CN114120257A - Motor vehicle limiter identification method and device and computer readable storage medium - Google Patents
Motor vehicle limiter identification method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN114120257A CN114120257A CN202111591185.4A CN202111591185A CN114120257A CN 114120257 A CN114120257 A CN 114120257A CN 202111591185 A CN202111591185 A CN 202111591185A CN 114120257 A CN114120257 A CN 114120257A
- Authority
- CN
- China
- Prior art keywords
- motor vehicle
- image
- stopper
- image frame
- frame
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for identifying a motor vehicle stopper and a computer readable storage medium, wherein the method comprises the following steps: extracting frame by frame from a video image in front of the driving direction of the motor vehicle collected and transmitted by a vehicle-mounted camera to obtain an original image frame of the motor vehicle under an overlooking visual angle; distortion correction is carried out on the original image frame based on a preset image distortion correction principle and calibration parameters of a vehicle-mounted camera to obtain a corrected image frame; performing image processing on the corrected image frame by adopting an adaptive threshold value binarization algorithm model based on preset image characteristics to obtain a binarization image frame, wherein the preset image characteristics comprise image color, image gradient and image gray; extracting an original characteristic region with a preset stopper characteristic from a binarization image frame; and removing the interference area in the original characteristic area, and judging all targets in the original characteristic area after the interference area is removed as the motor vehicle stopper. The embodiment can accurately identify the limiter of the parking space of the motor vehicle.
Description
Technical Field
The embodiment of the invention relates to the technical field of auxiliary driving of motor vehicles, in particular to a method and a device for identifying a motor vehicle stopper and a computer readable storage medium.
Background
At present, in order to limit a parking position of a motor vehicle when the motor vehicle is parked and prevent the motor vehicle from overtopping and colliding with other surrounding objects when the motor vehicle is driven into the parking space, a stopper (also called a wheel stopper, a car stopper or a position stopper and the like) is usually installed at one end opposite to a vehicle inlet and outlet end of the parking space in the parking space, and when wheels (rear wheels when the motor vehicle is backed into the parking space, front wheels when the motor vehicle is driven forward into the parking space) positioned at the front end of a driving direction of the motor vehicle abut against the stopper, the motor vehicle is parked in place. However, in practical applications, it is often difficult for a driver to accurately determine an actual distance between a wheel at the front end of the motor vehicle in the traveling direction and the stopper, so that the motor vehicle still keeps a faster traveling speed when the wheel abuts against the stopper, and the wheel collides with the stopper violently, which results in poor user experience of a driver and a passenger on the motor vehicle. Therefore, some existing motor vehicles can be provided with a device for actively identifying and reminding a stopper in a parking space when parking, so that the wheels can be ensured to slowly abut against the stopper to realize braking, and the user experience of drivers and passengers is improved.
An existing motor vehicle limiter identification method is generally an identification algorithm model based on deep learning, however, the detection method needs to carry out a large amount of learning training on the identification algorithm model in advance to improve the accuracy of actual identification, and the design difficulty is relatively large; moreover, the method needs strong computational hardware support in practical application, and the cost is relatively high; in addition, the identification difficulty of the method is relatively high due to the relatively complex driving environment of the motor vehicle.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is to provide a method for identifying a motor vehicle stopper, which can accurately identify the stopper of a motor vehicle parking space.
The embodiment of the invention further aims to solve the technical problem of providing a motor vehicle stopper identification device which can accurately identify a stopper of a motor vehicle parking space.
A further object of embodiments of the present invention is to provide a computer-readable storage medium for storing a computer program for accurately identifying a parking space limiter of a motor vehicle.
In order to solve the above technical problem, an embodiment of the present invention provides the following technical solutions: a method of identifying a motor vehicle stopper, comprising the steps of:
extracting the original image frames frame by frame from the video image in front of the driving direction of the motor vehicle collected and transmitted by the vehicle-mounted camera; distortion correction is carried out on the original image frame based on a preset image distortion correction principle and calibration parameters of the vehicle-mounted camera to obtain a corrected image frame;
performing image processing on the corrected image frame by adopting an adaptive threshold value binarization algorithm model based on preset image characteristics to obtain a binarization image frame, wherein the preset image characteristics comprise image color, image gradient and image gray;
extracting an original characteristic region with a preset limiter characteristic from the binarization image frame; and
and removing the interference area in the original characteristic area, and judging all targets in the original characteristic area after the interference area is removed as the motor vehicle stopper.
