CN116665440B - Expressway inter-vehicle distance measurement method, system and equipment - Google Patents
Expressway inter-vehicle distance measurement method, system and equipment Download PDFInfo
- Publication number
- CN116665440B CN116665440B CN202310589241.3A CN202310589241A CN116665440B CN 116665440 B CN116665440 B CN 116665440B CN 202310589241 A CN202310589241 A CN 202310589241A CN 116665440 B CN116665440 B CN 116665440B
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- area
- distance
- 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.)
- Active
Links
- 238000000691 measurement method Methods 0.000 title claims description 11
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 206010039203 Road traffic accident Diseases 0.000 abstract description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- 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
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
- Measurement Of Optical Distance (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method, a system and equipment for measuring the distance between driving vehicles on a highway, and belongs to the technical field of intelligent traffic. The method of the invention comprises the following steps: carrying out primary detection and positioning on a license plate of a vehicle in a traffic video frame of a highway roadside facility by using a license plate detection model based on YOLOv to obtain an initial positioning area of the license plate; cutting out an image of an initial positioning area of the license plate according to the initial detection positioning result, determining the final position of the license plate through image processing operation, and calculating the final license plate area; and calculating the vehicle distance according to the final license plate area and the relation between the final license plate area and the vehicle distance. The method can be applied to real-time monitoring of the driving distance of the expressway, and can identify potential risks in time, avoid traffic accidents and improve traffic safety management level.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic, and particularly relates to a method, a system and equipment for measuring the distance between driving wheels on an expressway.
Background
Traffic safety is a long-term challenge faced by all national transportation authorities. In particular, in expressway scenes, dynamic traffic environments are complex, a large number of vehicle objects run at high speed, and therefore safety tasks are difficult to manage, and even accidents occur. Too close a high-speed driving distance is a main reason for causing rear-end collision, and further improvement of road safety management capability is one of main directions of intelligent traffic development. In the case of high-speed traveling, traffic accidents are easily caused by vehicles traveling close to others, and thus, controlling the distance between overspeed vehicles is a necessary condition to ensure personal safety and create an appropriate traffic environment.
In past studies, most scholars have focused on how to estimate the distance between a vehicle and its lead in the field of autopilot, which can be achieved based on a reference or lane line. There is little research for monitoring vehicle distance for traffic enforcement in a large highway scenario. Distance measurement methods can be generally classified into conventional methods and deep learning methods according to the detection algorithm used. Furthermore, it can be further classified into a monocular vision-based method, a binocular vision-based method, and a radar-based method based on the sensing device. The license plate is very small and fuzzy in the expressway scene, so that the detection result is poor. Further research is needed to improve the efficiency of the detection and localization process.
Vehicle distance measurements are currently more common in the field of autopilot to obtain distance from a previous vehicle. Zaarane et al in the paper "Vehicle to VEHICLE DISTANCE measurement for self-DRIVING SYSTEMS" propose a simple method based on stereoscopic technology, divided into three parts: vehicle detection, stereo matching, and distance measurement. First, a discrete wavelet transform is used to detect vehicles in one camera, then match vehicles detected in the other cameras, calculate the horizontal centroid of the vehicle in the different images and measure distance. On highways it is often difficult to install two cameras at the same horizontal position, and this approach is not versatile.
Disclosure of Invention
The invention aims to provide a method, a system and equipment for measuring the distance between the vehicles on the expressway, which are used for calculating the distance between the vehicles on the expressway based on a license plate positioning result, do not need to calibrate a camera, are simple to operate and can monitor the potential risk of the road in real time.
