CN115273023A - Vehicle-mounted road pothole identification method and system and automobile - Google Patents

Vehicle-mounted road pothole identification method and system and automobile Download PDF

Info

Publication number
CN115273023A
CN115273023A CN202210796921.8A CN202210796921A CN115273023A CN 115273023 A CN115273023 A CN 115273023A CN 202210796921 A CN202210796921 A CN 202210796921A CN 115273023 A CN115273023 A CN 115273023A
Authority
CN
China
Prior art keywords
vehicle
road
pothole
front road
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210796921.8A
Other languages
Chinese (zh)
Inventor
王乔木
郑兴
何纯华
赵曜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Changan New Energy Automobile Technology Co Ltd
Original Assignee
Chongqing Changan New Energy Automobile Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Changan New Energy Automobile Technology Co Ltd filed Critical Chongqing Changan New Energy Automobile Technology Co Ltd
Priority to CN202210796921.8A priority Critical patent/CN115273023A/en
Publication of CN115273023A publication Critical patent/CN115273023A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Business, Economics & Management (AREA)
  • Multimedia (AREA)
  • Human Resources & Organizations (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Automation & Control Theory (AREA)
  • Strategic Management (AREA)
  • Software Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to a vehicle-mounted road pothole identification method, a vehicle-mounted road pothole identification system and an automobile, wherein the method comprises the following steps: the camera collects data of a front road in real time; judging whether a front road has a covering vehicle or not; if the hidden vehicle does not exist, judging whether a pothole exists in the front road or not based on the front road image information; if the hidden vehicle exists, whether the front road has a pothole or not is judged based on the shaking range of the hidden vehicle. The method and the system are based on the visual identification technology, carry out hollow judgment based on real-time road conditions, have better real-time performance, simultaneously divide the road conditions into two scenes, and distinguish identification modes aiming at the two scenes, so that the identification accuracy is improved, further, the method and the system can analyze and early warn the road hollow risks under all road conditions, and the comfort and the safety of hollow road sections during automatic driving are improved.