Further, after the binarization image frame is obtained, a parking space image of the motor vehicle at present is identified from the binarization image frame, a preset calibration area in the parking space image is extracted as an area of interest, and then the original characteristic area is extracted from the area of interest.
Further, an image denoising and interference point filtering are adopted to remove an interference region in the original characteristic region.
Further, the predetermined stopper feature is a shape feature.
Further, the image distortion correction principle is a checkerboard correction principle.
Further, the original image frames are image frames of the motor vehicle under a top view angle.
On the other hand, in order to solve the above further technical problem, an embodiment of the present invention provides the following technical solutions: a motor vehicle stopper recognition device is respectively connected with a vehicle-mounted camera used for shooting video images of the surrounding environment of a motor vehicle and providing panoramic video images and a motor vehicle braking system used for braking the motor vehicle according to recognition results output by the motor vehicle stopper recognition device, the motor vehicle stopper recognition device comprises a processor, a memory and a computer program which is stored in the memory and configured to be executed by the processor, and the processor realizes the motor vehicle stopper recognition method when executing the computer program.
Further, the vehicle-mounted camera is a fisheye camera.
In another aspect, to solve the above further technical problem, an embodiment of the present invention provides the following technical solutions: a computer-readable storage medium comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform a motor vehicle stopper identification method as in any one of the above.
After the technical scheme is adopted, the embodiment of the invention at least has the following beneficial effects: according to the embodiment of the invention, the original image frame is obtained from the video image in front of the motor vehicle in the driving direction, which is collected and transmitted by the vehicle-mounted camera, and then the original image frame is subjected to distortion correction to obtain the corrected image frame, so that the interference of image distortion on image recognition is avoided, and the image recognition accuracy is improved; further, the corrected image frame is subjected to image processing based on preset image characteristics by adopting an adaptive threshold value binarization algorithm model to obtain a binarization image frame, so that the extraction of the image is convenient, the interference of ambient light and driving environment on the image extraction is avoided, the binarization is performed based on the image color, the image gradient and the image gray level, the influence on the characteristics of the image is small, then an original characteristic region with preset stopper characteristics is extracted from the binarization image frame, the stopper is distinguished by adopting a characteristic extraction mode, the identification accuracy is high, finally the interference region in the original characteristic region is removed, all targets in the original characteristic region after the interference region is removed are judged as the motor vehicle stoppers, the stoppers around the motor vehicle can be accurately identified, the data processing process is relatively simple, and the hardware support with strong calculation power is not needed, the cost is reduced.
Drawings
Fig. 1 is a flow chart illustrating steps of an alternative embodiment of a method for identifying a vehicle restraint device according to the present invention.
Fig. 2 is a schematic view of an alternative embodiment of the motor vehicle stopper identification method of the present invention.
Fig. 3 is a schematic diagram of an actual recognition result of an alternative embodiment of the motor vehicle stopper recognition method of the present invention.
Fig. 4 is a schematic diagram showing an actual recognition result of a further alternative embodiment of the motor vehicle stopper recognition method of the present invention.
Fig. 5 is a schematic diagram showing an actual recognition result of still another alternative embodiment of the motor vehicle stopper recognition method of the present invention.
Fig. 6 is a schematic diagram showing an actual recognition result of another alternative embodiment of the motor vehicle stopper recognition method of the present invention.
Fig. 7 is a schematic block diagram of an alternative embodiment of the motor vehicle stop recognition device of the present invention.
Fig. 8 is a functional block diagram of an alternative embodiment of the motor vehicle stopper identifying device of the present invention.
Detailed Description
The present application will now be described in further detail with reference to the accompanying drawings and specific examples. It should be understood that the following illustrative embodiments and description are only intended to explain the present invention, and are not intended to limit the present invention, and features of the embodiments and examples in the present application may be combined with each other without conflict.
