CN111104900A - Expressway cost sorting method and device - Google Patents
Expressway cost sorting method and device Download PDFInfo
- Publication number
- CN111104900A CN111104900A CN201911312883.9A CN201911312883A CN111104900A CN 111104900 A CN111104900 A CN 111104900A CN 201911312883 A CN201911312883 A CN 201911312883A CN 111104900 A CN111104900 A CN 111104900A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- classified
- road condition
- camera
- condition video
- 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.)
- Granted
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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- 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
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- 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
-
- 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)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a highway expense clearing method and a highway expense clearing device, wherein the method comprises the following steps: acquiring a road condition video shot by a camera, determining a running track of a vehicle to be classified according to the video, and intercepting a vehicle picture from the video according to the running track of the vehicle to be classified; extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the samples, and extracting apparent features through the trained vehicle apparent feature extractor; comparing the apparent characteristics with other vehicles, obtaining the road section of the vehicle to be classified in the second road condition video according to the result, and simulating the possible driving path of the vehicle to be classified; calculating the instantaneous speed according to the road condition video; determining a driving path according to the possible driving path and the instantaneous speed; and carrying out expense liquidation calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path. By adopting the method, the sorting of the highway cost can be more accurately realized.
Description
Technical Field
The invention relates to the technical field of highway expense clearing, in particular to a highway expense clearing method and device.
Background
With the rapid development of highway networks in China, the highway between provinces is gradually forming a network. Due to the diversification of highway construction investment channels in China, the arrangement of toll stations cannot be completely overlapped with road sections constructed by main bodies of investors, and therefore, the problem of accurately distinguishing the high-speed cost is very important.
At present, the highway network charge clearing method disclosed in China utilizes a deep convolutional network to extract image features, obtains license plate numbers of vehicles, and then takes the shortest paths of the vehicles corresponding to the license plates as vehicle charging bases. Or continuously acquiring the position information of the vehicle by using the GPS positioning function and the high-speed high-definition picture shooting technology of the mobile communication terminal, respectively calculating the driving paths of the vehicle according to the position information acquired by two different position information acquisition technologies, and selecting a proper driving path as the charging basis of the toll of the highway of the vehicle.
However, in the above highway network cost sorting method, the former is affected by the definition of the license plate of the highway vehicle, and the latter depends on the positioning accuracy of the GPS and the data transmission speed of the mobile terminal, and these unstable factors may cause the identified path to deviate from the actual driving path of the vehicle, so that the purpose of accurately identifying the driving path of the vehicle cannot be achieved, and the profit of the highway investor is affected.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides an expressway cost clearing method for accurately identifying the real driving path of a vehicle.
The embodiment of the invention provides a highway expense clearing method, which comprises the following steps:
acquiring a road condition video shot by a camera, determining a running track of a vehicle to be classified according to the road condition video, and intercepting a vehicle picture from the road condition video according to the running track of the vehicle to be classified;
extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor;
acquiring a second road condition video shot by a second camera, wherein the second camera and the camera are arranged on different road sections, comparing the apparent characteristics with second apparent characteristics of vehicles appearing in the second road condition video, obtaining the road sections of the vehicles to be classified in the second road condition video according to the comparison result, and simulating the possible driving path of the vehicles to be classified according to the road sections;
calculating the vehicle instantaneous speed of the vehicle to be classified according to the road condition video;
determining a running path of the vehicle to be classified according to the possible running path and the instantaneous speed of the vehicle;
and carrying out expense liquidation calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path.
In one embodiment, the method further comprises:
obtaining the vehicles to be classified of each frame of picture in the road condition video, and sequentially calculating the intersection ratio of the vehicles to be classified in two continuous frames, wherein the intersection ratio is the overlapping rate of the vehicles to be classified in the two continuous frames;
and when the intersection ratio is greater than a preset threshold value, connecting the vehicles to be classified in two continuous frames, and forming the running track according to the connection result.
In one embodiment, the method further comprises:
acquiring the transmission frame number per second of the road condition video, and calculating the frame number of the vehicles to be classified in the road condition video;
acquiring a positioning line vertical to the highway and acquiring the distance between the positioning line and the camera;
and calculating the vehicle instantaneous speed of the vehicle to be classified according to the distance between the positioning line and the camera, the per-second transmission frame number of the camera and the frame number of the vehicle to be classified in the running track.