Description

Vehicle-mounted road depression identification method and system and automobile
Technical Field
The invention relates to the technical field of automatic driving, in particular to an image recognition technology.
Background
With the development of intelligent driving technology, vehicles using IACC (integrated adaptive cruise control) are increasing on roads, and when the vehicles with these functions run on a pothole road, due to the problems of the recognition rate of the scene and the like, the vehicles do not have an effective deceleration strategy or avoidance strategy for the scene, so that a serious safety accident or poor driving experience is caused. Particularly, in the process of driving on a highway, a driver uses related functions of automatic driving, the attention of the driver is probably not in the front, effective human interference is not done on a hollow road section, the intelligent driving system visual perception module does not achieve effective identification, and a vehicle passes through a hollow position at a high speed, so that accidents such as tire burst, out-of-control and the like are easily caused, and great potential safety hazards are caused. At present, when the driver touches a hollow road section, the driver is mainly reminded by acquiring road condition information through vehicle navigation or a high-precision map, and risks are avoided.
The road condition information updating of vehicle navigation or high-precision maps needs a certain period, the real-time performance of data is not high, and part of data is uploaded by a vehicle owner and lacks reliable digital support.
The prior art provides a vehicle-mounted road pothole reminding method and system based on big data, and the method comprises the following steps: collecting road image information of a front road in the driving process of a vehicle; when the road surface of the road in front is judged to have the potholes, uploading the collected images with the potholes and the positioning information to the cloud platform; judging whether a pothole exists or not according to the automobile driving data; when the potholes exist according to the automobile driving data, the automobile driving data and the positioning information are uploaded to the cloud platform; the cloud platform marks corresponding areas on the map according to the positioning information; when a vehicle runs to a corresponding area, the cloud platform issues depression information of the area to the vehicle; when the vehicle runs in the area, corresponding response is made according to the hollow marks on the map. In the vehicle driving process, the hollow road sections can be effectively reminded, the problem of safe driving under the scene is reduced, and the cloud platform enables data to be more real-time.
In the prior art, the scheme is based on big data, the automobile is reminded by the big data recorded by the hollow, the real-time performance and the reliability are insufficient, and newly-generated hollow cannot be avoided in time.
Disclosure of Invention
One of the purposes of the invention is to provide a vehicle-mounted road pothole identification method, so as to solve the problem that newly-generated potholes cannot be avoided in time in the prior art; the second purpose is to provide a vehicle-mounted road pothole identification system; the third purpose is to provide an automobile.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a vehicle-mounted road pothole identification method,
the camera collects data of a front road in real time;
judging whether a front road has a covering vehicle or not;
if the hidden vehicle does not exist, judging whether a pothole exists in the front road or not based on the front road image information;
if the hidden vehicle exists, whether the front road has a pothole or not is judged based on the shaking range of the hidden vehicle.
According to the technical means, the method is based on the image recognition technology, the scenes are divided into the vehicles with the covering vehicles and the vehicles without the covering vehicles, the response is made aiming at the two scenes, the recognition accuracy and the recognition reliability are improved, meanwhile, the image recognition technology is based on the current road conditions, the real-time performance is good, and the vehicles can avoid potholes in advance.
Further, the method of determining whether or not a pothole is present in the road ahead based on the road image information ahead if there is no hidden vehicle includes:
acquiring an image of a front road, and carrying out gray processing on the image;
acquiring the outline of the part with the abrupt change of the gray value through an edge detection algorithm;
and acquiring the average depth value of the part with the sudden change of the gray value, if the average depth value is larger than or equal to a first set value, judging that the part with the sudden change of the gray value is a hollow, and if the average depth value is smaller than the first set value, judging that the part with the sudden change of the gray value is not the hollow.
According to the technical means, the recognition accuracy is improved for the scene without the hidden vehicle.
Further, the method for determining whether or not a pothole is present in the road ahead based on the shaking range of the masking vehicle, if the masking vehicle is present, includes:
acquiring a front video shot by a camera, reading and displaying an image of each frame of the video;
selecting the covering vehicle of each frame of image, if the following formula is met, determining that a pothole exists in the road ahead, otherwise, determining that no pothole exists;
Hn+1-Hn≥Hsetting up，
Wherein Hn＝Ln1-Ln2；
