (namely an alarm) arranged on the road side sends out a text prompt to remind the vehicle A, C driving from north to south of paying attention to the zebra crossing pedestrian, so that the collision accident is avoided. To be more specific, when the pedestrian 21 walks to the front of the vehicle B to be turned left in the driving direction from south to north, the vehicle a and the pedestrian 21 are in the blind vision area and cannot observe the other side; at this time, the pedestrian signal lamp 24 is turned to the red state, the traffic signal lamp 25 for controlling the vehicle to travel from south to north is turned to the green state, and if the display device 26 does not issue a text prompt, the vehicle a is likely to collide with the pedestrian 21 after accelerating.
Example three:
referring to fig. 7, at the intersection of the ramp and the main road, a laser radar 31 (or a camera) installed in the road test collects the motion state data of the vehicles running on the main road and the ramp in real time; a prediction analysis unit (not shown in the figure) analyzes whether the vehicle 32 and the vehicle 33 running to the intersection collide with each other or not according to the collected motion state data, and if the vehicle 32 and the vehicle 33 are judged to possibly collide with each other, a display device 34 (namely an alarm) with a road side sends out a text prompt to prompt the vehicle 33 to decelerate and crawl so as to avoid collision; the vehicle 32 may perform deceleration running in accordance with the presentation of the display device 34.
Example four:
referring to fig. 8, at an intersection without a traffic light, a camera 41 installed in a road test collects motion state data of a vehicle running from south to north in real time, a camera 42 collects motion state data of the vehicle running from east to west in real time, and a prediction analysis unit (not shown in the figure) analyzes whether a vehicle a/C running to the intersection collides with a vehicle B according to the collected motion state data, and if it is determined that the vehicle a/C may collide with the vehicle B, a display device 43 (i.e., an alarm) provided with a roadside sends out a text prompt to prompt the vehicle running from south to north to slow down and avoid collision.
In other examples, the system of the invention can also be applied to a section with a sharp turn, a section with an entrance in a lane and other sections with collision risks.
While embodiments of the present invention have been described above, the present invention is not limited to the specific embodiments and applications described above, which are intended to be illustrative, instructive, and not limiting. Those skilled in the art, having the benefit of this disclosure, may effect numerous modifications thereto without departing from the scope of the invention as defined by the appended claims.
Claims (10)
1. The utility model provides a road collision early warning system towards non-networking traffic individual which characterized in that includes: the device comprises a sensing unit, a prediction analysis unit and a warning unit;
the perception unit is used for acquiring dynamic data of traffic individuals in a road in real time and sending the acquired dynamic data to the prediction analysis unit;
the prediction analysis unit is used for carrying out collision prediction analysis on the traffic individuals in the road sections with different driving directions according to the dynamic data to generate a collision prediction result; sending the collision prediction result to the warning unit;
and the warning unit generates a collision early warning prompt according to the collision prediction result and sends an early warning prompt to the traffic individuals possibly suffering from the collision risk.
2. The non-networked traffic individual-oriented road collision warning system according to claim 1, wherein the traffic individual comprises: automotive, non-automotive, pedestrian.
3. The non-internet traffic individual-oriented road collision warning system according to claim 1, wherein the different driving direction road sections comprise: the intersection motor vehicle lane, the intersection motor vehicle lane and the non-motor vehicle lane, the intersection motor vehicle lane and the crosswalk, the intersection non-motor vehicle lane and the crosswalk, the sharp turn road section, and the road section with the entrance and the exit in the lane.
4. The non-internet traffic individual-oriented road collision early warning system according to claim 1, wherein the performing collision prediction analysis on the traffic individuals in the road sections with different driving directions by the prediction analysis unit specifically comprises: (1) fusing traffic environment information and a high-precision map; (2) predicting the track of the traffic individual; (3) and predicting the collision of the traffic individuals in the target scene.
5. The non-internet traffic individual-oriented road collision early warning system according to claim 4, wherein the method for fusing the traffic environment information and the high-precision map comprises the following specific steps:
marking a plurality of calibration points in a target area, wherein the calibration points are fixed objects, finding out the corresponding positions of the calibration points in an environment perception coordinate system and a high-precision map, obtaining an affine transformation matrix through a following formula (1), and fusing traffic environment information with the high-precision map through affine transformation;
wherein, X and Y are coordinates of a calibration point in a high-precision map, X and Y are coordinates of a calibration point in an environment perception coordinate system, and a1～a4，tx，tyThe matrix parameters are affine transformed.