In one embodiment, the method further comprises the following formula:
v＝D÷(L÷FPS÷3600)
wherein v is the vehicle instantaneous speed of the vehicle to be classified, D is the distance between the positioning line and the camera, the unit is km, L is the number of frames of the vehicle to be classified in the driving track, the unit is a frame, FPS is the number of frames transmitted by the camera per second, and the unit is a frame/s.
In one embodiment, the method further comprises:
acquiring the screen occupation ratio of the vehicle to be classified in the road condition video;
and acquiring the time point with the largest screen ratio, and capturing the vehicle picture at the time point.
In one embodiment, the method further comprises:
acquiring a starting point camera and an end point camera corresponding to the possible driving path, and calculating to obtain a time difference according to the occurrence time of the vehicle to be classified in the starting point camera and the end point camera;
calculating to obtain an estimated speed according to the distance duration corresponding to the driving path and the time difference;
comparing the estimated speed with the vehicle instantaneous speed, and keeping the estimated speed with the minimum difference value between the estimated speed and the vehicle instantaneous speed in the comparison result;
and storing the running path corresponding to the estimated speed with the minimum difference as the running path of the vehicle to be classified.
The embodiment of the invention provides a highway expense clearing device, which comprises:
the acquisition module is used for acquiring a road condition video shot by a camera, determining a running track of a vehicle to be classified according to the road condition video, and intercepting a vehicle picture from the road condition video according to the running track of the vehicle to be classified;
the extraction module is used for extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor;
the comparison module is used for acquiring a second road condition video shot by a second camera, the second camera and the camera are arranged on different road sections, the apparent feature is compared with a second apparent feature of a vehicle appearing in the second road condition video, the road section of the vehicle to be classified in the second road condition video is obtained according to the comparison result, and a possible driving path of the vehicle to be classified is simulated according to the road section;
the calculating module is used for calculating the vehicle instantaneous speed of the vehicle to be classified according to the road condition video;
the route determination module is used for determining the running route of the vehicle to be cleared according to the possible running route and the instantaneous speed of the vehicle;
and the clearing module is used for carrying out expense clearing calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path.
In one embodiment, the apparatus further comprises:
the second acquisition module is used for acquiring the vehicles to be classified of each frame of picture in the road condition video and sequentially calculating the intersection ratio of the vehicles to be classified in two continuous frames, wherein the intersection ratio is the overlapping rate of the vehicles to be classified in the two continuous frames;
and the connecting module is used for connecting the vehicles to be classified in two continuous frames when the intersection ratio is greater than a preset threshold value, and forming the driving track according to the connecting result.
The embodiment of the invention provides electronic equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of the highway expense liquidation method.
Embodiments of the present invention provide a non-transitory computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-mentioned highway toll collection method.
According to the highway cost clearing method and device provided by the embodiment of the invention, the road condition video shot by the camera is obtained, the driving track of the vehicle to be cleared is determined according to the video, and the vehicle picture is intercepted from the road condition video according to the driving track; extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor; acquiring a second road condition video shot by a second camera, wherein the second camera and the camera are arranged on different road sections, comparing the apparent characteristics with second apparent characteristics of vehicles appearing in the second road condition video, obtaining a road section of the vehicle to be classified in the second road condition video according to the comparison result, and simulating a possible driving path of the vehicle to be classified according to the road section; calculating the vehicle instantaneous speed of the vehicle to be classified according to the running track; determining a running path of a vehicle to be classified according to the possible running path and the instantaneous speed of the vehicle; and carrying out expense liquidation calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path. The method can accurately determine the vehicle running track by comparing the extracted apparent characteristics of the vehicle, and accurately count the expressway cost among various contract main bodies according to the determined running track, thereby ensuring the income of various investors on the expressway.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a highway fare clearance method in an embodiment of the present invention;
FIG. 2 is a block diagram of an expressway cost liquidation apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a highway cost liquidation method according to an embodiment of the present invention, and as shown in fig. 1, the embodiment of the present invention provides a highway cost liquidation method, including:
step S101, acquiring a road condition video shot by a camera, determining a running track of a vehicle to be classified according to the road condition video, and capturing a vehicle picture from the road condition video according to the running track of the vehicle to be classified.