Ln1Representing the distance between the leftmost point and the rightmost point of the masked vehicle;
Ln2representing the distance between the uppermost point and the lowermost point of the masked vehicle;
n represents the number of frames;
Hsetting upIndicating the second set point.
According to the technical means, the recognition accuracy is improved for the scene with the hidden vehicle.
Further, if a pothole is present in the front, the pothole position is communicated to an autopilot controller that plans a route that avoids the pothole.
Further, the planning of a route a avoiding a pothole: the pothole is avoided by changing to the right lane; or B: avoiding potholes in a mode of changing to a left lane; or C: directly through the potholes by way of deceleration.
Further, the automatic driving controller first determines whether the mode a can be adopted, and then determines whether the mode B can be adopted if the mode a cannot be adopted, and then determines whether the mode C can be adopted if the mode B cannot be adopted.
According to the technical means, the priority of avoidance modes is set, and the automatic driving controller is favorable for selecting the optimal mode to avoid the influence of the potholes.
Further, before the masking vehicle for each frame of image is selected, each frame of image is processed by the following method:
and converting each frame image into a gray scale image, binarizing, and corroding or enlarging the edge of the binarized image.
According to the technical means, a clearer image can be obtained, and the identification accuracy is improved.
A vehicle-mounted road hollow identification system based on the method comprises
The judging module is configured to receive information of the front road shot by the camera and judge whether the front road has a hidden vehicle or not; the processing module is configured to judge whether a pothole exists on the front road or not based on the image information of the front road if the front road does not have the hidden vehicle; if the front road has the hidden vehicle, whether the front road has the depression or not is judged based on the shaking range of the hidden vehicle.
Further, when the first pothole identification module or the second pothole identification module identifies that a pothole exists in the road ahead,
the first or second hole identification module sends the location of the hole to the autonomous driving controller, which then plans a route that avoids the hole.
An automobile is provided with the system.
The invention has the beneficial effects that:
the method and the system are based on the visual identification technology, carry out hollow judgment based on real-time road conditions, have better real-time performance, simultaneously divide the road conditions into two scenes, and distinguish identification modes aiming at the two scenes, so that the identification accuracy is improved, further the method and the system can analyze and early warn the hollow risks of the road under the whole road condition, the influence of the hollow is better and effectively avoided or reduced, and the comfort and the safety on the hollow road section during automatic driving are improved.
Drawings
FIG. 1 is a flow chart of a method according to the present invention;
FIG. 2 is a schematic view of scenario A;
FIG. 3 is a schematic view of scenario B;
FIG. 4 is a schematic diagram of a system for carrying out the method of the present invention.
Wherein, 1-camera; 2-a judging module; 3-a processing module; 4-an automatic driving controller; 5-an actuator.
Detailed Description
Other advantages and effects of the present invention will be readily apparent to those skilled in the art from the disclosure herein, wherein embodiments of the present invention are described below with reference to the accompanying drawings and preferred embodiments. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, and are not intended to limit the scope of the present invention.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation, and the type, amount and proportion of each component in actual implementation can be changed freely, and the layout of the components can be more complicated.
The embodiment provides a vehicle-mounted road pothole identification method, which specifically comprises the following steps of:
during the process of vehicle moving, the data of the road ahead are collected in real time through the camera, and the vehicle is in an automatic driving state at the moment.
And judging whether the hidden vehicle exists on the front road or not through the front road data acquired by the camera.
If there is no hidden vehicle, it is determined whether there is a pothole in the road ahead based on the road image information ahead.
The scene is shown in fig. 2, and the method specifically comprises the following steps:
acquiring an image of a front road, and carrying out gray processing on the image;
the edge detection algorithm is applied to the image by an edge detection algorithm, the edge of the image being composed of a set of pixels between two adjacent regions in the image, meaning the end of one region and the beginning of the other region in the image. It is also understood that an image edge is a collection of pixels in an image that have a spatially abrupt change in gray scale value. The gradient direction and the amplitude are two properties of the image edge, and the change amplitude of the pixel value is relatively smooth along the direction vertical to the edge; along the direction parallel to the edge, the variation range of the pixel value is relatively large. Therefore, according to the variation characteristic, a method of calculating a first or second derivative is generally used to describe and detect the image edge.