Specifically, in one aspect, the present invention provides a highway following distance measuring method, including:
Inputting a trained YOLOv license plate detection basic model into a license plate image appearing in a highway traffic video frame, and performing primary detection and positioning to obtain an image of an initial license plate positioning area as an initial license plate positioning image;
Cutting out an image of an initial positioning area of the license plate according to the initial detection positioning result, determining the final position of the license plate through image processing operation, and calculating the final license plate area;
Calculating the vehicle distance according to the final license plate area, the relationship between the final license plate area and the vehicle distance;
the relation between the final license plate area and the vehicle distance is as follows:
Wherein d' is the distance between the vehicles to be measured, z is the set value, d 1 is the distance from the license plate of the first vehicle to be measured to the camera of the road side facility, d is the distance from the license plate of the second vehicle to be measured to the camera of the road side facility, s 1 is the area of the license plate corresponding to d 1 in the traffic video frame image, and s is the area of the license plate corresponding to d in the highway traffic video frame image.
Further, the set value z is obtained by the following formula:
D 0 is the preset distance from the license plate of the vehicle to the camera of the drive test facility, and s 0 is the area of the license plate corresponding to d 0 in the expressway traffic video frame image.
Further, the step of cutting out the image of the initial positioning area of the license plate according to the initial detection positioning result, and determining the final position of the license plate through image processing operation comprises the following steps:
Carrying out Gaussian blur operation on the license plate initial positioning image I 0 to obtain a license plate image I gas after noise reduction;
the noise-reduced license plate image I gas is subjected to gray-scale pretreatment to obtain a gray-scale license plate image I gray;
Converting the noise-reduced license plate image I gas image into an HSV space to obtain an HSV space license plate image I hsv, and extracting color features in the license plate image;
Carrying out morphological operation and binarization operation on the grayscale license plate image I gray according to the color characteristics in the extracted license plate image I hsv to generate a black-and-white license plate image I bin;
Screening license plate candidate frames from the black-and-white license plate image I bin according to the shape characteristics of the license plates, and determining the final position of the license plates; if the final position of the license plate is determined to be empty through the step, the initial positioning area of the license plate is taken as the final position of the license plate.
On the other hand, the invention also provides a highway inter-vehicle distance measurement system for realizing the highway inter-vehicle distance measurement method, which comprises a data acquisition module, a deep learning module, an image processing module, a inter-vehicle distance calculation module and a risk early warning module;
The data acquisition module is used for sensing highway conditions by using cameras erected on highway side facilities and acquiring highway traffic video data;
The deep learning module is used for processing the expressway traffic video frame acquired by the data acquisition module into an image, inputting a trained YOLOv license plate detection basic model, and performing primary detection and positioning to acquire an image of an initial license plate positioning area as an initial license plate positioning image;
The image processing module cuts out an image of an initial positioning area of the license plate according to the initial detection positioning result, determines the final position of the license plate through image processing operation, and calculates the area of the license plate in the expressway traffic video frame image to be used as the final license plate area;
The driving distance calculation module calculates the driving distance of the vehicle according to the area of the license plate of each vehicle in the expressway traffic video frame image;
and the risk early warning module is used for judging whether the current vehicle running distance is smaller than a safe running distance threshold value and sending a risk prompt for the condition smaller than the threshold value.
In yet another aspect, the present invention also provides an expressway following distance measurement apparatus, the apparatus including a memory and a processor; the memory stores a computer program for implementing the highway inter-vehicle distance measurement method, and the processor executes the computer program to implement the steps of the method.
In yet another aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
The highway inter-vehicle distance measuring method, system and equipment have the following beneficial effects:
According to the expressway distance measurement method, system and equipment, the corresponding model method is provided for real-time monitoring of the distance between vehicles on the expressway aiming at traffic rear-end collision accidents frequently occurring in high speed, and the road risk can be judged and early warned in time by comparing the distance between vehicles with the safe distance threshold value, so that references are provided for high-speed traffic safety control, the occurrence rate of traffic accidents is effectively reduced, and the road management capability is improved.
According to the expressway inter-vehicle distance measuring method, system and equipment, modeling is carried out according to the view angle of monitoring equipment erected on an expressway, and a high-speed video is processed by using deep learning and traditional image processing technology, so that license plates are detected and positioned; and analyzing the relation between the license plate area and the driving distance by means of a camera imaging principle, and deducing a calculation formula of the vehicle distance to obtain the driving distance. On highways, the most commonly used monitoring equipment is a vision sensor camera. Therefore, the method has high accuracy, is convenient to implement and saves resources. The invention can be applied to high-speed traffic management law enforcement.