Specifically, the obtaining method for determining the driving track of the vehicle to be classified may be: firstly, the number of frames of the vehicle appearing in the road condition video and the specific position of the vehicle in the current frame are located, and the located data can include but is not limited to: f-id (frame number), box-id (id of the vehicle under the current frame, such as self-defined vehicle number and the like), x (x-axis coordinate (taking a camera image as a coordinate)), y (y-axis coordinate), w (width of a boundary box of a positioning result), h (height of the boundary box of the positioning result), score (confidence degree of the positioning result ) and other data, deleting the positioning result of which the confidence degree, the length, the width and the length-width ratio are not in a threshold range, finally connecting the rest positioning results, namely the driving track of the vehicle to be sorted, and selecting a picture containing the vehicle to be sorted from the driving track corresponding to the driving track of the vehicle to be sorted after obtaining the driving track of the vehicle to be sorted according to the driving track of the vehicle shot by the camera.
And S102, extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor.
Specifically, the spatiotemporal characteristics of the vehicle are: temporally, the same vehicle can only appear at one location in the same frame; spatially, the spatial displacement of the same vehicle is to be continuous in the direction of highway travel. In the pictures containing the vehicles to be classified, positive samples are used when the space-time characteristics are met, negative samples are used when the space-time characteristics are not met, a vehicle apparent characteristic extractor (a convolutional neural network in the prior art) is trained through the positive samples and the negative samples, after the trained vehicle apparent characteristic extractor is obtained, pictures corresponding to the vehicles are input, and corresponding apparent characteristics (including colors, vehicle types and local representative visible and invisible information of vehicle surroundings) are obtained, wherein generally speaking, the apparent characteristics of the vehicles are multidimensional matrixes.
And step S103, calculating the vehicle instantaneous speed of the vehicle to be classified according to the running track.
Specifically, the length of the running track is the length of the number of frames of the vehicle to be classified appearing in the road condition video, the actual distance of the running track can be obtained by a method of distance measurement on the real ground, and the vehicle instantaneous speed of the vehicle to be classified can be calculated according to the actual distance of the running track and the length of the number of frames.
Step S104, acquiring a second road condition video shot by a second camera, wherein the second camera and the camera are arranged on different road sections, comparing the apparent characteristics with second apparent characteristics of vehicles appearing in the second road condition video, obtaining the appearing road sections of the vehicles to be classified in the second road condition video according to the comparison result, and simulating the possible driving path of the vehicles to be classified according to the appearing road sections;
specifically, other (second) road condition videos shot by other (second) cameras are obtained, apparent features of vehicles appearing in the other road condition videos are obtained, the apparent features of the vehicles to be classified obtained according to the calculation are compared with the apparent features of the vehicles shot by the cameras of other different road sections, when the apparent features are the same or similar (the difference value is smaller than the threshold value), it is indicated that the vehicles to be classified also appear in the cameras of other road sections, namely the vehicles to be classified also appear in the road sections corresponding to the other cameras, and possible running paths of all the vehicles to be classified are simulated for the vehicles to be classified according to each camera through which the vehicles to be classified pass.
Step S105, determining the driving path of the vehicle to be classified according to the possible driving path and the instantaneous speed of the vehicle;
specifically, according to the real highway network structure and the cameras on the highway, the camera videos corresponding to the possible running paths can be correspondingly obtained, the running duration of the vehicle to be classified on the possible running paths is further obtained, the speed on the running paths can be calculated according to the path length and the running duration of the running paths, the speed on the running paths is compared with the instantaneous speed of the vehicle, and the running paths of the vehicle to be classified are determined according to the running paths corresponding to the running path speed with the minimum speed difference in the comparison result.
And step S106, carrying out expense liquidation calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path.
Specifically, since the charging standards of different driving routes may be different, the liquidation calculation needs to be performed according to the charging standards of different routes and different routes.
According to the highway cost clearing method and device provided by the embodiment of the invention, a road condition video shot by a camera is obtained, a running track of a vehicle to be cleared is determined according to the video, and a vehicle picture is intercepted from the road condition video according to the running track; extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor; comparing the apparent characteristics with various road condition videos shot by cameras of different road sections to obtain the appearing road sections of the vehicles to be classified in the various road condition videos, and simulating the possible driving paths of the vehicles to be classified according to the appearing road sections; calculating the vehicle instantaneous speed of the vehicle to be classified according to the running track; determining a running path of a vehicle to be classified according to the possible running path and the instantaneous speed of the vehicle; and carrying out expense liquidation calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path. The method can more accurately determine the vehicle running track according to the vehicle instantaneous speed, and carry out the liquidation calculation of the highway cost according to the determined running track, thereby ensuring the income of the highway investor.