6. The non-internet traffic individual-oriented road collision early warning system according to claim 5, wherein the method for predicting the track of the traffic individual comprises the following specific steps:
(21) synchronizing the position information of each time of the traffic individual to a high-precision map;
(22) recording the position information of each target in the traffic environment at different moments, and providing a target speed equation as follows:
Vx＝αx1t+αx2t2+...+αxntn+δ (2)
Vy＝αy1t+αy2t2+...+αyntn+δ (3)
wherein, αx1,αx2,...,αxnAnd αy1,αy2,...,αynParameter, V, representing the equation of speedx,VyRepresenting the speed of the target in the x and y directions in a vehicle coordinate system at the moment t, wherein n represents the order of the equation and is a positive integer greater than 0;
(23) solving an object velocity equation, and providing a solving formula according to the position information and the velocity equation of each object at different moments as follows:
in the formula, i represents a time sequence, and m represents a statistical time length;
(24) and further obtaining a velocity equation parameter calculation formula by the solving formula:
ω＝(XTX)-1XTY
in the formula, ω represents [ α ]1,α1,…,αn,δ]T，
tiFor different time, Y represents the speed V of the target on the x and Y coordinate axes at different times0,V1,…Vi](ii) a Substituting each target by a formulaAnd (3) obtaining a speed equation parameter by processing the time and the speed V, and obtaining the speed equation by substituting the parameters into the formulas (2) and (3).
7. The non-internet traffic individual-oriented road collision early warning system according to claim 6, wherein the method for predicting the collision of the traffic individual in the target scene comprises the following specific steps:
(31) obtaining a speed equation of each target according to the step (2), and obtaining a target motion track, X, according to the following iterative equationi-1,Yi-1For the origin position, X, of the vehicle coordinate systemi,YiIs the post-iteration position; wherein, the track is divided into a front segment real motion track and a subsequent prediction track, and the latest moment T is recorded0Then T follows1，T2，T3···TnIs a predicted time; the iteration equation is as follows:
Xi＝Xi-1+Vx,i-1*(Ti-Ti-1)
Yi＝Yi-1+Vy,i-1*(Ti-Ti-1)
(32) obtaining a bounding box of each traffic target, and regarding the targets as rectangles to obtain the positions of the targets at the time to be predicted; namely, the position of each target boundary box and each target is known to judge whether the target is possible to collide.
8. A road collision early warning method for non-internet traffic individuals is characterized by comprising the following steps:
1) acquiring dynamic data of traffic individuals in a road in real time;
2) performing collision prediction analysis on the traffic individuals in the road sections in different driving directions according to the acquired dynamic data to generate a collision prediction result;
3) judging whether an early warning prompt needs to be sent or not according to a collision prediction result, and if so, generating a control instruction for controlling the alarm to send the early warning prompt; if not, repeating the step 3);
4) and carrying out collision early warning prompt.
9. The non-internet traffic individual-oriented road collision early warning method according to claim 8, wherein the step 1) specifically comprises: dynamic data of each individual traffic in the road, including motor vehicle information, non-motor vehicle information and pedestrian information of the road surface, are acquired through one or a combination of a camera and a laser radar which are arranged on the road side.