The basic idea of the image segmentation method based on edge detection is to detect edge pixels in an image first, and then to connect these edge pixels together to form a desired target region boundary. Edges in the image can be detected and determined by taking the derivative of the gray values, whereas the derivative can be achieved by calculating a differential operator. In the field of digital image processing, differential operations are often approximated by differential calculations. And then obtaining the contour of the part with the abrupt change of the gray value.
And calculating the average depth value of the gray value abrupt change part in the contour of the gray value abrupt change part, if the average depth value is larger than or equal to a first set value, judging that the gray value abrupt change part is a pit, and if the average depth value is smaller than the first set value, judging that the gray value abrupt change part is not a pit.
The first set value can be obtained by arranging a plurality of image samples with pits, determining the contour of the part with the abrupt change of the gray value by the image through an edge detection method, then calculating the depth value of the contour, and further determining the first set value according to the depth values of all the contours.
If the hidden vehicle exists, whether the front road has a pothole or not is judged based on the shaking range of the hidden vehicle.
As shown in fig. 3, the method specifically comprises:
the local video is loaded through the VideoCapture, and each frame is read in a loop and displayed.
In order to increase the operation speed of the computer, the image is generally converted into a gray scale image before image processing
Because color pictures are 3-channel (RGB) 24-bit depth images, while gray-scale maps are single-channel 8-bit depth images, processing gray-scale maps is much more efficient than color mapping. frontMat is the previous frame and affermat is the next frame.
And (4) binarizing the image by a threshold function, and operating on binarized data of the image, mainly aiming at highlight parts. Using an algorithm, the edges of the image are etched away. The "burrs" of the edges of the target are removed. Or operate on binarized data of the picture, mainly on highlights. Using an algorithm, the edges of the image are enlarged. The effect is to fill out the edge or inner pits of the target.
And (3) framing each frame of image to cover the vehicle, wherein the framing principle is to find the leftmost point and the rightmost point of the white square block to obtain the size difference (rectangle width) between the leftmost point and the rightmost point of the white square block, and find the topmost point and the bottommost point of the white square block to obtain the size difference (rectangle height H) between the topmost point and the bottommost point. A rectangle containing the white square can be drawn by width and height, and the coordinate of the upper left corner of the rectangle is determined by the uppermost value and the leftmost value of the white square.
If the following formula is satisfied, the shaking range of the front covering vehicle is large, the front road is considered to have a depression, otherwise, the front road is considered to have the depression
The shaking amplitude is small, and no potholes exist;
Hn+1-Hn≥Hsetting up，
Wherein Hn＝Ln1-Ln2；
Ln1Representing the distance between the leftmost point and the rightmost point of the masked vehicle;
Ln2representing the distance between the uppermost point and the lowermost point of the masked vehicle;
n represents the number of frames;
Hsetting upIndicating the second set point.
If a hollow is present in the front, the hollow position is transmitted to the automatic driving controller, and the automatic driving controller plans a route for avoiding the hollow.
Planning a route A for avoiding the potholes: the pothole is avoided by changing to the right lane; or B: avoiding potholes in a mode of changing to a left lane; or C: directly through the pothole in a decelerating manner. The priority of the method is sequentially (descending) A, B and C.
Namely, the automatic driving controller firstly judges whether the mode A can be adopted or not, if the mode A cannot be adopted, then judges whether the mode B can be adopted or not, and if the mode B cannot be adopted, then judges whether the mode C can be adopted or not.
The embodiment further provides a vehicle-mounted road depression identification system, which is based on the method and specifically comprises the following steps:
comprises a judging module 2 and a processing module 3,
the judging module 2 is configured to receive information of a front road shot by the camera 1 and judge whether a hidden vehicle exists on the front road;
the processing module 3 is configured to judge whether a pothole exists on the front road based on the image information of the front road if the front road does not have the hidden vehicle; if the front road has the hidden vehicle, whether the front road has the depression or not is judged based on the shaking range of the hidden vehicle.
When the processing module 3 identifies that a pothole exists in the road ahead, the processing module 3 sends the pothole position to the automatic driving controller 4, then the automatic driving controller 4 plans a pothole avoiding route, automatic lane changing is started after avoidance measures are defined, and an instruction is issued to the executing mechanism 5.
The embodiment also provides an automobile provided with the vehicle-mounted road hollow identification system.
The above embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention.