As shown in fig. 1 and 2, an alternative embodiment of the present invention provides a motor vehicle stopper identification method including the steps of:
s1: extracting the original image frames frame by frame from the video image in front of the driving direction of the motor vehicle collected and transmitted by the vehicle-mounted camera 1;
s2: distortion correction is carried out on the original image frame based on a preset image distortion correction principle and calibration parameters of the vehicle-mounted camera 1 to obtain a corrected image frame;
s3: performing image processing on the corrected image frame by adopting an adaptive threshold value binarization algorithm model based on preset image characteristics to obtain a binarization image frame, wherein the preset image characteristics comprise image color, image gradient and image gray;
s4: extracting an original characteristic region A with a preset stopper characteristic from the binarization image frame; and
s5: and removing the interference area B in the original characteristic area A, and judging all targets in the original characteristic area A after the interference area B is removed as the motor vehicle stopper C.
According to the embodiment of the invention, the original image frame is obtained from the video image in front of the motor vehicle in the driving direction, which is collected and transmitted by the vehicle-mounted camera, and then the original image frame is subjected to distortion correction to obtain the corrected image frame, so that the interference of image distortion on image recognition is avoided, and the image recognition accuracy is improved; further, the corrected image frame is subjected to image processing based on the preset image characteristics by adopting an adaptive threshold value binarization algorithm model to obtain a binarization image frame, so that the extraction of the image is convenient, the interference of the ambient light and the driving environment on the image extraction is avoided, the binarization is carried out based on the image color, the image gradient and the image gray level, the influence on the characteristics of the image is small, then an original characteristic region A with the preset stopper characteristics is extracted from the binarization image frame, the stopper C is distinguished by adopting a characteristic extraction mode, the identification accuracy is high, finally the interference region B in the original characteristic region A is removed, all the targets in the original characteristic region A after the interference region B is removed are judged to be the motor vehicle stopper C, the stoppers C around the motor vehicle can be accurately identified, and the data processing process is relatively simple, hardware support with strong calculation power is not needed, and cost is reduced.
In specific implementation, the recognition result schematic diagrams in practical application scenes as shown in fig. 3-6 are measured through specific experiments, wherein the recognition success rates of the dim light parking space background and the color parking space background are both greater than 90%, and the recognition success rate of the open air parking space background is more than 95%, so that the motor vehicle stopper recognition method provided by the embodiment of the invention has good stopper recognition success rates in various parking environments.
In an optional embodiment of the present invention, as shown in fig. 2, after the binarized image frame is obtained, a parking space image P in which a motor vehicle is currently parked is further identified from the binarized image frame, a predetermined calibration region in the parking space image P is first extracted as an area of interest R, and then the original feature region a is extracted from the area of interest R. In this embodiment, after the binarized image is obtained, the parking space image P around the motor vehicle is identified from the binarized image frame, because the motor vehicle stopper is usually arranged in a predetermined region of the parking space of the motor vehicle, the mounting positions of the stoppers in the parking spaces suitable for motor vehicles of different models are also slightly different, taking the parking space suitable for a compact car as an example, the length of the parking space is usually 5 meters, and the stopper is usually arranged at a position away from the tail end of the parking space by a distance of 1 meter, at this time, a region 0.5 meter to 2 meters ahead from the tail end of the parking space can be calibrated as an area of interest R in advance, so that the data operation amount can be greatly reduced, the data processing efficiency is improved, and the hardware computation cost is reduced.
In an optional embodiment of the present invention, an image denoising and interference point filtering are adopted to remove an interference region B in the original characteristic region a. In the embodiment, the image denoising and interference point filtering modes are adopted, so that the interference areas B including dirt, sundries, unrelated obstacles and the like in the original characteristic area A can be effectively filtered, and the identification accuracy of the motor vehicle stopper is effectively improved.
In an alternative embodiment of the invention, the predetermined stop feature is a shape feature. In this embodiment, the shape of the vehicle stopper C is generally, for example: the original characteristic region A can be quickly identified through the shape characteristics of the strip, the rectangular shape divided into two sections and the like.