10. The non-internet traffic individual-oriented road collision early warning method according to claim 8, wherein the step 2) specifically comprises:
21) fusing traffic environment information and a high-precision map;
22) predicting the track of the traffic individual;
23) and predicting the collision of the traffic individuals in the target scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010064872.XA CN111243274A (en) | 2020-01-20 | 2020-01-20 | Road collision early warning system and method for non-internet traffic individuals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010064872.XA CN111243274A (en) | 2020-01-20 | 2020-01-20 | Road collision early warning system and method for non-internet traffic individuals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111243274A true CN111243274A (en) | 2020-06-05 |
Family
ID=70864194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010064872.XA Pending CN111243274A (en) | 2020-01-20 | 2020-01-20 | Road collision early warning system and method for non-internet traffic individuals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111243274A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627252A (en) * | 2020-06-10 | 2020-09-04 | 上海商汤智能科技有限公司 | Vehicle early warning method and device, electronic equipment and storage medium |
| CN112098969A (en) * | 2020-11-18 | 2020-12-18 | 长沙莫之比智能科技有限公司 | Target detection and early warning optimization method for millimeter wave large vehicle blind area radar |
| CN112700470A (en) * | 2020-12-30 | 2021-04-23 | 上海智能交通有限公司 | Target detection and track extraction method based on traffic video stream |
| CN113345267A (en) * | 2021-06-03 | 2021-09-03 | 招商局检测车辆技术研究院有限公司 | Crossing approaching signal area early warning method and system based on generalized V2X |
| CN113362601A (en) * | 2021-06-15 | 2021-09-07 | 中山大学 | Man-vehicle collision avoidance control method and system based on intelligent lamp pole communication technology |
| CN113628444A (en) * | 2021-08-12 | 2021-11-09 | 智道网联科技(北京)有限公司 | Method, device and computer-readable storage medium for prompting traffic risk |
| CN114038239A (en) * | 2021-11-08 | 2022-02-11 | 青岛海信网络科技��份有限公司 | Vehicle collision early warning method and device |
| CN114187759A (en) * | 2021-11-19 | 2022-03-15 | 东南大学 | A roadside unit driving assistance method and device based on a data-driven model |
| CN114530058A (en) * | 2022-03-03 | 2022-05-24 | 恒大恒驰新能源汽车研究院(上海)有限公司 | Collision early warning method, device and system |
| CN115188219A (en) * | 2022-07-12 | 2022-10-14 | 陈升俊 | Accident black spot blind area prompt system based on RFID |
| CN115691213A (en) * | 2021-07-29 | 2023-02-03 | 北京万集科技股份有限公司 | Early warning method, device, equipment and readable storage medium |
| CN116129675A (en) * | 2023-01-17 | 2023-05-16 | 中信科智联科技有限公司 | Method, device and equipment for early warning of collision between people and vehicles |
| WO2023221118A1 (en) * | 2022-05-20 | 2023-11-23 | 北京小米移动软件有限公司 | Information processing methods and apparatus, electronic device, and storage medium |
| CN117218895A (en) * | 2023-10-18 | 2023-12-12 | 哈尔滨工业大学 | Conflict detection method between autonomous vehicles and pedestrians based on potential collision determination |
| CN117710909A (en) * | 2024-02-02 | 2024-03-15 | 多彩贵州数字科技股份有限公司 | Rural road intelligent monitoring system based on target detection and instance segmentation |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604419A (en) * | 2009-07-16 | 2009-12-16 | 浙江大学 | A Method for Automatically Extracting Proposed Locations of Construction Projects |
| CN104376154A (en) * | 2014-10-31 | 2015-02-25 | 中国科学院苏州生物医学工程技术研究所 | Rigid-body collision track prediction display unit |
| GB2518187A (en) * | 2013-09-12 | 2015-03-18 | Ford Global Tech Llc | Collision warning for a driver controlled vehicle |
| CN105206108A (en) * | 2015-08-06 | 2015-12-30 | 同济大学 | Early warning method against vehicle collision based on electronic map |
| CN105374231A (en) * | 2014-08-27 | 2016-03-02 | 中国移动通信集团公司 | Early warning method, device and system |
| CN105761547A (en) * | 2016-03-28 | 2016-07-13 | 安徽云森物联网科技有限公司 | Traffic collision pre-warning technique and system based on images |
| CN106485735A (en) * | 2015-09-01 | 2017-03-08 | 南京理工大学 | Human body target recognition and tracking method based on stereovision technique |
