CN115311850A - Sprinkler identification and early warning method and system based on crowdsourcing mode - Google Patents
Sprinkler identification and early warning method and system based on crowdsourcing mode Download PDFInfo
- Publication number
- CN115311850A CN115311850A CN202210833512.0A CN202210833512A CN115311850A CN 115311850 A CN115311850 A CN 115311850A CN 202210833512 A CN202210833512 A CN 202210833512A CN 115311850 A CN115311850 A CN 115311850A
- Authority
- CN
- China
- Prior art keywords
- projectile
- information
- data
- early warning
- vehicle
- 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.)
- Withdrawn
Links
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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees
Abstract
The utility model provides a projectile discernment and early warning method and system based on crowd-sourced mode, its is at the car end, through the vehicle data collection that traveles, discerns whether the projectile exists the projectile based on data to carry out the target location to the projectile, risk assessment, then with the projectile information upload high in the clouds: at the cloud end, after the information of the sprinkled object is received, whether the recorded information of the sprinkled object exists at the same position or not is judged firstly, if not, the information of the sprinkled object is recorded into newly found information of the sprinkled object, if so, the information of the sprinkled object is fused with the recorded information of the sprinkled object, the information of the sprinkled object is updated, and finally, early warning information of the sprinkled object is pushed to the terminal. The invention adopts a crowdsourcing mode, utilizes vehicle-mounted multi-sensor data of a large number of vehicles to identify the sprinklers based on crowdsourcing data and capacity of the large number of vehicles, and realizes iterative updating and issuing of the sprinklers at accurate positions on the road through cooperation with cloud information, so that accurate identification and early warning of the sprinklers on the road can be improved, the cost is reduced, and the safety of road driving is improved.
Description
Technical Field
The invention is used in the field of machine vision and intelligent traffic, and particularly relates to a road projectile identification and early warning method and system based on a crowdsourcing mode.
Background
In recent years, with the rapid development of economy in China, the traffic and transportation development is rapid, the total mileage on roads in China reaches 528 kilometers, the number of motor vehicles in China reaches 4.02 hundred million, and the traffic safety situation is increasingly severe. Driving safety has become a key concern during traveling, in which vehicle safety accidents caused by road spills (the spills are discarded or discarded tires, steel, cement, gravel, carton, wood blocks, pets and other road surface shelters that hinder driving safety) frequently occur. The road sprinkles bring great risks to the safe driving of vehicles, and threaten the life and property safety of drivers and passengers. How to quickly and accurately identify the sprinkled objects on the road, issue early warning information and timely eliminate the risk hidden danger, so that the guarantee of the smooth road safety becomes an important problem in the field of road safety.
By combing the existing related research and technical schemes, part of achievements are found in the field of road projectile detection. In the chinese patent "road surface toss detection method based on machine vision" (patent No. CN 111339824A), by acquiring each frame image in a video, a gaussian mixture model is used to realize the separation of a moving target from a background and form an enhanced moving target image, and then frame selection of a road surface toss area is realized based on YOLO v 3. The method can improve the accuracy of detection of the sprinkled object to a certain extent, but the single image processing technology still has misjudgment and missed judgment of the sprinkled object caused by illumination shadow, weather conditions and the like; meanwhile, the fixed camera is adopted to detect the sprinkled objects on the road section, and the defect that the detection coverage of the sprinkled objects on the road is not comprehensive enough exists. In addition, in the chinese patent "a road surface projectile early warning method, device and storage medium" (patent No. CN 114512006A), the moving trajectory of the projectile of the leading vehicle is sensed according to the laser radar and the camera of the vehicle, and the driving strategy of the vehicle is adjusted to ensure the driving safety of the vehicle. Although the identification method of the movement track of the projectile based on the laser radar and the camera is added, in the implementation process, whether the projectile exists or not and the volume of the projectile are judged by using radar data, and then the movement track of the projectile is judged by using video data, so that the defect that the whole method fails due to radar data judgment errors exists, and information obtained after the radar data and the video data are fused is not fully used. The above two patents (and similar ones) also have the drawback of not being clear as to where the projectile is located and the extent of its effect. Generally speaking, the projectile will stay on a certain lane and will have a traffic influence on the corresponding lane and adjacent lanes, so that the projectile will have a range of influences both laterally (perpendicular to the direction of extension of the lane) and longitudinally (parallel to the direction of extension of the lane), and for the position and influence of the projectile it is obvious that the projectile should be positioned at the lane level, and a single projectile describing the road would appear to be insufficient. At present along with the intelligent development of vehicle, the sensor that the vehicle carried is more and more, and how to utilize on-vehicle multisensor data to carry out the identification of throwing thing is a new direction and thinking, but the crowdsourcing data and the ability based on a large amount of vehicles simultaneously can reduce cost.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a method, a device, a storage medium and a system for identifying and early warning a road toss based on a crowdsourcing mode, wherein the toss are identified by utilizing vehicle-mounted multi-sensor data, and meanwhile, iterative updating and publishing of the information of the toss at accurate positions on a road are realized based on crowdsourcing data and capabilities of a large number of vehicles, so that the accurate identification and early warning of the road toss are improved, and the cost is reduced.