In an alternative embodiment of the invention, the image distortion correction principle is a checkerboard correction principle. In the embodiment, a checkerboard correction principle is adopted, the precision of image distortion correction is relatively high, and the identification accuracy of a subsequent motor vehicle stopper can be improved.
In an alternative embodiment of the present invention, the original image frames are image frames of a motor vehicle in a top view. In this embodiment, the original image frame is an image frame of a motor vehicle at a top view angle, and the similarity between the shape feature of the stopper C in the image and the actual shape feature is higher, which is more beneficial to improving the identification efficiency of the motor vehicle stopper C.
On the other hand, as shown in fig. 7, an alternative embodiment of the present invention further provides a motor vehicle stopper recognition device 3, which is respectively connected to the vehicle-mounted camera 1 for capturing video images of surroundings of the motor vehicle and providing panoramic video images, and the motor vehicle braking system 5 for braking the motor vehicle according to the recognition result output by the motor vehicle stopper recognition device, wherein the motor vehicle stopper recognition device 3 comprises a processor 30, a memory 32, and a computer program stored in the memory 32 and configured to be executed by the processor 30, and the processor 30 implements the motor vehicle stopper recognition method according to the above embodiment when executing the computer program.
In an alternative embodiment of the present invention, the vehicle-mounted camera 1 is a fisheye camera. In the embodiment, the vehicle-mounted camera 1 adopts the fisheye camera, the range of the visual field of the fisheye camera is wide, the environment images of the motor vehicle at all angles can be effectively shot and obtained, the environment range around the motor vehicle contained in the original image frame is larger, and more limiters around the motor vehicle can be conveniently recognized at one time.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory 32 and executed by the processor 30 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program in the motor vehicle stop recognition device 3. For example, the computer program may be divided into functional blocks in the motor vehicle stopper recognition apparatus 3 as shown in fig. 8, wherein the image extraction module 41, the distortion correction module 42, the binarization processing module 43, the raw region extraction module 44, and the target determination module 45 respectively perform the above steps S1-S5.
The motor vehicle stopper identifying device 3 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The vehicle stop recognition device 3 may include, but is not limited to, a processor 30, a memory 32. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the vehicle stop recognition device 3, and does not constitute a limitation of the vehicle stop recognition device 3, and may include more or less components than those shown, or combine some components, or different components, for example, the vehicle stop recognition device 3 may further include an input-output device, a network access device, a bus, etc.
The Processor 30 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor 30 is a control center of the vehicle stopper identifying device 3, and various interfaces and lines are used to connect various parts of the entire vehicle stopper identifying device 3.
The memory 32 can be used for storing the computer programs and/or modules, and the processor 30 implements various functions of the motor vehicle stopper recognition device 3 by operating or executing the computer programs and/or modules stored in the memory 32 and calling up the data stored in the memory 32. The memory 32 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a pattern recognition function, a pattern stacking function, etc.), and the like; the storage data area may store data (such as graphic data, etc.) created according to the use of the control device, etc. Further, the memory 32 may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The functions described in the embodiments of the present invention may be stored in a storage medium readable by a computing device if they are implemented in the form of software functional modules or units and sold or used as independent products. Based on such understanding, all or part of the flow in the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by the processor 30, the steps of the above-described method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
In another aspect, an alternative embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the computer-readable storage medium controls an apparatus to execute the method for identifying a vehicle stopper according to the above embodiment.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other.
Claims (9)
1. A method of identifying a motor vehicle stopper, the method comprising the steps of:
extracting the original image frames frame by frame from the video image in front of the driving direction of the motor vehicle collected and transmitted by the vehicle-mounted camera;
distortion correction is carried out on the original image frame based on a preset image distortion correction principle and calibration parameters of the vehicle-mounted camera to obtain a corrected image frame;
performing image processing on the corrected image frame by adopting an adaptive threshold value binarization algorithm model based on preset image characteristics to obtain a binarization image frame, wherein the preset image characteristics comprise image color, image gradient and image gray;
extracting an original characteristic region with a preset limiter characteristic from the binarization image frame; and
and removing the interference area in the original characteristic area, and judging all targets in the original characteristic area after the interference area is removed as the motor vehicle stopper.