On the basis of the above embodiment, the highway fee liquidation method further includes:
obtaining the vehicles to be classified of each frame of picture in the road condition video, and sequentially calculating the intersection ratio of the vehicles to be classified in two continuous frames, wherein the intersection ratio is the overlapping rate of the vehicles to be classified in the two continuous frames;
and when the intersection ratio is greater than a preset threshold value, connecting the vehicles to be classified in two continuous frames, and forming the running track according to the connection result.
In the embodiment of the invention, the server can take the result of positioning the vehicles to be classified in the first frame containing the vehicles to be classified in the road condition video as the positioning result of the vehicles, then read in the next frame, and sequentially calculate the intersection and parallel ratio of all the positioning results in two continuous frames, namely the overlapping rate of the areas occupied by the vehicles to be classified in the positioning results in the two continuous frames, if the intersection and parallel ratio is greater than the threshold value, the positioning results in the two continuous frames indicate that the same vehicle to be classified is present, and then connect each frame of images in the road condition video into tracks according to the positioning results in the two adjacent frames. In addition, when the intersection ratio is smaller than the threshold value, it is indicated that one of the frames of pictures may identify the positioning result of other vehicles, and the positioning results of other vehicles are not connected.
The embodiment of the invention calculates the overlapping rate of each frame of picture to judge whether the current frame is the positioning result of the same vehicle to be classified, and connects the positioning results of the same vehicle to be classified according to the judgment result, thereby preventing the driving tracks of other vehicles from influencing the calculation of the subsequent steps.
On the basis of the above embodiment, the highway fee liquidation method further includes:
acquiring a positioning line vertical to the highway and acquiring the distance between the positioning line and the camera;
acquiring the transmission frame number per second of the camera, and calculating the frame number of the vehicle to be classified in the running track;
and calculating the vehicle instantaneous speed of the vehicle to be classified according to the distance between the positioning line and the camera, the per-second transmission frame number of the camera and the frame number of the vehicle to be classified in the running track.
In the embodiment of the invention, the positioning line can be a positioning point of a first frame of a vehicle to be distinguished appearing in the road condition video, and a positioning line vertical to the expressway is determined through the positioning point. After the positioning line is determined, the distance between the positioning line and the camera is obtained, wherein when the camera is at a high position, the distance between the horizontal plane of the expressway corresponding to the camera and the positioning line can be obtained, then the transmission frame per second of the camera and the number of frames of the vehicles to be classified are obtained, the number of frames of the vehicles to be classified can be obtained through calculation of the first frame and the last frame of the vehicles to be classified in the road condition video, the duration of the vehicles to be classified passing through the shooting range of the camera can be obtained according to the transmission frame per second of the camera and the number of frames of the vehicles to be classified in the driving track, and then the instantaneous speed of the vehicles is calculated by combining the distance between the positioning line and the camera. The specific formula for calculating the vehicle instantaneous speed of the vehicle to be classified can be as follows:
v＝D÷(L÷FPS÷3600)
wherein v is the vehicle instantaneous speed of the vehicle to be classified, D is the distance between a positioning line and the camera, the unit is km, L is the number of frames of the vehicle to be classified in the driving track, the unit is a frame, and FPS is the number of frames transmitted by the camera per second, and the unit is a frame/s.
According to the embodiment of the invention, the vehicle instantaneous speed of the vehicle to be classified is obtained through the number of frames transmitted per second by the camera, the number of frames of the vehicle to be classified in the driving track and the distance between the positioning line and the camera, so that more accurate vehicle instantaneous speed can be obtained.
On the basis of the above embodiment, the highway fee liquidation method further includes:
acquiring the screen occupation ratio of the vehicle to be classified in the road condition video;
and acquiring the time point with the largest screen ratio, and capturing the vehicle picture at the time point.
When the vehicle picture of the vehicle to be classified in the road condition video is captured, the screen proportion of the vehicle to be classified in the road condition video is analyzed, the screen proportion can be the proportion of the size of the vehicle in the current display to the whole display screen, the time point of the maximum screen proportion of the vehicle to be classified is obtained, and the picture of the vehicle to be classified at the current time point is captured for subsequent calculation.
According to the embodiment of the invention, the picture of the vehicle to be classified is captured by acquiring the time point when the screen occupation ratio of the vehicle to be classified is maximum, so that the vehicle to be classified is larger and clearer on the picture, and the subsequent data acquisition and calculation are facilitated.
On the basis of the above embodiment, the highway fee liquidation method further includes:
acquiring a starting point camera and an end point camera corresponding to the possible driving path, and calculating to obtain a time difference according to the occurrence time of the vehicle to be classified in the starting point camera and the end point camera;
calculating to obtain an estimated speed according to the distance duration corresponding to the driving path and the time difference;
comparing the estimated speed with the vehicle instantaneous speed, and keeping the estimated speed with the minimum difference value between the estimated speed and the vehicle instantaneous speed in the comparison result;
and determining the running path corresponding to the estimated speed with the minimum difference value as the running path of the vehicle to be classified.
In the embodiment of the invention, the distance between the starting point camera and the end point camera of the possible driving path can be obtained according to the structure of the real highway network. In the above steps, the cameras through which the vehicle passes are obtained, so that the specific time of the vehicle passing through each camera can be obtained in the road condition video, and the time difference between the two cameras can be calculated. And calculating the average speed of the vehicle on the path between the two cameras according to the distance and the time. And comparing the instantaneous speed with the average speed, deleting a path from the simulated possible driving paths if a difference value between two speed values is found to be larger by comparing a certain path, sequentially checking all paths which accord with the matching result, and reserving a path with the minimum speed difference to judge as the driving path of the vehicle.
According to the embodiment of the invention, the speed corresponding to each possible path is calculated and compared with the instantaneous speed, the most possible running path of the vehicle to be classified can be determined according to the comparison result, and then accurate expense classification calculation is carried out among all the contract main bodies.
Fig. 2 is a device for clearing highway fees according to an embodiment of the present invention, including: an obtaining module 201, an extracting module 202, a comparing module 203, a calculating module 204, a path determining module 205 and an inventory module 206, wherein:
the acquiring module 201 is configured to acquire a road condition video shot by the camera, determine a driving track of a vehicle to be classified according to the road condition video, and capture a vehicle picture from the road condition video according to the driving track of the vehicle.
The extraction module 202 is configured to extract positive and negative samples in the vehicle picture according to the space-time characteristics of the vehicle, train a vehicle apparent feature extractor according to the positive and negative samples, and extract the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor.
The comparison module 203 is configured to acquire a second road condition video shot by a second camera, where the second camera and the camera are arranged on different road sections, compare the apparent feature with a second apparent feature of a vehicle appearing in the second road condition video, obtain a road section of the vehicle to be classified in the second road condition video according to a comparison result, and simulate a possible driving path of the vehicle to be classified according to the road section.
And the calculating module 204 is used for calculating the vehicle instantaneous speed of the vehicle to be classified according to the road condition video.
And the path determining module 205 is used for determining the running path of the vehicle to be classified according to the possible running path and the instantaneous speed of the vehicle.
A scoring module 206 for calculating the fare score among the highway investment bodies according to the driving route and the charging standard corresponding to the driving route
In one embodiment, the apparatus may further comprise:
and the second acquisition module is used for acquiring the vehicles to be classified of each frame of picture in the road condition video, and sequentially calculating the intersection and parallel ratio of the vehicles to be classified in two continuous frames, wherein the intersection and parallel ratio is the overlapping rate of the vehicles to be classified in the two continuous frames.
And the connecting module is used for connecting the vehicles to be classified in two continuous frames when the intersection ratio is greater than a preset threshold value, and forming a driving track according to a connecting result.
In one embodiment, the apparatus may further comprise:
and the third acquisition module is used for acquiring the transmission frame number per second of the road condition video and calculating the frame number of the vehicles to be classified in the road condition video.
And the fourth acquisition module is used for acquiring a positioning line vertical to the expressway and acquiring the distance between the positioning line and the camera.
And the second calculation module is used for calculating the vehicle instantaneous speed of the vehicle to be classified according to the distance between the positioning line and the camera, the transmission frame number per second of the camera and the frame number of the vehicle to be classified in the running track.
In one embodiment, the apparatus may further comprise:
the instantaneous speed calculating module is used for calculating the vehicle instantaneous speed of the vehicle to be classified according to the following formula:
v＝D÷(L÷FPS÷3600)
wherein v is the vehicle instantaneous speed of the vehicle to be classified, D is the distance between a positioning line and the camera, the unit is km, L is the number of frames of the vehicle to be classified in the driving track, the unit is a frame, and FPS is the number of frames transmitted by the camera per second, and the unit is a frame/s.
In one embodiment, the apparatus may further comprise:
and the fifth acquisition module is used for acquiring the screen occupation ratio of the vehicles to be classified in the road condition video.
And the sixth acquisition module is used for acquiring the time point with the largest screen ratio and intercepting the vehicle picture at the time point.
In one embodiment, the apparatus may further comprise:
and the seventh acquisition module is used for acquiring a starting point camera and an end point camera corresponding to the possible driving path and calculating the time difference according to the occurrence time of the vehicles to be classified in the starting point camera and the end point camera.
And the third calculation module is used for calculating to obtain the estimated speed according to the distance duration and the time difference corresponding to the driving path.
And the comparison module is used for comparing the estimated speed with the instantaneous speed of the vehicle and keeping the estimated speed with the minimum difference between the estimated speed and the instantaneous speed of the vehicle in the comparison result.
And the storage module is used for storing the running path corresponding to the estimated speed with the minimum difference as the running path of the vehicle to be classified.
For the specific definition of the highway expense counting device, reference may be made to the above definition of the highway expense counting method, which is not described herein again. All or part of the modules in the highway toll collection device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Fig. 3 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 3: a processor (processor)301, a memory (memory)302, a communication Interface (Communications Interface)303 and a communication bus 304, wherein the processor 301, the memory 302 and the communication Interface 303 complete communication with each other through the communication bus 304. The processor 301 may call logic instructions in the memory 302 to perform the following method: acquiring a road condition video shot by a camera, determining a running track of a vehicle to be classified according to the road condition video, and intercepting a vehicle picture from the road condition video according to the running track of the vehicle to be classified; extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor; acquiring a second road condition video shot by a second camera, wherein the second camera and the camera are arranged on different road sections, comparing the apparent characteristics with second apparent characteristics of vehicles appearing in the second road condition video, obtaining the road sections of the vehicles to be classified in the second road condition video according to the comparison result, and simulating the possible driving path of the vehicles to be classified according to the road sections; calculating the vehicle instantaneous speed of the vehicle to be classified according to the road condition video; determining a running path of the vehicle to be classified according to the possible running path and the instantaneous speed of the vehicle; and carrying out expense liquidation calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path.
Furthermore, the logic instructions in the memory 302 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the transmission method provided in the foregoing embodiments when executed by a processor, and for example, the method includes: acquiring a road condition video shot by a camera, determining a running track of a vehicle to be classified according to the road condition video, and intercepting a vehicle picture from the road condition video according to the running track of the vehicle to be classified; extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor; acquiring a second road condition video shot by a second camera, wherein the second camera and the camera are arranged on different road sections, comparing the apparent characteristics with second apparent characteristics of vehicles appearing in the second road condition video, obtaining the road sections of the vehicles to be classified in the second road condition video according to the comparison result, and simulating the possible driving path of the vehicles to be classified according to the road sections; calculating the vehicle instantaneous speed of the vehicle to be classified according to the road condition video; determining a running path of the vehicle to be classified according to the possible running path and the instantaneous speed of the vehicle; and carrying out expense liquidation calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A highway fee liquidation method is characterized by comprising the following steps:
acquiring a road condition video shot by a camera, determining a running track of a vehicle to be classified according to the road condition video, and intercepting a vehicle picture from the road condition video according to the running track of the vehicle to be classified;
extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor;
acquiring a second road condition video shot by a second camera, wherein the second camera and the camera are arranged on different road sections, comparing the apparent characteristics with second apparent characteristics of vehicles appearing in the second road condition video, obtaining the road sections of the vehicles to be classified in the second road condition video according to the comparison result, and simulating the possible driving path of the vehicles to be classified according to the appearing road sections;
calculating the vehicle instantaneous speed of the vehicle to be classified according to the road condition video;
determining a running path of the vehicle to be classified according to the possible running path and the instantaneous speed of the vehicle;
and carrying out expense liquidation calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path.
2. The highway cost liquidation method according to claim 1, wherein the step of determining the driving track of the vehicle to be liquidated according to the road condition video comprises the following steps:
obtaining the vehicles to be classified of each frame of picture in the road condition video, and sequentially calculating the intersection ratio of the vehicles to be classified in two continuous frames, wherein the intersection ratio is the overlapping rate of the vehicles to be classified in the two continuous frames;
and when the intersection ratio is greater than a preset threshold value, connecting the vehicles to be classified in two continuous frames, and forming the running track according to the connection result.
3. The highway cost liquidation method according to claim 1, wherein the step of calculating the vehicle instantaneous speed of the vehicle to be liquidated according to the road condition video comprises the following steps:
acquiring the transmission frame number per second of the road condition video, and calculating the frame number of the vehicles to be classified in the road condition video;
acquiring a positioning line vertical to the highway and acquiring the distance between the positioning line and the camera;
and calculating the vehicle instantaneous speed of the vehicle to be classified according to the distance between the positioning line and the camera, the per-second transmission frame number of the camera and the frame number of the vehicle to be classified in the running track.
4. A highway cost liquidation method according to claim 3 wherein said vehicle instantaneous speed of the vehicle to be liquidated is calculated by the formula:
v＝D÷(L÷FPS÷3600)
wherein v is the vehicle instantaneous speed of the vehicle to be classified, D is the distance between the positioning line and the camera, the unit is km, L is the number of frames of the vehicle to be classified in the driving track, the unit is a frame, FPS is the number of frames transmitted by the camera per second, and the unit is a frame/s.
5. The highway cost liquidation method according to claim 1, wherein the step of capturing a vehicle picture from the road condition video according to the driving track of the vehicle to be liquidated comprises the following steps:
acquiring the screen occupation ratio of the vehicle to be classified in the road condition video;
and acquiring the time point with the largest screen ratio, and capturing the vehicle picture at the time point.
6. The highway fare liquidation method of claim 1 further comprising:
acquiring a starting point camera and an end point camera corresponding to the possible driving path, and calculating to obtain a time difference according to the occurrence time of the vehicle to be classified in the starting point camera and the end point camera;
calculating to obtain an estimated speed according to the distance duration corresponding to the driving path and the time difference;
comparing the estimated speed with the vehicle instantaneous speed, and keeping the estimated speed with the minimum difference value between the estimated speed and the vehicle instantaneous speed in the comparison result;
and storing the running path corresponding to the estimated speed with the minimum difference as the running path of the vehicle to be classified.
7. An expressway cost liquidation device, comprising:
the acquisition module is used for acquiring a road condition video shot by a camera, determining a running track of a vehicle to be classified according to the road condition video, and intercepting a vehicle picture from the road condition video according to the running track of the vehicle to be classified;
the extraction module is used for extracting positive and negative samples from the vehicle picture according to the space-time characteristics of the vehicle, training a vehicle apparent feature extractor according to the positive and negative samples, and extracting the apparent features of the vehicle to be classified through the trained vehicle apparent feature extractor;
the comparison module is used for acquiring a second road condition video shot by a second camera, the second camera and the camera are arranged on different road sections, the apparent feature is compared with a second apparent feature of a vehicle appearing in the second road condition video, the road section of the vehicle to be classified in the second road condition video is obtained according to the comparison result, and a possible driving path of the vehicle to be classified is simulated according to the road section;
the calculating module is used for calculating the vehicle instantaneous speed of the vehicle to be classified according to the road condition video;
the route determination module is used for determining the running route of the vehicle to be cleared according to the possible running route and the instantaneous speed of the vehicle;
and the clearing module is used for carrying out expense clearing calculation among the highway investment bodies according to the driving path and the charging standard corresponding to the driving path.
8. The apparatus of claim 7, further comprising:
the second acquisition module is used for acquiring the vehicles to be classified of each frame of picture in the road condition video and sequentially calculating the intersection ratio of the vehicles to be classified in two continuous frames, wherein the intersection ratio is the overlapping rate of the vehicles to be classified in the two continuous frames;
and the connecting module is used for connecting the vehicles to be classified in two continuous frames when the intersection ratio is greater than a preset threshold value, and forming the driving track according to the connecting result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the highway fare liquidation method according to any one of claims 1 to 6 are carried out when the program is executed by the processor.
10. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, performs the steps of the highway fare liquidation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911312883.9A CN111104900B (en) | 2019-12-18 | 2019-12-18 | Highway fee sorting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911312883.9A CN111104900B (en) | 2019-12-18 | 2019-12-18 | Highway fee sorting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111104900A true CN111104900A (en) | 2020-05-05 |
| CN111104900B CN111104900B (en) | 2023-07-14 |
Family
ID=70422195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911312883.9A Active CN111104900B (en) | 2019-12-18 | 2019-12-18 | Highway fee sorting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111104900B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120288140A1 (en) * | 2011-05-13 | 2012-11-15 | Carnegie Mellon University | Method and system for selecting a video analysis method based on available video representation features |
| CN106991725A (en) * | 2017-03-02 | 2017-07-28 | 上海市城市建设设计研究总院（集团）有限公司 | Region freeway net vehicle running path analytical equipment and analysis method |
| CN107886757A (en) * | 2017-10-19 | 2018-04-06 | 深圳市元征软件开发有限公司 | Vehicle positioning method and parking management equipment |
| CN108038925A (en) * | 2017-12-13 | 2018-05-15 | 广州华工信息软件有限公司 | A kind of expressway tol lcollection method, device, equipment and storage medium |
| CN109903404A (en) * | 2019-04-23 | 2019-06-18 | 北京梦陀螺科技有限公司 | A kind of vehicle on highway charging system and its working method |
| CN110443828A (en) * | 2019-07-31 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Method for tracing object and device, storage medium and electronic device |
-
2019
- 2019-12-18 CN CN201911312883.9A patent/CN111104900B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120288140A1 (en) * | 2011-05-13 | 2012-11-15 | Carnegie Mellon University | Method and system for selecting a video analysis method based on available video representation features |
| CN106991725A (en) * | 2017-03-02 | 2017-07-28 | 上海市城市建设设计研究总院（集团）有限公司 | Region freeway net vehicle running path analytical equipment and analysis method |
| CN107886757A (en) * | 2017-10-19 | 2018-04-06 | 深圳市元征软件开发有限公司 | Vehicle positioning method and parking management equipment |
| CN108038925A (en) * | 2017-12-13 | 2018-05-15 | 广州华工信息软件有限公司 | A kind of expressway tol lcollection method, device, equipment and storage medium |
| CN109903404A (en) * | 2019-04-23 | 2019-06-18 | 北京梦陀螺科技有限公司 | A kind of vehicle on highway charging system and its working method |
| CN110443828A (en) * | 2019-07-31 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Method for tracing object and device, storage medium and electronic device |
Non-Patent Citations (2)
| Title |
|---|
| "Hedging Deep Features for Visual Tracking", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
| 王三军等: "湖北高速公路收费清分方法与校核***研究", 《交通信息与安全》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111104900B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108986465B (en) | Method, system and terminal equipment for detecting traffic flow | |
| CN109087510B (en) | Traffic monitoring method and device | |
| CN109145708B (en) | Pedestrian flow statistical method based on RGB and D information fusion | |
| CN108388879A (en) | Mesh object detection method, device and storage medium | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| US9846823B2 (en) | Traffic lane boundary line extraction apparatus and method of extracting traffic lane boundary line | |
| CN112070074B (en) | Object detection method and device, terminal equipment and storage medium | |
| CN111612104B (en) | Vehicle loss assessment image acquisition method, device, medium and electronic equipment | |
| CN105631418A (en) | People counting method and device | |
| CN112434566B (en) | Passenger flow statistics method and device, electronic equipment and storage medium | |
| CN112651398B (en) | Snapshot control method and device for vehicle and computer readable storage medium | |
| CN110991297A (en) | Target positioning method and system based on scene monitoring | |
| CN107506753B (en) | Multi-vehicle tracking method for dynamic video monitoring | |
| CN112447060A (en) | Method and device for recognizing lane and computing equipment | |
| CN114495520A (en) | Vehicle counting method, device, terminal and storage medium | |
| CN111950507B (en) | Data processing and model training method, device, equipment and medium | |
| CN113591643A (en) | Underground vehicle station entering and exiting detection system and method based on computer vision | |
| CN115641728B (en) | ETC charge auditing method, ETC charge auditing system, electronic equipment and medium | |
| CN114078319A (en) | Method and device for detecting potential hazard site of traffic accident | |
| CN111104900B (en) | Highway fee sorting method and device | |
| CN113177504B (en) | Vehicle queuing information detection method and device, electronic equipment and storage medium | |
| CN115953759A (en) | Method and device for detecting parking space limiter, electronic equipment and storage medium | |
| CN115909241A (en) | Lane line detection method, system, electronic device and storage medium | |
| CN114913470A (en) | Event detection method and device | |
| CN112749577A (en) | Parking space detection method and device |
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 |