Claims (10)

1. A vehicle-mounted road pothole identification method is characterized by comprising the following steps:
the camera collects data of a front road in real time;
judging whether a front road has a covering vehicle or not;
if the hidden vehicle does not exist, judging whether a pothole exists in the front road or not based on the front road image information;
if the hidden vehicle exists, whether the front road has a pothole or not is judged based on the shaking range of the hidden vehicle.
2. The method of claim 1, wherein: the method for judging whether the front road has the pothole or not based on the front road image information when the hidden vehicle does not exist comprises the following steps:
acquiring an image of a front road, and carrying out gray processing on the image;
acquiring the contour of a part with a sudden change of the gray value through an edge detection algorithm;
and acquiring the average depth value of the part with the sudden change of the gray value, if the average depth value is larger than or equal to a first set value, judging that the part with the sudden change of the gray value is a hollow, and if the average depth value is smaller than the first set value, judging that the part with the sudden change of the gray value is not the hollow.
3. The method of claim 1, wherein: the method for judging whether the pothole exists on the road ahead or not based on the shaking range of the masking vehicle if the masking vehicle exists comprises the following steps:
acquiring a front video shot by a camera, reading and displaying an image of each frame of the video;
selecting the covering vehicle of each frame of image, if the following formula is met, determining that a pothole exists in the road ahead, otherwise, determining that no pothole exists;
Hn+1-Hn≥Hsetting up，
Wherein Hn＝Ln1-Ln2；
Ln1Representing the distance between the leftmost point and the rightmost point of the masked vehicle;
Ln2representing the distance between the uppermost point and the lowermost point of the masked vehicle;
n represents the number of frames;
Hsetting upIndicating the second set point.
4. A method according to claim 2 or 3, characterized in that: if a pothole is in the front, the pothole position is communicated to an autonomous driving controller, which plans a route that avoids the pothole.
5. The method of claim 4, wherein: and planning a route A for avoiding the potholes: the pothole is avoided by changing to the right lane; or B: avoiding potholes in a mode of changing to a left lane; or C: directly through the pothole in a decelerating manner.
6. The method of claim 5, wherein: the automatic driving controller firstly judges whether the mode A can be adopted or not, if the mode A cannot be adopted, then judges whether the mode B can be adopted or not, and if the mode B cannot be adopted, then judges whether the mode C can be adopted or not.
7. The method of claim 3, wherein: before the masking vehicle of each frame of image is selected, each frame of image is processed by the following method:
and converting each frame image into a gray scale image, binarizing, and corroding or enlarging the edge of the binarized image.
8. An on-board road hole identification system based on the method of any one of claims 1-7, characterized in that: comprises that
The judging module is configured to receive information of the front road shot by the camera and judge whether the front road has a hidden vehicle or not; the processing module is configured to judge whether potholes exist on the front road or not based on the front road image information if the front road does not have the covering vehicle; if the hidden vehicle exists on the front road, whether the pothole exists on the front road is judged based on the shaking range of the hidden vehicle.
9. The system of claim 8, wherein: when the first hollow identification module or the second hollow identification module identifies that a hollow exists in the road ahead, the first hollow identification module or the second hollow identification module sends the position of the hollow to an automatic driving controller, and then the automatic driving controller plans a route for avoiding the hollow.
10. An automobile, characterized in that: provided with a system according to claim 8 or 9.
CN202210796921.8A 2022-07-08 2022-07-08 Vehicle-mounted road pothole identification method and system and automobile Pending CN115273023A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210796921.8A CN115273023A (en) 2022-07-08 2022-07-08 Vehicle-mounted road pothole identification method and system and automobile

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210796921.8A CN115273023A (en) 2022-07-08 2022-07-08 Vehicle-mounted road pothole identification method and system and automobile

Publications (1)

Publication Number Publication Date
CN115273023A true CN115273023A (en) 2022-11-01

Family

ID=83762260

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210796921.8A Pending CN115273023A (en) 2022-07-08 2022-07-08 Vehicle-mounted road pothole identification method and system and automobile

Country Status (1)

Country Link
CN (1) CN115273023A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116189133A (en) * 2023-04-26 2023-05-30 宜宾闪马智通科技有限公司 Road inspection judging method and device
CN116534006A (en) * 2023-05-05 2023-08-04 三安车业集团有限公司 Vehicle power control method, device and storage medium
CN116588078A (en) * 2023-07-17 2023-08-15 上海鉴智其迹科技有限公司 Vehicle control method, device, electronic equipment and computer readable storage medium
CN116668852A (en) * 2023-07-28 2023-08-29 新汽有限公司 Vision acquisition system that wisdom commodity circulation car intelligent terminal was equipped with
CN117901599A (en) * 2024-01-23 2024-04-19 杭州泛舟科技有限公司 Damping and adjusting system of electric motorcycle
US11983932B1 (en) 2023-07-28 2024-05-14 New Automobile Co., Ltd Vision acquisition system equipped in intelligent terminal of smart logistics vehicle
CN118521166A (en) * 2024-07-23 2024-08-20 华东交通大学 Road safety risk assessment method based on intelligent perception

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116189133A (en) * 2023-04-26 2023-05-30 宜宾闪马智通科技有限公司 Road inspection judging method and device
CN116534006A (en) * 2023-05-05 2023-08-04 三安车业集团有限公司 Vehicle power control method, device and storage medium
CN116534006B (en) * 2023-05-05 2023-09-26 三安车业集团有限公司 Vehicle power control method, device and storage medium
CN116588078A (en) * 2023-07-17 2023-08-15 上海鉴智其迹科技有限公司 Vehicle control method, device, electronic equipment and computer readable storage medium
CN116588078B (en) * 2023-07-17 2023-09-15 上海鉴智其迹科技有限公司 Vehicle control method, device, electronic equipment and computer readable storage medium
CN116668852A (en) * 2023-07-28 2023-08-29 新汽有限公司 Vision acquisition system that wisdom commodity circulation car intelligent terminal was equipped with
CN116668852B (en) * 2023-07-28 2023-09-22 新汽有限公司 Vision acquisition system that wisdom commodity circulation car intelligent terminal was equipped with
US11983932B1 (en) 2023-07-28 2024-05-14 New Automobile Co., Ltd Vision acquisition system equipped in intelligent terminal of smart logistics vehicle
CN117901599A (en) * 2024-01-23 2024-04-19 杭州泛舟科技有限公司 Damping and adjusting system of electric motorcycle
CN118521166A (en) * 2024-07-23 2024-08-20 华东交通大学 Road safety risk assessment method based on intelligent perception
CN118521166B (en) * 2024-07-23 2024-10-11 华东交通大学 Road safety risk assessment method based on intelligent perception

Similar Documents

Publication Publication Date Title
CN115273023A (en) Vehicle-mounted road pothole identification method and system and automobile
CN111212772B (en) Method and device for determining a driving strategy of a vehicle
US9959624B2 (en) Early detection of turning condition identification using perception technology
US10853673B2 (en) Brake light detection
CN110501018B (en) Traffic sign information acquisition method for high-precision map production
CN110443225B (en) Virtual and real lane line identification method and device based on feature pixel statistics
CN106647776B (en) Method and device for judging lane changing trend of vehicle and computer storage medium
US11338807B2 (en) Dynamic distance estimation output generation based on monocular video
CN105678285B (en) A kind of adaptive road birds-eye view transform method and road track detection method
JP4696248B2 (en) MOBILE NAVIGATION INFORMATION DISPLAY METHOD AND MOBILE NAVIGATION INFORMATION DISPLAY DEVICE
US9652980B2 (en) Enhanced clear path detection in the presence of traffic infrastructure indicator
US8670592B2 (en) Clear path detection using segmentation-based method
JP6254084B2 (en) Image processing device
RU2568777C2 (en) Device to detect moving bodies and system to detect moving bodies
JP2009037622A (en) Method and device for evaluating image
CN107449440A (en) The display methods and display device for prompt message of driving a vehicle
CN110738081B (en) Abnormal road condition detection method and device
CN109635737A (en) Automobile navigation localization method is assisted based on pavement marker line visual identity
US8233054B2 (en) Scenery imaging apparatus, scenery imaging method, scenery imaging program, and computer-readable recording medium
US12071010B2 (en) Onboard display device, onboard display method, and computer readable storage medium
CN113029185B (en) Road marking change detection method and system in crowdsourcing type high-precision map updating
CN115240471B (en) Intelligent factory collision avoidance early warning method and system based on image acquisition
CN113602282A (en) Vehicle driving and monitoring system and method for maintaining situational awareness at a sufficient level
CN110733416A (en) lane departure early warning method based on inverse perspective transformation
CN116524454A (en) Object tracking device, object tracking method, and storage medium

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