The technical scheme of the invention is as follows:
the invention provides a road projectile identification and early warning method based on a crowdsourcing mode in one aspect, which comprises the following steps: the method includes the steps that data are collected through a running vehicle at a vehicle end, whether a throwing object exists in the throwing object or not is recognized based on the data, target positioning and risk assessment are conducted on the throwing object, and then throwing object information is uploaded to a cloud end.
At the cloud end, after the information of the sprinkled object is received, whether the recorded information of the sprinkled object exists at the same position or not is judged firstly, if not, the information of the sprinkled object is recorded into newly found information of the sprinkled object, if so, the information of the sprinkled object is fused with the recorded information of the sprinkled object, the information of the sprinkled object is updated, and finally, early warning information of the sprinkled object is pushed to the terminal.
The method comprises the following specific steps:
at the vehicle end: step 301, acquiring data at a vehicle end when the vehicle is in running;
at the cloud: step 401, the cloud receives the projectile information and judges whether recorded projectile information exists in the same position; if not, go to step 402, if yes, go to step 403
The method further comprises the steps that the vehicle end monitors the sprinkled objects, the display is carried out after the vehicle end receives the early warning information of the sprinkled objects, meanwhile, whether the corresponding positions still have the passing conditions or not is judged according to the influence range of the sprinkled objects, if not, the roads are reselected, and if yes, the driving lanes are adjusted in advance according to the positions of the sprinkled objects and the influence lanes; and meanwhile, starting specific position projectile detection, detecting whether projectiles exist in corresponding positions, carrying out projectile target positioning and risk assessment if yes, and uploading projectile information to the cloud.
The method comprises the following specific steps:
and step 508, uploading the throwing object information to a cloud.
In the above technical scheme, the vehicle end and the cloud end mainly complete the following work:
1. identification of a projectile
When the vehicle runs, a sensor of the vehicle continuously collects surrounding environment data, a special identification module for identifying the front sprinkled object needs to be provided for improving the accuracy of the running vehicle in identifying the front sprinkled object, the radar data and the video data are firstly subjected to feature fusion by utilizing the module, and then the identification of the sprinkled object is further realized based on the fused feature data.
2. Determination of projectile position and impact
When a certain vehicle (simply called a vehicle) finishes the identification of a front throwing object, the position and the influence range of the throwing object are also expected to be accurately positioned, and at this time, the accurate position of the throwing object is solved by utilizing the relative position relation of the throwing object and the vehicle by combining the positioning data (through GNSS, IMU and wheel speed) of the vehicle, so that the lane occupied by the throwing object is determined, and the influence range of the throwing object is evaluated according to the type of the throwing object.
3. Sprinkler risk early warning issuing
On one hand, after the vehicle completes the identification of the front throwing object, the vehicle immediately generates throwing object warning information to remind the vehicle to adjust the traffic strategy. On the other hand, in order to realize sharing of the object throwing information, after the vehicle finishes determining the position and the influence range of the object throwing in front of the vehicle, early warning information is immediately uploaded to the cloud end, and the early warning information is pushed to the vehicle which is about to pass through the dangerous circuit break by the cloud end, so that the safety factor of subsequent passing vehicles is improved. Meanwhile, the cloud end also issues a projectile early warning message prompt to relevant departments so as to prompt cleaning of projectiles and comprehensively guarantee road driving safety.