2. The motor vehicle stopper identifying method as recited in claim 1, wherein after the binarized image frame is obtained, a parking space image in which the motor vehicle is currently parked is identified from the binarized image frame, a pre-calibrated region in the parking space image is extracted as an area of interest, and then the original feature region is extracted from the area of interest.
3. The motor vehicle stopper identifying method according to claim 1 or 2, wherein an interference region in the original feature region is removed using image denoising and interference point filtering.
4. The method of identifying a motor vehicle stopper of claim 1 wherein the predetermined stopper characteristic is a shape characteristic.
5. The motor vehicle stopper identification method of claim 1 wherein the image distortion correction principle is a checkerboard correction principle.
6. The vehicle stop identification method according to claim 4, wherein said raw image frames are image frames of a vehicle from a top view perspective.
7. A motor vehicle stopper recognition device, respectively connected to a vehicle-mounted camera for capturing video images of the surroundings of a motor vehicle and providing panoramic video images, and a motor vehicle braking system for braking the motor vehicle based on recognition results output by the motor vehicle stopper recognition device, characterized in that the motor vehicle stopper recognition device comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the motor vehicle stopper recognition method according to any one of claims 1 to 6 when executing the computer program.
8. The vehicle stop identification device of claim 7, wherein the vehicle-mounted camera is a fisheye camera.
9. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the motor vehicle stopper identification method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111591185.4A CN114120257A (en) | 2021-12-23 | 2021-12-23 | Motor vehicle limiter identification method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111591185.4A CN114120257A (en) | 2021-12-23 | 2021-12-23 | Motor vehicle limiter identification method and device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114120257A true CN114120257A (en) | 2022-03-01 |
Family
ID=80362286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111591185.4A Pending CN114120257A (en) | 2021-12-23 | 2021-12-23 | Motor vehicle limiter identification method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114120257A (en) |
-
2021
- 2021-12-23 CN CN202111591185.4A patent/CN114120257A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112528878B (en) | Method and device for detecting lane line, terminal equipment and readable storage medium | |
| CN108638999B (en) | Anti-collision early warning system and method based on 360-degree look-around input | |
| CN108872975B (en) | Vehicle-mounted millimeter wave radar filtering estimation method and device for target tracking and storage medium | |
| US11288833B2 (en) | Distance estimation apparatus and operating method thereof | |
| CN110834667B (en) | Vehicle steering control method and device, vehicle, terminal device and storage medium | |
| CN106845332B (en) | Vision-based wet road condition detection using tire side splash | |
| CN110008891B (en) | Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium | |
| CN113297881B (en) | Target detection method and related device | |
| CN110348273B (en) | Neural network model training method and system and lane line identification method and system | |
| KR20190095567A (en) | Method and apparatus of identifying object | |
| US20230415760A1 (en) | Method for assisting safer driving and electronic device | |
| CN114120257A (en) | Motor vehicle limiter identification method and device and computer readable storage medium | |
| CN107452230B (en) | Obstacle detection method and device, terminal equipment and storage medium | |
| CN115965636A (en) | Vehicle side view generating method and device and terminal equipment | |
| CN115496775A (en) | Vehicle door clamped object detection method, device, equipment and storage medium | |
| CN117333837A (en) | Driving safety auxiliary method, electronic equipment and storage medium | |
| CN112184605A (en) | Method, equipment and system for enhancing vehicle driving visual field | |
| CN114475780A (en) | Automatic parking method, device, equipment and storage medium | |
| CN111161542B (en) | Vehicle identification method and device | |
| CN114898325B (en) | Vehicle dangerous lane change detection method and device and electronic equipment | |
| US20230419682A1 (en) | Method for managing driving and electronic device | |
| CN115675454B (en) | Vehicle collision recognition method, vehicle-mounted terminal, vehicle, and storage medium | |
| TWI841130B (en) | Method for detecting lane line and related devices | |
| CN112183413B (en) | Parking space detection method and device, storage medium and vehicle | |
| US11836933B2 (en) | Method for calculating information relative to a relative speed between an object and a camera |
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 |