Drawings
FIG. 1 is a flow chart of a method of an embodiment of the present invention.
FIG. 2 is a diagram of a result of determining a final position of a license plate according to an embodiment of the present invention.
Fig. 3 is an enlarged view of a portion of the license plate of fig. 2.
Fig. 4 is a schematic diagram of license plate imaging principle according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the examples and with reference to the accompanying drawings.
Example 1:
One embodiment of the invention relates to a highway inter-vehicle distance measurement system, which comprises a data acquisition module, a deep learning module, an image processing module, a inter-vehicle distance calculation module and a risk early warning module.
The data acquisition module is used for sensing highway conditions by using cameras erected on highway side facilities and acquiring highway traffic video data.
And the deep learning module is used for processing the expressway traffic video frame acquired by the data acquisition module into an image, inputting a trained YOLOv license plate detection basic model, and carrying out primary detection and positioning to obtain an image of the initial license plate positioning area as an initial license plate positioning image.
The image processing module cuts out an image of an initial positioning area of the license plate according to the initial detection positioning result, determines the final position of the license plate through image processing operation, and calculates the area of the license plate in the expressway traffic video frame image as the final license plate area.
And the driving distance calculation module is used for calculating the driving distance of the vehicle according to the area of the license plate of each vehicle in the expressway traffic video frame image.
And the risk early warning module is used for judging whether the current vehicle running distance is smaller than a safe running distance threshold value and sending a risk prompt for the condition that the current vehicle running distance is smaller than the threshold value.
The expressway distance measurement method of the invention, as shown in figure 1, comprises the following steps:
Step 1: and (5) primarily detecting and positioning the license plate.
Inputting a trained YOLOv license plate detection basic model into a license plate image appearing in an expressway traffic video frame I, and performing primary detection and positioning to obtain an image of an initial license plate positioning area as an initial license plate positioning image I 0.
Preferably, the trained YOLOv license plate detection basic model is obtained by the following method:
and marking 500 license plate images as a training data set for training YOLOv license plate detection basic models, and training for 50 rounds.
Step 2: cutting out an image of an initial positioning area of the license plate according to the initial detection positioning result, determining the final position of the license plate through image processing operation, and calculating the final license plate area. The method specifically comprises the following steps:
Step 2.1: carrying out Gaussian blur operation on the license plate initial positioning image I 0 to obtain a license plate image I gas after noise reduction; to reduce image noise and to reduce the level of detail.
Step 2.2: and carrying out grey pretreatment on the noise-reduced license plate image I gas to obtain a grey license plate image I gray. The grey license plate image occupies smaller memory, the running speed is faster, and the target area is highlighted more.
Step 2.3: and converting the noise-reduced license plate image I gas image into an HSV space to obtain an HSV space license plate image I hsv so as to extract color features in the license plate image.
Step 2.4: and generating a black-and-white license plate image I bin by morphological operation and binarization operation on the license plate image I gray subjected to graying according to the color characteristics (such as a license plate is generally blue-bottomed) in the extracted license plate image I hsv so as to remove noise.
Step 2.5: and screening license plate candidate frames from the black-and-white license plate image I bin according to the shape features of the license plates, determining the final positions of the license plates and calculating the final license plate areas.
If the final position of the license plate is determined to be empty in the step 2.5, namely a more accurate positioning frame is not found, calculating the area of the license plate by using the initial positioning area of the license plate, namely the initial positioning area of the license plate is taken as the final position of the license plate.
The final position of the license plate is determined, the final license plate area is calculated, the detection frame drawn by the dotted line is the result of initial positioning image of the license plate, the detection frame drawn by the solid line is the final position of the license plate, and the area of the detection frame drawn by the solid line is the final license plate area, as shown in fig. 2 and 3.
Step 3: and calculating the vehicle distance according to the final license plate area and the relation between the final license plate area and the vehicle distance.