4. Updating of projectile information
When other vehicles (other vehicles for short) approach the identified region where the projectile is located, the other vehicles complete the identification of the projectile again according to the projectile identification modules of the other vehicles and upload information to the cloud. And the cloud again processes the information of the sprinkled objects uploaded by other vehicles, and the latest state of the sprinkled objects (continuous early warning or early warning cancellation, influence range and the like) is issued after the cloud information is cooperated.
5. Display of early warning information of projectile
When other vehicles (other vehicles for short) connected to the system and related departments holding corresponding terminals receive early warning information of the sprinkled objects pushed by the cloud, the terminals provide the sprinkled object information (positions, influence ranges and the like) which is obviously displayed in a mode of combining audio and a map.
The technical scheme is different from the mode of identifying, positioning and early warning the information of the objects thrown by road condition information acquisition in the prior art, the method adopts a crowdsourcing mode, utilizes vehicle-mounted multi-sensor data of a large number of vehicles to identify the objects thrown by the vehicle-mounted multi-sensor data based on crowdsourcing data and capacity of the large number of vehicles, and realizes iterative updating and issuing of the information of the objects thrown by the precise positions on the road through cooperation with cloud information, so that the accurate identification and early warning of the objects thrown by the road can be improved, the cost is reduced, and the driving safety of the road is improved.
Drawings
Fig. 1 is a schematic diagram of an application of a crowd-sourced mode-based projectile identification and warning method.
Fig. 2 is a schematic block diagram of a crowd-sourced mode-based projectile identification and warning method.
Fig. 3 is a schematic flow chart of the vehicle end identifying and uploading the missiles on the road.
Fig. 4 is a schematic flow chart of the process of receiving and processing the projectile information by the cloud.
Fig. 5 is a schematic flow chart of the identification of a projectile in a specific location by the vehicle end.
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail and clearly with reference to the accompanying drawings.
Referring to fig. 1, the invention is a schematic flow of a projectile identification and early warning method based on a crowdsourcing mode, the invention adopts the crowdsourcing mode, the projectile information is detected by using running vehicles and uploaded to a cloud through a wireless network, the cloud cooperates with the projectile information reported by a plurality of vehicles, such as vehicles a and vehicles b in the figure, after receiving the projectile information, the cloud pushes the projectile information to each vehicle, and the vehicle end receives the projectile information and displays a prompt.
Referring to fig. 2, a system framework diagram of implementation of the method for identifying and warning a projectile based on a crowdsourcing mode includes module units at a vehicle end and a cloud end.
Specifically, the vehicle end includes:
the data acquisition module is used for acquiring data including radar data, video data, GNSS data, IMU data and wheel speed data during the running of the vehicle.
And the target identification module comprises a target detection unit and a feature fusion unit and is used for detecting based on the acquired data, performing feature fusion on the video data and the radar point cloud data, and completing identification of the projectile by using the data after the feature fusion.
The target positioning module comprises a target positioning unit and a vehicle positioning unit, the position of the vehicle is determined by using positioning data, then the accurate position of the projectile is determined based on the forward intersection principle, and meanwhile, a lane line is extracted by using the video frame image and the lane where the projectile is located is analyzed.
And the risk evaluation module comprises a grade evaluation unit and an influence evaluation unit and is used for carrying out grade evaluation on the risk and lane analysis on the influence of the sprinkled objects.
And the data transmission module comprises an information uploading unit and an information receiving unit and is used for uploading the projectile information to the cloud and receiving the early warning information pushed by the cloud.
Include in the high in the clouds:
and the data transmission module comprises an information pushing unit and an information receiving unit and is used for receiving the throwing object information uploaded by the vehicle end and pushing the early warning information to the vehicle end.