| CN106530825A (en) * | 2016-11-16 | 2017-03-22 | 淮阴工学院 | Method for detecting traffic conflict between motor-assisted bicycle and automobile based on ST-MRF model |
| CN107221197A (en) * | 2017-07-26 | 2017-09-29 | 维沃移动通信有限公司 | A kind of information processing method and intelligent terminal |
| CN108172025A (en) * | 2018-01-30 | 2018-06-15 | 东软集团股份有限公司 | A kind of auxiliary driving method, device, car-mounted terminal and vehicle |
| CN109080629A (en) * | 2017-06-14 | 2018-12-25 | 福特全球技术公司 | The method of cross traffic is considered while vehicle is driven out to and executes the vehicle of this method |
| CN109671297A (en) * | 2017-10-16 | 2019-04-23 | 大众汽车有限公司 | Avoid collision method, road user vehicle, other vehicles and computer program |
-
2020
- 2020-01-20 CN CN202010064872.XA patent/CN111243274A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604419A (en) * | 2009-07-16 | 2009-12-16 | 浙江大学 | A Method for Automatically Extracting Proposed Locations of Construction Projects |
| GB2518187A (en) * | 2013-09-12 | 2015-03-18 | Ford Global Tech Llc | Collision warning for a driver controlled vehicle |
| CN105374231A (en) * | 2014-08-27 | 2016-03-02 | 中国移动通信集团公司 | Early warning method, device and system |
| CN104376154A (en) * | 2014-10-31 | 2015-02-25 | 中国科学院苏州生物医学工程技术研究所 | Rigid-body collision track prediction display unit |
| CN105206108A (en) * | 2015-08-06 | 2015-12-30 | 同济大学 | Early warning method against vehicle collision based on electronic map |
| CN106485735A (en) * | 2015-09-01 | 2017-03-08 | 南京理工大学 | Human body target recognition and tracking method based on stereovision technique |
| CN105761547A (en) * | 2016-03-28 | 2016-07-13 | 安徽云森物联网科技有限公司 | Traffic collision pre-warning technique and system based on images |
| CN106530825A (en) * | 2016-11-16 | 2017-03-22 | 淮阴工学院 | Method for detecting traffic conflict between motor-assisted bicycle and automobile based on ST-MRF model |
| CN109080629A (en) * | 2017-06-14 | 2018-12-25 | 福特全球技术公司 | The method of cross traffic is considered while vehicle is driven out to and executes the vehicle of this method |
| CN107221197A (en) * | 2017-07-26 | 2017-09-29 | 维沃移动通信有限公司 | A kind of information processing method and intelligent terminal |
| CN109671297A (en) * | 2017-10-16 | 2019-04-23 | 大众汽车有限公司 | Avoid collision method, road user vehicle, other vehicles and computer program |
| CN108172025A (en) * | 2018-01-30 | 2018-06-15 | 东软集团股份有限公司 | A kind of auxiliary driving method, device, car-mounted terminal and vehicle |
Non-Patent Citations (3)
| Title |
|---|
| 吴立烜: "公路交通流动态诱导信息系统建设研究", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技Ⅱ辑》 * |
| 岳东杰: "地图扫描矢量化误差的最小二乘配置法处理研究", 《测绘科学》 * |
| 秦永: "遥感影像支持的实时导航应用研究", 《测绘科学》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627252A (en) * | 2020-06-10 | 2020-09-04 | 上海商汤智能科技有限公司 | Vehicle early warning method and device, electronic equipment and storage medium |
| CN112098969A (en) * | 2020-11-18 | 2020-12-18 | 长沙莫之比智能科技有限公司 | Target detection and early warning optimization method for millimeter wave large vehicle blind area radar |
| CN112098969B (en) * | 2020-11-18 | 2021-02-02 | 长沙莫之比智能科技有限公司 | Target detection and early warning optimization method for millimeter wave large vehicle blind area radar |
| CN112700470B (en) * | 2020-12-30 | 2023-12-08 | 上海智能交通有限公司 | A method of target detection and trajectory extraction based on traffic video streams |
| CN112700470A (en) * | 2020-12-30 | 2021-04-23 | 上海智能交通有限公司 | Target detection and track extraction method based on traffic video stream |
| CN113345267A (en) * | 2021-06-03 | 2021-09-03 | 招商局检测车辆技术研究院有限公司 | Crossing approaching signal area early warning method and system based on generalized V2X |
| CN113345267B (en) * | 2021-06-03 | 2022-11-29 | 招商局检测车辆技术研究院有限公司 | Intersection near signal area early warning method and system based on generalized V2X |
| CN113362601A (en) * | 2021-06-15 | 2021-09-07 | 中山大学 | Man-vehicle collision avoidance control method and system based on intelligent lamp pole communication technology |
| CN115691213A (en) * | 2021-07-29 | 2023-02-03 | 北京万集科技股份有限公司 | Early warning method, device, equipment and readable storage medium |
| CN113628444A (en) * | 2021-08-12 | 2021-11-09 | 智道网联科技(北京)有限公司 | Method, device and computer-readable storage medium for prompting traffic risk |
| CN114038239B (en) * | 2021-11-08 | 2022-11-25 | 青岛海信网络科技股份有限公司 | Vehicle collision early warning method and device |