The relation between the final license plate area and the vehicle distance is as follows:
Wherein d' is the distance between the vehicles to be measured, z is the set value, d 1 is the distance from the license plate of the first vehicle to be measured to the camera of the road side facility, d is the distance from the license plate of the second vehicle to be measured to the camera of the road side facility, s 1 is the area of the license plate corresponding to d 1 in the traffic video frame image, and s is the area of the license plate corresponding to d in the traffic video frame image.
The set value z is obtained by the following formula:
D 0 is the preset distance from the license plate of the vehicle to the camera of the drive test facility, and s 0 is the area of the license plate corresponding to d 0 in the expressway traffic video frame image.
The relation between the final license plate area and the vehicle distance is obtained by deduction according to a camera imaging principle and the conversion relation between a world coordinate system and an image coordinate system of a final license plate image.
The geometric model of the final license plate image in the world coordinate system and the image coordinate system is shown in fig. 4. A. Two points B are two endpoints of a short side of the license plate in the world coordinate system, the number AB represents the edge of the license plate in the world coordinate system, and the number H represents the length of the number AB, namely the height of the license plate in the world coordinate system. The two points A 'and B' respectively represent projections of A, B points in an image coordinate system, the I A 'B' I represents projections of the I AB I in the image coordinate system, the h represents the length of the I A 'B' I, and the height of a license plate in the image coordinate system.
In the world coordinate system, the point A coordinates are (X 2,Y2), and the point B coordinates are (X 1,Y1); in the image coordinate system, the a 'point coordinates are (x 2,y2), and the B' point coordinates are (x 1,y1). d represents the distance from the license plate to the camera of the roadside facility, f is the focal length of the camera of the roadside facility, and O is the optical center of the camera. In the case of neglecting the camera tilt (i.e. the tilt angle is set to 0), the following derivation process is performed to derive the relationship between license plate area s and the distance d of the license plate to the camera of the roadside facility.
According to the similar triangle theorem (ΔABO- ΔA 'B' O in FIG. 4), the following equation can be obtained:
The term transfer is obtained:
the following equations can be obtained in the same manner:
The two y coordinates are subtracted to obtain:
The same principle can be obtained:
in the expressway following distance measuring method based on license plate positioning, the conversion relation between an image coordinate system and a pixel coordinate system is as follows:
Wherein, (x, y) represents the coordinates of any point in the image coordinate system, (u, v) represents the coordinates of the point (x, y) corresponding to the coordinates in the pixel coordinate system, (u 0,v0) represents the coordinates of the midpoint of the image of the video frame of highway traffic in the pixel coordinate system, dx and dy represent the physical dimensions of each pixel on the horizontal axis x and the vertical axis y in the image coordinate system, respectively.
By referring to the Euclidean measurement formula, the relationship between the projected length H of the two endpoints of the short side of the license plate in the image coordinate system and the projected length H of the two endpoints of the short side of the license plate in the world coordinate system can be calculated as follows:
Wherein, (u 1,v1) and (u 2,v2) are the coordinates of two endpoints A and B of the short side of the license plate in the world coordinate system under the pixel coordinate system respectively.
The relation between the projected length W of the two endpoints of the long side of the license plate in the image coordinate system and the projected length W of the two endpoints of the long side of the license plate in the world coordinate system can be obtained by the same method:
Thus, the relationship between the area s of the license plate in the image and the distance d from the license plate to the camera of the roadside facility can be calculated as follows:
I.e.
Wherein,Is a constant value, and is marked as z to obtain:
Wherein d 0 is a preset distance from the license plate of the vehicle to the camera of the drive test facility, for example, 10m, and the value of z can be calculated according to the above formula by counting the area s 0 of the license plate corresponding to d 0 in the image.
Finally, the vehicle running distance d' is obtained as follows:
The distance z between the vehicles to be measured is a set value, d 1 is the distance from the license plate of the first vehicle to be measured to the camera of the road side facility, d is the distance from the license plate of the second vehicle to be measured to the camera of the road side facility, s 1 is the area of the license plate corresponding to d 1 in the traffic video frame image, and s is the area of the license plate corresponding to d in the traffic video frame image.