The crowd-sourced information fusion module is used for judging whether recorded projectile information exists in the same position or not according to the received projectile information; and if not, recording the projectile information as newly-found projectile information, if yes, fusing the projectile information with the recorded projectile information, and finally pushing projectile early warning information to the terminal.
And the data storage module is used for storing data.
In a further implementation of the invention, as shown in fig. 3, a schematic flow chart is provided in which the vehicle end identifies and uploads a projectile on the roadway. The method comprises the following implementation steps:
And step 302, judging whether the throwing object exists or not, and if the identification result is that the throwing object does not exist, directly ending the process.
And step 304, completing the risk analysis of the projectile on the basis of the information obtained by the step 303, and completing the grade evaluation of the risk and the lane analysis of the impact of the projectile in the process.
And 305, uploading the information of the projectile to the cloud after the complete information (position, influence range and the like) of the projectile is obtained.
And step 306, ending.
In another embodiment, as shown in fig. 4, a schematic flow chart of the process of receiving and processing the projectile information by the cloud is shown.
405, step 402, if there is no projectile information reported at the location, recording the projectile information as newly found projectile information, and proceeding to step 405.
And 403, if the position has the reported projectile information, triggering projectile information fusion, in the process, comparing the currently uploaded projectile information with the projectile information uploaded at the previous moment of the same position, judging whether the currently submitted projectile is the same as the projectile submitted at the previous moment, and if not, turning to 402 to mark as new projectile information.
If yes, the method performs fusion according to the confidence degrees of the front and back information and updates the throwing object information (position, influence range and the like), and then the step 405 is executed.
At this time, there may be two situations in the updating of the information of the projectile, one is that the projectile still exists but the information of the precise position, the influence range, etc. changes, and the other is that the projectile at this time does not exist, and for the different situations, the information types when the projectile is pushed are respectively marked as "update release" and "release", and the corresponding information type of the projectile which is found and pushed for the first time is marked as "release".
And step 405, finally, pushing the updated projectile information to the vehicle end.
As shown in fig. 5, this embodiment is a schematic flow of identifying a projectile in a specific location by a vehicle end, that is, after a vehicle has found that a projectile exists in a certain location, the cloud end pushes projectile information, and the vehicle end receives the projectile information and the rear end invokes projectile monitoring on the location. The process is as follows:
And 503, if the vehicle cannot pass, the vehicle end reselects the road, namely the travel route is changed in advance.
And step 504, if the vehicle can still pass through, the vehicle end adjusts the driving lane in advance according to the position of the sprinkled object and the affected lane, so that the affected lane can be avoided in advance.
And 505, adding a specific position projectile monitoring task at the vehicle end, starting specific position projectile identification at the vehicle end when the vehicle runs to the region where the projectile is located, namely monitoring whether the projectile exists at the corresponding position, and judging whether the projectile still exists after the specific position projectile identification is completed. If no throwing object exists in the specific position, the vehicle end uploads throwing object information which is not detected in the area to the cloud end in step 508.
If a specific location projectile is present, the location of the projectile is determined by calculation, step 506.
In step 507, the risk analysis of the projectile is completed on the basis of the information obtained in step 506.
And step 508, finally, uploading the projectile information to a cloud.
The preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, however, the present invention is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present invention within the technical idea of the present invention, and these simple modifications all fall within the protection scope of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. The invention is not described in detail in order to avoid unnecessary repetition. In addition, any combination of the various embodiments of the present invention is also possible, and the same should be considered as the disclosure of the present invention as long as it does not depart from the spirit of the present disclosure.
Claims (10)
1. The utility model provides a projectile discernment and early warning method based on crowdsourcing mode, its characterized in that, the method is in the car end, through the vehicle data collection that traveles, discerns whether there is the projectile on the basis of data to carry out the target location to the projectile, risk assessment, then with the projectile information upload cloud in the clouds:
at the cloud end, after the information of the sprinkled object is received, whether the recorded information of the sprinkled object exists at the same position or not is judged firstly, if not, the information of the sprinkled object is recorded into newly found information of the sprinkled object, if so, the information of the sprinkled object is fused with the recorded information of the sprinkled object, the information of the sprinkled object is updated, and finally, early warning information of the sprinkled object is pushed to the terminal.