| CN114038239A (en) * | 2021-11-08 | 2022-02-11 | 青岛海信网络科技股份有限公司 | Vehicle collision early warning method and device |
| CN114187759A (en) * | 2021-11-19 | 2022-03-15 | 东南大学 | A roadside unit driving assistance method and device based on a data-driven model |
| CN114530058A (en) * | 2022-03-03 | 2022-05-24 | 恒大恒驰新能源汽车研究院(上海)有限公司 | Collision early warning method, device and system |
| WO2023221118A1 (en) * | 2022-05-20 | 2023-11-23 | 北京小米移动软件有限公司 | Information processing methods and apparatus, electronic device, and storage medium |
| CN117441350A (en) * | 2022-05-20 | 2024-01-23 | 北京小米移动软件有限公司 | Information processing methods and devices, electronic equipment and storage media |
| CN115188219A (en) * | 2022-07-12 | 2022-10-14 | 陈升俊 | Accident black spot blind area prompt system based on RFID |
| CN116129675A (en) * | 2023-01-17 | 2023-05-16 | 中信科智联科技有限公司 | Method, device and equipment for early warning of collision between people and vehicles |
| CN117218895A (en) * | 2023-10-18 | 2023-12-12 | 哈尔滨工业大学 | Conflict detection method between autonomous vehicles and pedestrians based on potential collision determination |
| CN117218895B (en) * | 2023-10-18 | 2024-09-10 | 哈尔滨工业大学 | Conflict detection method between autonomous driving vehicles and pedestrians based on potential collision judgment |
| CN117710909A (en) * | 2024-02-02 | 2024-03-15 | 多彩贵州数字科技股份有限公司 | Rural road intelligent monitoring system based on target detection and instance segmentation |
| CN117710909B (en) * | 2024-02-02 | 2024-04-12 | 多彩贵州数字科技股份有限公司 | Rural road intelligent monitoring system based on target detection and instance segmentation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111243274A (en) | Road collision early warning system and method for non-internet traffic individuals | |
| CN110264783B (en) | Vehicle anti-collision early warning system and method based on vehicle-road cooperation | |
| CN111223302B (en) | External coordinate real-time three-dimensional road condition auxiliary device for mobile carrier and system | |
| CN112700470B (en) | A method of target detection and trajectory extraction based on traffic video streams | |
| CN109242251B (en) | Driving behavior safety detection method, device, equipment and storage medium | |
| CN113147733B (en) | Intelligent speed limiting system and method for automobile in rain, fog and sand dust weather | |
| CN107346612B (en) | Vehicle anti-collision method and system based on Internet of vehicles | |
| US11912286B2 (en) | Driving risk identification model calibration method and system | |
| CN113453263B (en) | A Vehicle-Infrastructure Cooperative V2I Simulation Test System and Method | |
| JP7072133B2 (en) | Driver control operation quantification method and device based on the minimum action amount principle | |
| CN114419874B (en) | Target driving safety risk early warning method based on roadside sensing device data fusion | |
| CN110446278A (en) | Intelligent driving automobile sensor blind area method of controlling security and system based on V2I | |
| CN116564116A (en) | Intelligent assisted driving guidance system and method driven by digital twin | |
| CN110634297B (en) | Signal lamp state identification and passing control system based on vehicle-mounted laser radar | |
| CN112116031A (en) | Target fusion method and system based on road side equipment, vehicle and storage medium | |
| CN113851017A (en) | Pedestrian and vehicle identification and early warning multifunctional system based on road side RSU | |
| CN112140995A (en) | Intelligent automobile safe driving system based on network cloud | |
| US12469394B2 (en) | Centralized prediction and planning for improving lane platooning and intersection vehicle behavior | |
| CN113178081A (en) | Vehicle immission early warning method and device and electronic equipment | |
| CN112185170B (en) | Traffic safety reminder method and road monitoring equipment | |
| CN114872734A (en) | Automatic driving emergency decision-making method | |
| CN111301396B (en) | Smart driving test | |
| AU2024227350A1 (en) | Improved motion tracking for autonomous vehicle driving | |
| US12086904B2 (en) | Reality image reconstruction system | |
| CN111915916A (en) | Prompting method and system for whole highway section |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |
|
| RJ01 | Rejection of invention patent application after publication |