The distance between the vehicles can be measured by only counting the areas of the vehicles and substituting the areas and the set z value into the formula.
According to the expressway distance measurement method, system and equipment, the corresponding model method is provided for real-time monitoring of the distance between vehicles on the expressway aiming at traffic rear-end collision accidents frequently occurring in high speed, and the road risk can be judged and early warned in time by comparing the distance between vehicles with the safe distance threshold value, so that references are provided for high-speed traffic safety control, the occurrence rate of traffic accidents is effectively reduced, and the road management capability is improved.
According to the expressway inter-vehicle distance measuring method, system and equipment, modeling is carried out according to the view angle of monitoring equipment erected on an expressway, and a high-speed video is processed by using deep learning and traditional image processing technology, so that license plates are detected and positioned; and analyzing the relation between the license plate area and the driving distance by means of a camera imaging principle, and deducing a calculation formula of the vehicle distance to obtain the driving distance. On highways, the most commonly used monitoring equipment is a vision sensor camera. Therefore, the method has high accuracy, is convenient to implement and saves resources. The invention can be applied to high-speed traffic management law enforcement.
In some embodiments, certain aspects of the techniques described above may be implemented by one or more processors of a processing system executing software. The software includes one or more sets of executable instructions stored or otherwise tangibly embodied on a non-transitory computer-readable storage medium. The software may include instructions and certain data that, when executed by one or more processors, operate the one or more processors to perform one or more aspects of the techniques described above. The non-transitory computer readable storage medium may include, for example, a magnetic or optical disk storage device, a solid state storage device such as flash memory, cache, random Access Memory (RAM), or other non-volatile memory device. Executable instructions stored on a non-transitory computer-readable storage medium may be in source code, assembly language code, object code, or other instruction format that is interpreted or otherwise executed by one or more processors.
A computer-readable storage medium may include any storage medium or combination of storage media that can be accessed by a computer system during use to provide instructions and/or data to the computer system. Such storage media may include, but is not limited to, optical media (e.g., compact Disc (CD), digital Versatile Disc (DVD), blu-ray disc), magnetic media (e.g., floppy disk, magnetic tape, or magnetic hard drive), volatile memory (e.g., random Access Memory (RAM) or cache), non-volatile memory (e.g., read Only Memory (ROM) or flash memory), or microelectromechanical system (MEMS) based storage media. The computer-readable storage medium may be embedded in a computing system (e.g., system RAM or ROM), fixedly attached to the computing system (e.g., a magnetic hard drive), removably attached to the computing system (e.g., an optical disk or Universal Serial Bus (USB) based flash memory), or coupled to the computer system via a wired or wireless network (e.g., network-accessible storage (NAS)).
While the application has been disclosed in terms of preferred embodiments, the embodiments are not intended to limit the application. Any equivalent changes or modifications can be made without departing from the spirit and scope of the present application, and are intended to be within the scope of the present application. The scope of the application should therefore be determined by the following claims.
Claims (5)
1. A highway inter-vehicle distance measurement method, comprising:
Inputting a trained YOLOv license plate detection basic model into a license plate image appearing in a highway traffic video frame, and performing primary detection and positioning to obtain an image of an initial license plate positioning area as an initial license plate positioning image;
Cutting out an image of an initial positioning area of the license plate according to the initial detection positioning result, determining the final position of the license plate through image processing operation, and calculating the final license plate area;
Calculating the vehicle distance according to the final license plate area, the relationship between the final license plate area and the vehicle distance;
the relation between the final license plate area and the vehicle distance is as follows:
Wherein d' is the distance between the vehicle and the road, d 1 is the distance from the license plate of the first vehicle to the camera of the road, d is the distance from the license plate of the second vehicle to the camera of the road, s 1 is the area of the license plate corresponding to d 1 in the video frame image of the highway, s is the area of the license plate corresponding to d in the video frame image of the highway, and z is the set value, which is obtained by the following formula:
D 0 is the preset distance from the license plate of the vehicle to the camera of the road side facility, and s 0 is the area of the license plate corresponding to d 0 in the expressway traffic video frame image.