2. The crowd-sourced mode-based projectile identification and early warning method of claim 1, wherein the method comprises,
at the vehicle end: step 301, acquiring data at a vehicle end when the vehicle is running;
step 302, the vehicle end identifies the throwing objects based on the acquired data, judges whether the throwing objects exist or not, if not, the flow is ended, and if yes, step 303 is carried out;
step 303, positioning the target of the throwing object;
step 304, performing risk assessment on the sprinkled object;
step 305, uploading the projectile information to the cloud:
at the cloud: step 401, the cloud receives the projectile information and judges whether recorded projectile information exists in the same position; if not, go to step 402, if yes, go to step 403
Step 402, recording the projectile information as newly found projectile information, and then performing step 405;
step 403, fusing the recorded projectile information;
step 404, updating the projectile information fusion;
step 405, the projectile warning information is pushed to the terminal.
3. The crowd-sourced mode-based projectile identification and warning method of claim 2, further comprising projectile monitoring: the vehicle end displays the early warning information after receiving the throwing object, judges whether the corresponding position still has a traffic condition according to the influence range of the throwing object, reselects a road if the corresponding position still has the traffic condition, and adjusts a driving lane in advance according to the position of the throwing object and the influence lane if the corresponding position does not have the traffic condition; and meanwhile, starting specific position projectile detection, detecting whether projectiles exist in corresponding positions, carrying out projectile target positioning and risk assessment if yes, and uploading projectile information to the cloud.
4. The crowd-sourced mode-based projectile identification and warning method of claim 3, wherein the projectile monitoring specific steps comprise:
step 501, a vehicle end receives early warning information of a projectile;
step 502, displaying early warning information of the projectile at the vehicle end, judging whether a corresponding position still has a passing condition according to the influence range of the projectile, if not, performing step 503, and if so, performing step 504;
step 503, the vehicle end reselects the road, and then the process is finished;
step 504, the vehicle end adjusts a driving lane in advance according to the position of the sprinkled object and the influence lane;
step 505, starting specific position projectile detection, detecting whether a corresponding position has a projectile, and if so, performing step 506; if not, step 508;
step 506, the target of the projectile is positioned,
step 507, estimating the risk of the sprinkled object;
and step 508, uploading the throwing object information to a cloud.
5. The method for identifying and warning sprinklers based on the crowdsourcing mode according to claim 2 or 4, wherein in the step 302 and the step 505, the vehicle end performs feature fusion on video data and radar point cloud data through a sprinkler identification module, and completes the identification of sprinklers by using the data after feature fusion.
6. The crowd-sourced mode-based projectile identification and early warning method as claimed in claim 2 or 4, wherein in the step 303 and the step 506, the projectile target location is to determine the position of the vehicle by using the location data, then determine the accurate position of the projectile based on the forward intersection principle, and simultaneously extract the lane line by using the video frame image and analyze the lane where the projectile is located.
7. The crowd-sourced mode-based projectile identification and warning method as claimed in claim 2 or 4, wherein said steps 304 and 507 comprise a risk level assessment and a lane analysis of projectile influence.
8. The crowd-sourced mode-based projectile identification and early warning method as claimed in claim 2 or 4, wherein the steps 305 and 508 are to upload the complete information of the projectile including location and influence range to the cloud.
9. The crowd-sourced mode-based projectile identification and early warning method according to claim 2 or 4, wherein in the step 403, the projectile information fusion is to determine whether the currently submitted projectile is the same projectile as the projectile submitted at the previous moment based on comparison between the currently uploaded projectile information and the projectile information uploaded at the previous moment at the same position, and if not, the step 402 is returned to; if so, go to step 404.