2. The method for measuring the distance between vehicles on the highway according to claim 1, wherein the step of cutting out the image of the initial positioning area of the license plate according to the initial detection positioning result, and determining the final position of the license plate through the image processing operation comprises the steps of:
Carrying out Gaussian blur operation on the license plate initial positioning image I 0 to obtain a license plate image I gas after noise reduction;
the noise-reduced license plate image I gas is subjected to gray-scale pretreatment to obtain a gray-scale license plate image I gray;
Converting the noise-reduced license plate image I gas image into an HSV space to obtain an HSV space license plate image I hsv, and extracting color features in the license plate image;
Carrying out morphological operation and binarization operation on the grayscale license plate image I gray according to the color characteristics in the extracted license plate image I hsv to generate a black-and-white license plate image I bin;
Screening license plate candidate frames from the black-and-white license plate image I bin according to the shape characteristics of the license plates, and determining the final position of the license plates; and if the result of determining the final position of the license plate is empty, taking the initial positioning area of the license plate as the final position of the license plate.
3. A highway inter-vehicle distance measurement system for implementing the highway inter-vehicle distance measurement method according to any one of claims 1-2, which is characterized by comprising a data acquisition module, a deep learning module, an image processing module, a inter-vehicle distance calculation module and a risk early warning module;
The data acquisition module is used for sensing highway conditions by using cameras erected on highway side facilities and acquiring highway traffic video data;
The deep learning module is used for processing the expressway traffic video frame acquired by the data acquisition module into an image, inputting a trained YOLOv license plate detection basic model, and performing primary detection and positioning to acquire an image of an initial license plate positioning area as an initial license plate positioning image;
The image processing module cuts out an image of an initial positioning area of the license plate according to the initial detection positioning result, determines the final position of the license plate through image processing operation, and calculates the area of the license plate in the expressway traffic video frame image to be used as the final license plate area;
The driving distance calculation module calculates the driving distance of the vehicle according to the area of the license plate of each vehicle in the expressway traffic video frame image;
And the risk early warning module is used for judging whether the current vehicle running distance is smaller than a safe running distance threshold value or not and sending a risk prompt for the condition that the current vehicle running distance is smaller than the safe running distance threshold value.
4. A highway following distance measuring device, characterized in that the device comprises a memory and a processor; the memory stores a computer program for implementing a highway inter-vehicle distance measurement method, the processor executing the computer program to implement the steps of the method according to any one of claims 1-2.
5. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310589241.3A CN116665440B (en) | 2023-05-24 | 2023-05-24 | Expressway inter-vehicle distance measurement method, system and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310589241.3A CN116665440B (en) | 2023-05-24 | 2023-05-24 | Expressway inter-vehicle distance measurement method, system and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116665440A CN116665440A (en) | 2023-08-29 |
CN116665440B true CN116665440B (en) | 2024-05-24 |
Family
ID=87711117
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310589241.3A Active CN116665440B (en) | 2023-05-24 | 2023-05-24 | Expressway inter-vehicle distance measurement method, system and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116665440B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101337536A (en) * | 2008-08-11 | 2009-01-07 | 北京中星微电子有限公司 | Vehicle device and method for determining vehicle-distance |