10. Sprinkler discernment and early warning system based on crowd-sourced mode, its characterized in that includes at the car end:
the data acquisition module is used for acquiring data including radar data, video data, GNSS data, IMU data and wheel speed data during the running of the vehicle;
the target identification module comprises a target detection unit and a feature fusion unit, and is used for detecting based on the acquired data, performing feature fusion on the video data and the radar point cloud data, and completing identification of the projectile by using the data after the feature fusion;
the target positioning module comprises a target positioning unit and a vehicle positioning unit, the position of the vehicle is determined by using positioning data, then the accurate position of the projectile is determined based on the forward intersection principle, and meanwhile, a lane line is extracted by using a video frame image and the lane where the projectile is located is analyzed;
the risk evaluation module comprises a grade evaluation unit and an influence evaluation unit and is used for carrying out grade evaluation on the risk and lane analysis on the influence of the sprinkled objects;
the data transmission module comprises an information uploading unit and an information receiving unit and is used for uploading the throwing object information to the cloud and receiving early warning information pushed by the cloud;
include in the high in the clouds:
the data transmission module comprises an information pushing unit and an information receiving unit and is used for receiving the projectile information uploaded by the vehicle end and pushing the early warning information to the vehicle end;
the crowd-sourced information fusion module is used for judging whether recorded projectile information exists in the same position or not according to the received projectile information; if not, the projectile information is recorded as newly found projectile information, if yes, the projectile information is fused with the recorded projectile information, and finally projectile early warning information is pushed to the terminal;
and the data storage module is used for storing data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210833512.0A CN115311850A (en) | 2022-07-15 | 2022-07-15 | Sprinkler identification and early warning method and system based on crowdsourcing mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210833512.0A CN115311850A (en) | 2022-07-15 | 2022-07-15 | Sprinkler identification and early warning method and system based on crowdsourcing mode |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115311850A true CN115311850A (en) | 2022-11-08 |
Family
ID=83857599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210833512.0A Withdrawn CN115311850A (en) | 2022-07-15 | 2022-07-15 | Sprinkler identification and early warning method and system based on crowdsourcing mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115311850A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105584485A (en) * | 2014-11-12 | 2016-05-18 | 通用汽车环球科技运作有限责任公司 | Use of participative sensing systems to enable enhanced road friction estimation |
| CN105711597A (en) * | 2016-02-25 | 2016-06-29 | 江苏大学 | System and method for sensing local driving environment in front |
| CN109101022A (en) * | 2018-08-09 | 2018-12-28 | 北京智行者科技有限公司 | A kind of working path update method |
| CN109143215A (en) * | 2018-08-28 | 2019-01-04 | 重庆邮电大学 | It is a kind of that source of early warning and method are cooperateed with what V2X was communicated based on binocular vision |
| CN110476077A (en) * | 2017-04-01 | 2019-11-19 | 华为技术有限公司 | Scan method, device and the system for controlling vehicle of trailer-mounted radar |
| CN110979321A (en) * | 2019-12-30 | 2020-04-10 | 北京深测科技有限公司 | Obstacle avoidance method for unmanned vehicle |
| WO2020103533A1 (en) * | 2018-11-20 | 2020-05-28 | 中车株洲电力机车有限公司 | Track and road obstacle detecting method |
| CN113674314A (en) * | 2021-07-14 | 2021-11-19 | 浙江大华技术股份有限公司 | Method and device for detecting throwing event, electronic device and storage medium |
| WO2021254175A1 (en) * | 2020-06-17 | 2021-12-23 | 华为技术有限公司 | Road safety monitoring method and system, and computer device |
| CN113869275A (en) * | 2021-10-15 | 2021-12-31 | 浙大宁波理工学院 | Vehicle object detection system that throws based on remove edge calculation |
| CN113920728A (en) * | 2021-10-11 | 2022-01-11 | 南京微达电子科技有限公司 | Detection and early warning method and system for obstacles thrown on expressway |
| CN114155500A (en) * | 2021-11-30 | 2022-03-08 | 联陆智能交通科技(上海)有限公司 | Abnormal road surface real-time acquisition and sharing system and method based on vehicle body sensor |
-
2022
- 2022-07-15 CN CN202210833512.0A patent/CN115311850A/en not_active Withdrawn
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105584485A (en) * | 2014-11-12 | 2016-05-18 | 通用汽车环球科技运作有限责任公司 | Use of participative sensing systems to enable enhanced road friction estimation |
| CN105711597A (en) * | 2016-02-25 | 2016-06-29 | 江苏大学 | System and method for sensing local driving environment in front |
| CN110476077A (en) * | 2017-04-01 | 2019-11-19 | 华为技术有限公司 | Scan method, device and the system for controlling vehicle of trailer-mounted radar |
| CN109101022A (en) * | 2018-08-09 | 2018-12-28 | 北京智行者科技有限公司 | A kind of working path update method |
| CN109143215A (en) * | 2018-08-28 | 2019-01-04 | 重庆邮电大学 | It is a kind of that source of early warning and method are cooperateed with what V2X was communicated based on binocular vision |
| WO2020103533A1 (en) * | 2018-11-20 | 2020-05-28 | 中车株洲电力机车有限公司 | Track and road obstacle detecting method |
| CN110979321A (en) * | 2019-12-30 | 2020-04-10 | 北京深测科技有限公司 | Obstacle avoidance method for unmanned vehicle |
| WO2021254175A1 (en) * | 2020-06-17 | 2021-12-23 | 华为技术有限公司 | Road safety monitoring method and system, and computer device |
| CN113674314A (en) * | 2021-07-14 | 2021-11-19 | 浙江大华技术股份有限公司 | Method and device for detecting throwing event, electronic device and storage medium |
| CN113920728A (en) * | 2021-10-11 | 2022-01-11 | 南京微达电子科技有限公司 | Detection and early warning method and system for obstacles thrown on expressway |
| CN113869275A (en) * | 2021-10-15 | 2021-12-31 | 浙大宁波理工学院 | Vehicle object detection system that throws based on remove edge calculation |
| CN114155500A (en) * | 2021-11-30 | 2022-03-08 | 联陆智能交通科技(上海)有限公司 | Abnormal road surface real-time acquisition and sharing system and method based on vehicle body sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109212514B (en) | Continuous tracking and associating method for moving and static targets by radar detection equipment | |
| JP4809321B2 (en) | Traffic information calculation device, traffic information calculation program, and traffic information calculation method | |
| CN110400478A (en) | A kind of road condition notification method and device | |
| US9604648B2 (en) | Driver performance determination based on geolocation | |
| CN105699095B (en) | A kind of test method of automatic driving vehicle | |
| CN103745595B (en) | Analyze method and system and the road condition analyzing server of traffic information | |
| CN102632839B (en) | Back sight image cognition based on-vehicle blind area early warning system and method | |
| CN105793910A (en) | Automatic driving assistance device, automatic driving assistance method, and program | |
| CN108769949A (en) | A kind of road test method of V2X equipment | |
| CN110264742B (en) | Vehicle-mounted information monitoring device suitable for expressway and warning method thereof | |
| CN110549941A (en) | pedestrian collision graded early warning method based on real-time information | |
| CN110428604B (en) | Taxi illegal parking monitoring and early warning method based on track and map data | |
| US10369995B2 (en) | Information processing device, information processing method, control device for vehicle, and control method for vehicle | |
| CN100589143C (en) | Method and appaatus for judging the traveling state of a floating vehicle | |
| CN108460968A (en) | A kind of method and device obtaining traffic information based on car networking | |
| CN1862620A (en) | Intelligent detecting prewarning method for expressway automobile running and prewaring system thereof | |
| CN103018754A (en) | Turning distinguishing method based on GPS (Global Position System) data | |
| CN107590999B (en) | Traffic state discrimination method based on checkpoint data | |
| CN216110866U (en) | Tunnel vehicle accident detection and early warning device based on RSSI | |
| CN101958043A (en) | Highway section calculation element hourage and method thereof | |
| CN205881163U (en) | Highway intelligence fog -zone bootstrap system | |
| CN112654892A (en) | Method for creating a map of an environment of a vehicle | |
| CN110182213A (en) | A kind of road condition detection method and corresponding system | |
| CN105374208A (en) | Method for reminding user of road condition and detecting state of camera, and device thereof | |
| CN114056324A (en) | Parking space identification method and system based on data fusion |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221108 |
|
| WW01 | Invention patent application withdrawn after publication |