CN106064587A (en) * | 2016-07-06 | 2016-11-02 | 北方工业大学 | Multi-lane vehicle distance recognition method and device based on license plate recognition |
KR20170094592A (en) * | 2016-02-11 | 2017-08-21 | 한국전자통신연구원 | Vehicle control system using vehicle license-plate recognition and vehicle control method thereof |
CN107832788A (en) * | 2017-11-01 | 2018-03-23 | 青岛理工大学 | Vehicle distance measuring method based on monocular vision and license plate recognition |
CN108399403A (en) * | 2018-02-28 | 2018-08-14 | 重庆大学 | A kind of vehicle distance detecting method calculated based on car plate size |
CN108875641A (en) * | 2018-06-21 | 2018-11-23 | 南京信息工程大学 | The long-term driving alongside recognition methods of highway and system |
JP2021196789A (en) * | 2020-06-12 | 2021-12-27 | 日立Astemo株式会社 | Inter-vehicle distance measurement device and vehicle control system |
-
2023
- 2023-05-24 CN CN202310589241.3A patent/CN116665440B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101337536A (en) * | 2008-08-11 | 2009-01-07 | 北京中星微电子有限公司 | Vehicle device and method for determining vehicle-distance |
KR20170094592A (en) * | 2016-02-11 | 2017-08-21 | 한국전자통신연구원 | Vehicle control system using vehicle license-plate recognition and vehicle control method thereof |
CN106064587A (en) * | 2016-07-06 | 2016-11-02 | 北方工业大学 | Multi-lane vehicle distance recognition method and device based on license plate recognition |
CN107832788A (en) * | 2017-11-01 | 2018-03-23 | 青岛理工大学 | Vehicle distance measuring method based on monocular vision and license plate recognition |
CN108399403A (en) * | 2018-02-28 | 2018-08-14 | 重庆大学 | A kind of vehicle distance detecting method calculated based on car plate size |
CN108875641A (en) * | 2018-06-21 | 2018-11-23 | 南京信息工程大学 | The long-term driving alongside recognition methods of highway and system |
JP2021196789A (en) * | 2020-06-12 | 2021-12-27 | 日立Astemo株式会社 | Inter-vehicle distance measurement device and vehicle control system |
Non-Patent Citations (1)
Title |
---|
利用车牌面积进行车距测量的研究;姚春莲 等;《系统仿真学报》;20171108;第29卷(第11期);第2820-2827页 * |
Also Published As
Publication number | Publication date |
---|---|
CN116665440A (en) | 2023-08-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP4109331A1 (en) | Obstacle detection method and apparatus, computer device, and storage medium | |
KR102109941B1 (en) | Method and Apparatus for Vehicle Detection Using Lidar Sensor and Camera | |
EP3171292B1 (en) | Driving lane data processing method, device, storage medium and apparatus | |
CN106647776B (en) | Method and device for judging lane changing trend of vehicle and computer storage medium | |
CN113370977B (en) | Intelligent vehicle forward collision early warning method and system based on vision | |
CN110794406B (en) | Multi-source sensor data fusion system and method | |
Labayrade et al. | In-vehicle obstacles detection and characterization by stereovision | |
CN106295459A (en) | Based on machine vision and the vehicle detection of cascade classifier and method for early warning | |
US10922824B1 (en) | Object tracking using contour filters and scalers | |
CN114359181B (en) | Intelligent traffic target fusion detection method and system based on image and point cloud | |
CN111915883A (en) | Road traffic condition detection method based on vehicle-mounted camera shooting | |
CN110341621B (en) | Obstacle detection method and device | |
JP2012123642A (en) | Image identifying device and program | |
CN114495064A (en) | Monocular depth estimation-based vehicle surrounding obstacle early warning method | |
KR20180098945A (en) | Method and apparatus for measuring speed of vehicle by using fixed single camera | |
CN104915642A (en) | Method and apparatus for measurement of distance to vehicle ahead | |
CN112683228A (en) | Monocular camera ranging method and device | |
CN114119955A (en) | Method and device for detecting potential dangerous target | |
Chen | Road vehicle recognition algorithm in safety assistant driving based on artificial intelligence | |
US20200372264A1 (en) | Image-based road cone recognition method and appartus, storage medium, and vehicle | |
CN112699748B (en) | Human-vehicle distance estimation method based on YOLO and RGB image | |
CN107506739B (en) | Night forward vehicle detection and distance measurement method | |
CN111332306A (en) | Traffic road perception auxiliary driving early warning device based on machine vision | |
CN112733678A (en) | Ranging method, ranging device, computer equipment and storage medium | |
CN117197019A (en) | Vehicle three-dimensional point cloud image fusion method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |