CN111126397A - Dynamic inspection method, system, terminal and medium for vehicle chassis - Google Patents

Dynamic inspection method, system, terminal and medium for vehicle chassis Download PDF

Info

Publication number
CN111126397A
CN111126397A CN201911378637.3A CN201911378637A CN111126397A CN 111126397 A CN111126397 A CN 111126397A CN 201911378637 A CN201911378637 A CN 201911378637A CN 111126397 A CN111126397 A CN 111126397A
Authority
CN
China
Prior art keywords
vehicle
information
target vehicle
license plate
detected
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911378637.3A
Other languages
Chinese (zh)
Inventor
周康明
陈�光
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Eye Control Technology Co Ltd
Original Assignee
Shanghai Eye Control Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Eye Control Technology Co Ltd filed Critical Shanghai Eye Control Technology Co Ltd
Priority to CN201911378637.3A priority Critical patent/CN111126397A/en
Publication of CN111126397A publication Critical patent/CN111126397A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/63—Scene text, e.g. street names
    • 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
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • 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
    • G06T2207/30241—Trajectory
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

The application provides a dynamic inspection method, a system, a terminal and a medium for a vehicle chassis, comprising the following steps: collecting video data of a chassis station of a vehicle to be detected; acquiring license plate number information of a vehicle to be detected; comparing the number plate information with license plate number information of a target vehicle, and if the comparison result information determines that the vehicle to be detected is the target vehicle, acquiring tracking track information of the target vehicle; acquiring initial position, end position information, initial time and end time information of the target vehicle according to the tracking track information; and judging whether the target vehicle moves according to the initial position information and the end position information, and if so, judging whether the dynamic inspection duration of the chassis meets the specification according to the initial time information and the end time information. The problem of prior art can have artificial negligence and leak in the testing process for annual inspection chassis dynamic detection efficiency is not high is solved, this application improves the standardization of supervise inspection process, prevents the problem that artificial negligence brought, makes annual inspection chassis dynamic detection efficiency and rate of accuracy improve.

Description

Dynamic inspection method, system, terminal and medium for vehicle chassis
Technical Field
The present application relates to the field of annual inspection of motor vehicles, and more particularly, to a dynamic inspection method, system, terminal and medium for vehicle chassis.
Background
With the rapid development of economy and the improvement of living standard of materials, vehicles are more and more popular in daily life of people, and the number of motor vehicles in China reaches 3.4 hundred million by 6 months in 2019. The vehicle brings great convenience to people in daily travel, and meanwhile, the safety problem of the vehicle is concerned more and more. The motor vehicles are required to be subjected to vehicle security inspection regularly according to relevant regulations, and the regular vehicle security inspection can help vehicle owners to find vehicles in time, so that potential safety hazards are effectively avoided. However, as vehicle keeping volumes increase year by year, annual vehicle inspection workload of relevant departments and institutions increases dramatically. Meanwhile, human negligence and holes can exist in the inspection process.
Content of application
In view of the above disadvantages of the prior art, an object of the present application is to provide a method, a system, a terminal and a medium for dynamically inspecting a vehicle chassis, which are used to solve the problem in the prior art that as the vehicle retention capacity increases year by year, the annual inspection workload of vehicles in related departments and institutions increases sharply, so that human negligence and holes may exist in the inspection process, and the dynamic inspection efficiency of the annual inspection chassis is not high.
To achieve the above and other related objects, the present application provides a method for dynamic inspection of a vehicle chassis, comprising: collecting video data of a chassis station of a vehicle to be detected; acquiring license plate number information of the vehicle to be detected according to the video data; comparing the license plate number information with license plate number information of a target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, acquiring tracking track information of the target vehicle according to the video data; acquiring initial position information, end position information, initial time information and end time information of the target vehicle according to the tracking track information; and judging whether the target vehicle moves or not according to the initial position information and the end position information, and if so, judging whether the dynamic inspection duration of the chassis meets the regulation or not according to the initial time information and the end time information.
In an embodiment of the application, the obtaining of the license plate number information of the vehicle to be inspected according to the video data includes: respectively inputting each frame image included in the video data into a vehicle detection model based on deep learning so as to output an image including the vehicle to be detected; extracting the vehicle to be detected according to the image of the vehicle to be detected; inputting the extracted vehicle to be detected into a license plate detection model based on deep learning so as to output license plate position information of the vehicle to be detected; and identifying the license plate number information according to the license plate position information of the vehicle to be detected.
In an embodiment of the application, will extract wait to examine a license plate detection model that waits to examine vehicle input based on degree of depth study, with the output wait to examine the license plate positional information of vehicle, include: when the number of the vehicles to be detected is multiple, storing each vehicle to be detected, and inputting each vehicle to be detected into a license plate detection model based on deep learning respectively so as to output license plate position information corresponding to each vehicle to be detected respectively; according to wait to examine the license plate position information discernment of vehicle license plate number information specifically does: and identifying the license plate number information according to the license plate position information of the vehicle to be detected.
In an embodiment of the present application, the obtaining tracking track information of the target vehicle according to the video data includes: acquiring coordinate information of the target vehicle in a target frame image of the video data; wherein the output image of the frame corresponding to the image of the vehicle to be detected is a target frame image; and obtaining the tracking track information of the target vehicle according to the coordinate information.
In an embodiment of the present application, obtaining the tracking trajectory information of the target vehicle according to the coordinate information includes: acquiring a preset target tracking algorithm; and obtaining the tracking track information of the target vehicle according to the target tracking algorithm and the coordinate information.
In an embodiment of the present application, a method of obtaining end position information and end time information of the target vehicle according to the tracking track information includes: when the target vehicle runs out of a detection site or the video for the target vehicle is finished, stopping tracking the target vehicle, and recording the position and the current time of the target vehicle when the tracking of the target vehicle is stopped; taking the position of the target vehicle when the tracking of the target vehicle is stopped as the end position information; and taking the current time as the end time information.
In an embodiment of the present application, the determining whether the target vehicle moves according to the initial position information and the end position information, and if so, determining whether the inspection duration of the chassis dynamics meets the specification according to the initial time information and the end time information includes: obtaining the coordinates of the center point of the initial position target vehicle and the coordinates of the center point of the end position target vehicle according to the initial position information and the end position information; obtaining the distance between the initial position and the end position according to the coordinates of the central point of the initial position target vehicle and the coordinates of the central point of the end position target vehicle; determining that the target vehicle moves according to the distance between the initial position and the end position; obtaining the total dynamic detection time of the target vehicle chassis according to the initial time and the end time; when the total duration is longer than the required duration, the dynamic detection result of the vehicle annual inspection chassis is a qualified detection result; otherwise, the result is a detection failure result.
In order to achieve the above and other related objects, the present application provides a system for dynamically inspecting a vehicle chassis, including a video data acquisition module for acquiring video data of a chassis station of a vehicle to be inspected; the license plate number information module is used for acquiring license plate number information of the vehicle to be detected according to the video data; the tracking track module is used for comparing the license plate number information with license plate number information of a target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, the tracking track information of the target vehicle is obtained according to the video data; the position and time determining module is used for acquiring initial position information, end position information, initial time information and end time information of the target vehicle according to the tracking track information; and the vehicle chassis dynamic detection result module is used for judging whether the target vehicle moves according to the initial position information and the end position information, and if so, judging whether the chassis dynamic detection duration meets the specification according to the initial time information and the end time information.
To achieve the above and other related objects, the present application provides a vehicle chassis dynamics verification terminal, comprising: a memory for storing a computer program; and the processor is used for running the computer program to execute the dynamic checking method of the vehicle chassis.
To achieve the above and other related objects, the present application provides a computer-readable storage medium storing a computer program which, when executed, implements the dynamic checking method of a vehicle chassis.
As described above, the dynamic inspection method, system, terminal and medium for vehicle chassis according to the present application have the following advantages: the method for analyzing the video data by utilizing the deep learning related technology helps standardize the effective supervision and inspection process of relevant departments and mechanisms of vehicle annual inspection, prevents the problems caused by human negligence, and greatly improves the dynamic detection efficiency and accuracy of the annual inspection chassis.
Drawings
Fig. 1 is a schematic structural diagram of an implementation environment in an embodiment of the present application.
Fig. 2 is a flow chart illustrating a method for dynamically checking a vehicle chassis according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of a system for checking the vehicle annual inspection chassis dynamics according to an embodiment of the present application.
Fig. 4 is a schematic structural diagram of an inspection terminal for vehicle annual inspection chassis dynamics according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It is noted that in the following description, reference is made to the accompanying drawings which illustrate several embodiments of the present application. It is to be understood that other embodiments may be utilized and that mechanical, structural, electrical, and operational changes may be made without departing from the spirit and scope of the present application. The following detailed description is not to be taken in a limiting sense, and the scope of embodiments of the present application is defined only by the claims of the issued patent. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. Spatially relative terms, such as "upper," "lower," "left," "right," "lower," "below," "lower," "over," "upper," and the like, may be used herein to facilitate describing one element or feature's relationship to another element or feature as illustrated in the figures.
Throughout the specification, when a part is referred to as being "coupled" to another part, this includes not only a case of being "directly connected" but also a case of being "indirectly connected" with another element interposed therebetween. In addition, when a certain part is referred to as "including" a certain component, unless otherwise stated, other components are not excluded, but it means that other components may be included.
The terms first, second, third, etc. are used herein to describe various elements, components, regions, layers and/or sections, but are not limited thereto. These terms are only used to distinguish one element, component, region, layer or section from another element, component, region, layer or section. Thus, a first element, component, region, layer or section discussed below could be termed a second element, component, region, layer or section without departing from the scope of the present application.
Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," and/or "comprising," when used in this specification, specify the presence of stated features, operations, elements, components, items, species, and/or groups, but do not preclude the presence, or addition of one or more other features, operations, elements, components, items, species, and/or groups thereof. The terms "or" and/or "as used herein are to be construed as inclusive or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a; b; c; a and B; a and C; b and C; A. b and C ". An exception to this definition will occur only when a combination of elements, functions or operations are inherently mutually exclusive in some way.
As shown in fig. 1, a schematic diagram of an implementation environment in the embodiment of the present application is shown.
In this embodiment, the acquisition device 11 is arranged in an inspection site for vehicle annual inspection chassis dynamic, acquires video data of chassis dynamic of the vehicle 12 to be inspected in a chassis dynamic scene in real time to obtain initial position information and end position information of the vehicle 12 to be inspected in the video data, and obtains an inspection result of the vehicle 12 annual inspection chassis dynamic of the vehicle to be inspected according to the initial time information and the end time information of the vehicle 12 to be inspected in the video data.
The capturing device 11 is any device that can capture a video image, and is not limited in this application. For example, the acquisition device 11 is an electronic device with a camera.
The application provides a dynamic inspection method of a vehicle chassis, which is used for solving the problem that the annual inspection workload of vehicles of related departments and mechanisms is increased sharply along with the annual increase of the vehicle holding amount in the prior art, and further causes artificial negligence and loopholes to exist in the inspection process of workers, so that the dynamic inspection efficiency of the annual inspection chassis is low.
As shown in fig. 2, a flow chart of a dynamic inspection method for a vehicle chassis in the embodiment of the present application is shown, which can be applied to the acquisition device 11 and the vehicle 12 in the embodiment of fig. 1, for example.
The method comprises the following steps:
step S201: and acquiring video data of a chassis dynamic detection scene of the vehicle to be detected.
Optionally, the acquisition device acquires video data of a dynamic chassis detection scene of the vehicle to be detected in real time.
Optionally, the acquisition device acquires video data of the vehicle to be detected in the dynamic chassis inspection scene in real time in the dynamic chassis inspection field for annual inspection of the vehicle.
Optionally, the camera collects video data of the vehicle to be detected in a dynamic chassis inspection scene in real time in a dynamic chassis inspection field of the annual vehicle inspection.
Step S202: and acquiring the license plate number information of the vehicle to be detected according to the video data.
Optionally, each frame image included in the video data is respectively input into a vehicle detection model based on deep learning, so as to output an image including the vehicle to be detected; extracting the vehicle to be detected according to the image of the vehicle to be detected; inputting the extracted vehicle to be detected into a license plate detection model based on deep learning so as to output license plate position information of the vehicle to be detected; and identifying the license plate number information according to the license plate position information of the vehicle to be detected.
Optionally, each frame of image in the video data is transmitted to a detection algorithm module, and then vehicle position information of the vehicle to be detected appearing in the video data is checked based on the deep-learning vehicle detection model.
Optionally, the detection algorithm includes: one or more of a Refinedet algorithm, an RCNN algorithm, an SSD algorithm, a Faster-RCNN algorithm, and a YOLO algorithm.
Optionally, each frame of image in the video data is transmitted to a detection algorithm module, then whether the vehicle to be detected appears in the video data is checked based on the deep learning vehicle detection model, and if the vehicle to be detected appears in the video data, vehicle position information of the vehicle to be detected is obtained; if not, the detection of the next frame is continued.
Optionally, a sample image containing the vehicle to be detected is found out according to the multi-frame image in the video data, the vehicle in the sample image is marked by using a rectangular frame, and vehicle marking information is obtained; the vehicle marking information comprises the position information of the target in the marking frame and the marking frame in the image; preferably, the vehicle position information is an x coordinate value and a y coordinate value of a vertex at the upper left corner of the labeling frame and length, width and height data of the labeling frame.
Optionally, the vehicle detection model is obtained by training using a refindet network.
Optionally, the training mode of the vehicle detection model includes: marking vehicle position information according to the video data; and inputting the vehicle position information into the vehicle detection model for training.
Optionally, the training mode of the vehicle detection model includes: marking vehicle position information according to the video data; and inputting the vehicle position information into the vehicle detection model for training, and finishing the model training when the training reaches convergence. A
Optionally, when a plurality of vehicles to be detected appear in the video data, the position information of the vehicles is stored one by one.
Optionally, work as the quantity of waiting to examine the vehicle is when a plurality of, will extract wait to examine that the vehicle inputs a license plate detection model based on degree of depth study, with the output wait to examine the license plate positional information of vehicle, include: and storing each vehicle to be detected, inputting any extracted vehicle to be detected into a license plate detection model based on deep learning so as to output the license plate position information of the vehicle to be detected.
Optionally, when the number of the vehicles to be detected is multiple, storing each vehicle to be detected, and inputting each vehicle to be detected into a license plate detection model based on deep learning respectively, so as to output license plate position information corresponding to each vehicle to be detected respectively; according to wait to examine the license plate position information discernment of vehicle license plate number information specifically does: and identifying the license plate number information according to the license plate position information of the vehicle to be detected.
Optionally, the vehicle to be detected is cut out from the whole image according to the vehicle position information of the vehicle to be detected, the cut-out image of the vehicle to be detected obtains license plate position information according to the license plate detection model so as to obtain license plate region information, the license plate region image is cut out, and the license plate information of the vehicle to be detected is obtained by identifying according to the license plate region image.
Step S203: and comparing the license plate number information with license plate number information of a target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, acquiring tracking track information of the target vehicle according to the video data.
Optionally, the manner of obtaining the tracking track information of the target vehicle according to the video data includes: acquiring coordinate information of the target vehicle in a target frame image of the video data; wherein the output image of the frame corresponding to the image of the vehicle to be detected is a target frame image; and obtaining the tracking track information of the target vehicle according to the coordinate information.
Optionally, the license plate number information of the vehicle to be detected is subjected to character recognition by using a recognition network according to the license plate position information of the vehicle to be detected, the recognized license plate number information is compared with the license plate number information of the target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, the position information of the target vehicle is recorded and timing is started.
Optionally, the text recognition method includes: (1) a method using an LSTM recognition mode, preferably LSTM + CTC; (2) utilizing a CRNN identification mode; (3) using the chinoseocr project identification.
Optionally, the license plate number information of the vehicle to be detected is identified according to the license plate position information of the vehicle to be detected, so as to be compared with the license plate number information of the target vehicle, if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, the position information of the target vehicle is recorded, and the timing mode is started to include:
identifying a license plate region image obtained according to the license plate position information of the vehicle to be detected to obtain license plate information of the vehicle to be detected;
comparing the license plate number information of the vehicle to be detected with the license plate number information of the target vehicle recorded by the system;
and if the license plate number information of the vehicle to be detected is consistent with the license plate number information of the target vehicle, determining that the vehicle to be detected is the target vehicle, and starting timing.
Optionally, the license plate number information of the vehicle to be detected is identified according to the license plate position information of the vehicle to be detected, so as to be compared with the license plate number information of the target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, the timing starting mode comprises the following steps:
according to the vehicle position information of the vehicle to be detected, cutting the vehicle to be detected from the whole image, obtaining license plate position information of the image of the cut vehicle to be detected according to the license plate detection model, further obtaining license plate region information, cutting the license plate region image, and identifying according to the license plate region image to obtain license plate information of the vehicle to be detected;
comparing the license plate number information of the vehicle to be detected with the license plate number information of the target vehicle automatically transmitted by the system;
if the license plate number information of the vehicle to be detected is consistent with the license plate number information of the target vehicle, determining the vehicle to be detected as the target vehicle, recording the current position information of the target vehicle and starting timing; and if the two are inconsistent, the identification is carried out again.
Optionally, the license plate number information of the vehicle to be detected is identified according to the license plate position information of the vehicle to be detected, so as to be compared with the license plate number information of the target vehicle, if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, the position information of the target vehicle is recorded, and the timing mode is started to include:
and according to the vehicle position information of the vehicle to be detected, cutting the vehicle to be detected from the whole image, obtaining the license plate position information of the image of the cut vehicle to be detected according to the license plate detection model, further obtaining the license plate region information, cutting the license plate region image, identifying by using the LSTM according to the license plate region image, and when a plurality of vehicles to be detected exist, respectively identifying the license plates of the vehicles to be detected by using the LSTM, so as to obtain the identification result of the license plates.
Comparing the license plate number information of the vehicle to be detected with the license plate number information of the target vehicle automatically transmitted by the system;
if the license plate number information of the vehicle to be detected is consistent with the license plate number information of the target vehicle, determining the vehicle to be detected as the target vehicle, recording the current position information of the target vehicle and starting timing; and if the two are inconsistent, the identification is carried out again.
S204: and acquiring initial position information, end position information, initial time information and end time information of the target vehicle according to the tracking track information.
Optionally, after the target vehicle is detected, the target vehicle is visually tracked in a subsequent video frame by using a target tracking algorithm, so as to obtain tracking track information of the target vehicle in the video data.
Optionally, the visually tracking the target vehicle by using a target tracking algorithm to obtain the tracking track information of the target vehicle on the video data includes:
acquiring coordinate information of the target vehicle in a current frame image of the video data;
and obtaining the tracking track information of the target vehicle by combining the target tracking algorithm.
Optionally, the visually tracking the target vehicle by using a target tracking algorithm to obtain the tracking track information of the target vehicle on the video data includes:
acquiring coordinate information of the target vehicle in a current frame image of the video data;
and inputting the coordinate information into the target tracking algorithm, and tracking the target vehicle in a subsequent video frame by using the algorithm to obtain the tracking track information of the target vehicle.
Optionally, the target tracking algorithm is an ECO target tracking algorithm.
Optionally, when the target vehicle runs out of the inspection site or the video is finished, stopping tracking the target vehicle, and recording initial position information, end position information, initial time information and end time information of the target vehicle according to the tracking track information.
Optionally, the method of recording the initial position information, the end position information, the initial time information, and the end time information of the target vehicle according to the tracking track information includes:
storing and acquiring initial position information and initial time of the target vehicle according to the tracking track information;
and saving end position information and end time information when the target vehicle does not appear in the video data according to the tracking track information.
Optionally, the obtaining of the end position information and the end time information of the target vehicle according to the tracking track information includes: when the target vehicle runs out of a detection site or the video for the target vehicle is finished, stopping tracking the target vehicle, and recording the position and the current time of the target vehicle when the tracking of the target vehicle is stopped; taking the position of the target vehicle when the tracking of the target vehicle is stopped as the end position information; and taking the current time as the end time information.
Optionally, the method of recording the initial position information, the end position information, the initial time information, and the end time information of the target vehicle according to the tracking track information includes:
storing and acquiring initial position information and initial time of the target vehicle according to the tracking track information;
and in the tracking process, stopping the tracking process of the target vehicle when the target vehicle is found to run out of the detection field or no video frame exists after the video is finished.
And when the tracking algorithm stops tracking the target vehicle, saving end position information and end time information when the target vehicle does not appear in the video data according to the tracking track information.
Optionally, the end time is a time of a current frame at the end time.
Optionally, the method of recording the initial position information, the end position information, the initial time information, and the end time information of the target vehicle according to the tracking track information includes:
storing and acquiring initial position information and initial time of the target vehicle according to the tracking track information;
and when the ECO algorithm finds that the target vehicle runs out of the detection site in the tracking process or no video frame exists after the video is finished, stopping the tracking process of the target vehicle.
And when the ECO tracking algorithm stops tracking the target vehicle, saving end position information and end time information when the target vehicle does not appear in the video data according to the tracking track information.
S205: and judging whether the target vehicle moves or not according to the initial position information and the end position information, and if so, judging whether the dynamic inspection duration of the chassis meets the regulation or not according to the initial time information and the end time information.
Optionally, the determining, according to the initial position information and the end position information, whether the target vehicle moves, and if so, determining, according to the initial time information and the end time information, whether the inspection duration of the chassis dynamics meets the specification includes:
obtaining the coordinates of the center point of the initial position target vehicle and the coordinates of the center point of the end position target vehicle according to the initial position information and the end position information;
obtaining the distance between the initial position and the end position according to the coordinates of the central point of the initial position target vehicle and the coordinates of the central point of the end position target vehicle;
determining that the target vehicle moves according to the distance between the initial position and the end position;
obtaining the total dynamic detection time of the target vehicle chassis according to the initial time and the end time;
when the total duration is longer than the required duration, the dynamic detection result of the vehicle annual inspection chassis is a qualified detection result; otherwise, the result is a detection failure result.
Optionally, the obtaining of the coordinates of the center point of the initial position target vehicle and the coordinates of the center point of the end position target vehicle according to the initial position information and the end position information includes:
initial position information r1(x1, y1, w1, h1) of the target vehicle is saved, while end position information r2(x2, y2, w2, h2) at the last occurrence of the target vehicle is saved when the ECO tracking algorithm ends tracking the target vehicle. X and y are coordinates of a fixed point at the upper left corner of the rectangular frame of the target vehicle respectively, and w and h are the width and the height of the rectangular frame of the target vehicle;
the coordinates p1(x3, y3) and p2(x4, y4) of the center point of the rectangular frame of the target vehicle at the initial position and the end position can be obtained through r1 and r2 respectively.
Optionally, the obtaining of the distance between the initial position and the end position according to the initial position target vehicle center point coordinate and the end position target vehicle center point coordinate includes:
the distance between p1 and p2 is calculated as follows:
Figure BDA0002341680600000091
wherein the coordinates of the center point of the initial position and the end position target vehicle rectangular frame are p1(x3, y3) and p2(x4, y 4).
Optionally, when the total dynamic detection time of the vehicle chassis is greater than 60 seconds, judging that the detection time meets the specification; and if the total dynamic detection time of the vehicle chassis is less than 60 seconds, judging that the detection time does not meet the standard.
In principle similarity with the above embodiments, the present application provides a dynamic checking system for a vehicle annual inspection chassis, the system comprising:
the video data acquisition module is used for acquiring video data of a chassis station of the vehicle to be detected;
the license plate number information module is used for acquiring license plate number information of the vehicle to be detected according to the video data;
the tracking track module is used for comparing the license plate number information with license plate number information of a target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, the tracking track information of the target vehicle is obtained according to the video data;
the position and time determining module is used for acquiring initial position information, end position information, initial time information and end time information of the target vehicle according to the tracking track information;
and the vehicle chassis dynamic detection result module is used for judging whether the target vehicle moves according to the initial position information and the end position information, and if so, judging whether the chassis dynamic detection duration meets the specification according to the initial time information and the end time information.
Specific embodiments are provided below in conjunction with the attached figures:
fig. 3 is a schematic structural diagram showing a vehicle annual inspection chassis dynamic inspection system in an embodiment of the present application.
The system comprises:
the video data acquisition module 31 is used for acquiring video data of a chassis dynamic detection scene of the vehicle to be detected;
the license plate number information module 32 is used for acquiring license plate number information of the vehicle to be detected according to the video data;
the tracking track module 33 is used for comparing the license plate number information with license plate number information of a target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, acquiring tracking track information of the target vehicle according to the video data;
a position and time determining module 34, configured to obtain initial position information, end position information, initial time information, and end time information of the target vehicle according to the tracking track information;
and the vehicle chassis dynamic detection result module 35 is configured to determine whether the target vehicle moves according to the initial position information and the end position information, and if so, determine whether a chassis dynamic inspection duration meets a specification according to the initial time information and the end time information.
Optionally, the video data collecting module 31 collects video data of a chassis dynamic detection scene of the vehicle to be detected;
optionally, the video data acquiring module 31 includes: the acquisition device acquires video data of a dynamic chassis detection scene of the vehicle to be detected in real time.
Optionally, the acquisition device acquires video data of the vehicle to be detected in the dynamic chassis inspection scene in real time in the dynamic chassis inspection field for annual inspection of the vehicle.
Optionally, the camera collects video data of the vehicle to be detected in a dynamic chassis inspection scene in real time in a dynamic chassis inspection field of the annual vehicle inspection.
Optionally, the license plate number information module 32 inputs each frame image included in the video data into a vehicle detection model based on deep learning, so as to output an image including the vehicle to be detected; extracting the vehicle to be detected according to the image of the vehicle to be detected; inputting the extracted vehicle to be detected into a license plate detection model based on deep learning so as to output license plate position information of the vehicle to be detected; and identifying the license plate number information according to the license plate position information of the vehicle to be detected.
Optionally, the license plate number information module 32 transmits each frame of image in the video data to the detection algorithm module, and then checks the vehicle position information of the vehicle to be detected appearing in the video data based on the deep-learning vehicle detection model.
Optionally, the detection algorithm includes: one or more of a refindeet algorithm, an RCNN algorithm, an SSD algorithm, a Faster-RCNN algorithm, and a YOLO algorithm.
Optionally, the license plate number information module 32 transmits each frame of image in the video data to a detection algorithm module, and then checks whether the vehicle to be detected appears in the video data based on the deep learning vehicle detection model, and if so, vehicle position information of the vehicle to be detected is obtained; if not, the detection of the next frame is continued.
Optionally, the license plate number information module 32 finds a sample image containing the vehicle to be detected according to the multi-frame image in the video data, marks the vehicle in the sample image by using a rectangular frame, and obtains vehicle marking information; the vehicle marking information comprises the position information of the target in the marking frame and the marking frame in the image; preferably, the vehicle position information is an x coordinate value and a y coordinate value of a vertex at the upper left corner of the labeling frame and length, width and height data of the labeling frame.
Optionally, the vehicle detection model is obtained by training using a refindet network.
Optionally, the training mode of the vehicle detection model includes: marking vehicle position information according to the video data; and inputting the vehicle position information into the vehicle detection model for training.
Optionally, the training mode of the vehicle detection model includes: marking vehicle position information according to the video data; and inputting the vehicle position information into the vehicle detection model for training, and finishing the model training when the training reaches convergence.
Optionally, when a plurality of vehicles to be detected appear in the video data, the license plate number information module 32 stores the position information of the vehicles one by one.
Optionally, when the quantity of waiting to examine the vehicle is a plurality of, license plate number information module 32 will extract wait to examine a license plate detection model of waiting to examine vehicle input based on degree of depth study, in order to output wait to examine the license plate positional information of examining the vehicle, include: and storing each vehicle to be detected, inputting any extracted vehicle to be detected into a license plate detection model based on deep learning so as to output the license plate position information of the vehicle to be detected.
Optionally, when the number of the vehicles to be detected is multiple, storing each vehicle to be detected, and inputting each vehicle to be detected into a license plate detection model based on deep learning respectively, so as to output license plate position information corresponding to each vehicle to be detected respectively; according to wait to examine the license plate position information discernment of vehicle license plate number information specifically does: and identifying the license plate number information according to the license plate position information of the vehicle to be detected.
Optionally, the license plate number information module 32 cuts the vehicle to be detected from the whole image according to the vehicle position information of the vehicle to be detected, obtains license plate position information according to the license plate detection model from the cut image of the vehicle to be detected, further obtains license plate area information, cuts the license plate area image, and identifies according to the license plate area image to obtain license plate number information of the vehicle to be detected.
Optionally, the manner of acquiring the tracking track information of the target vehicle by the tracking track module 33 according to the video data includes: acquiring coordinate information of the target vehicle in a target frame image of the video data; wherein the output image of the frame corresponding to the image of the vehicle to be detected is a target frame image; and obtaining the tracking track information of the target vehicle according to the coordinate information.
Optionally, the track tracking module 33 performs character recognition on the license plate number information of the vehicle to be detected by using a recognition network according to the license plate position information of the vehicle to be detected, compares the recognized license plate number information with the license plate number information of the target vehicle, and records the position information of the target vehicle and starts timing if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information.
Optionally, the text recognition method includes: (1) a method using an LSTM recognition mode, preferably LSTM + CTC; (2) utilizing a CRNN identification mode; (3) using the chinoseocr project identification.
Optionally, the track tracking module 33 identifies license plate number information of the vehicle to be detected according to license plate position information of the vehicle to be detected, so as to compare the license plate number information with license plate number information of the target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to comparison result information of the license plate number information, the position information of the target vehicle is recorded, and a timing mode is started, including:
identifying a license plate region image obtained according to the license plate position information of the vehicle to be detected to obtain license plate information of the vehicle to be detected;
comparing the license plate number information of the vehicle to be detected with the license plate number information of the target vehicle recorded by the system;
and if the license plate number information of the vehicle to be detected is consistent with the license plate number information of the target vehicle, determining that the vehicle to be detected is the target vehicle, and starting timing.
Optionally, the tracking module 33 identifies license plate number information of the vehicle to be detected according to the license plate position information of the vehicle to be detected, so as to compare the license plate number information with license plate number information of the target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to comparison result information of the license plate number information, the timing mode includes:
according to the vehicle position information of the vehicle to be detected, cutting the vehicle to be detected from the whole image, obtaining license plate position information of the image of the cut vehicle to be detected according to the license plate detection model, further obtaining license plate region information, cutting the license plate region image, and identifying according to the license plate region image to obtain license plate information of the vehicle to be detected;
comparing the license plate number information of the vehicle to be detected with the license plate number information of the target vehicle automatically transmitted by the system;
if the license plate number information of the vehicle to be detected is consistent with the license plate number information of the target vehicle, determining the vehicle to be detected as the target vehicle, recording the current position information of the target vehicle and starting timing; and if the two are inconsistent, the identification is carried out again.
Optionally, the track tracking module 33 identifies license plate number information of the vehicle to be detected according to license plate position information of the vehicle to be detected, so as to compare the license plate number information with license plate number information of the target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to comparison result information of the license plate number information, the position information of the target vehicle is recorded, and a timing mode is started, including:
and according to the vehicle position information of the vehicle to be detected, cutting the vehicle to be detected from the whole image, obtaining the license plate position information of the image of the cut vehicle to be detected according to the license plate detection model, further obtaining the license plate region information, cutting the license plate region image, identifying by using the LSTM according to the license plate region image, and when a plurality of vehicles to be detected exist, respectively identifying the license plates of the vehicles to be detected by using the LSTM, so as to obtain the identification result of the license plates.
Comparing the license plate number information of the vehicle to be detected with the license plate number information of the target vehicle automatically transmitted by the system;
if the license plate number information of the vehicle to be detected is consistent with the license plate number information of the target vehicle, determining the vehicle to be detected as the target vehicle, recording the current position information of the target vehicle and starting timing; and if the two are inconsistent, the identification is carried out again.
Optionally, after the position and time determining module 34 detects the target vehicle, the target vehicle is visually tracked in a subsequent video frame by using a target tracking algorithm, so as to obtain tracking track information of the target vehicle in the video data.
Optionally, the method for visually tracking the target vehicle by the position and time determination module 34 using a target tracking algorithm to obtain tracking track information of the target vehicle on the video data includes:
acquiring coordinate information of the target vehicle in a current frame image of the video data;
and obtaining the tracking track information of the target vehicle by combining the target tracking algorithm.
Optionally, the method for visually tracking the target vehicle by the position and time determination module 34 using a target tracking algorithm to obtain tracking track information of the target vehicle on the video data includes:
acquiring coordinate information of the target vehicle in a current frame image of the video data;
and inputting the coordinate information into the target tracking algorithm, and tracking the target vehicle in a subsequent video frame by using the algorithm to obtain the tracking track information of the target vehicle.
Optionally, the target tracking algorithm is an ECO target tracking algorithm.
Optionally, when the target vehicle runs out of the inspection site or the video is finished, stopping tracking the target vehicle, and recording initial position information, end position information, initial time information and end time information of the target vehicle according to the tracking track information.
Optionally, the manner in which the position and time determining module 34 records the initial position information, the end position information, the initial time information, and the end time information of the target vehicle according to the tracking track information includes:
storing and acquiring initial position information and initial time of the target vehicle according to the tracking track information;
and saving end position information and end time information when the target vehicle does not appear in the video data according to the tracking track information.
Optionally, the manner that the position and time determining module 34 obtains the end position information and the end time information of the target vehicle according to the tracking track information includes: when the target vehicle runs out of a detection site or the video for the target vehicle is finished, stopping tracking the target vehicle, and recording the position and the current time of the target vehicle when the tracking of the target vehicle is stopped; taking the position of the target vehicle when the tracking of the target vehicle is stopped as the end position information; and taking the current time as the end time information.
Optionally, the manner in which the position and time determining module 34 records the initial position information, the end position information, the initial time information, and the end time information of the target vehicle according to the tracking track information includes:
storing and acquiring initial position information and initial time of the target vehicle according to the tracking track information;
and in the tracking process, stopping the tracking process of the target vehicle when the target vehicle is found to run out of the detection field or no video frame exists after the video is finished.
And when the tracking algorithm stops tracking the target vehicle, saving end position information and end time information when the target vehicle does not appear in the video data according to the tracking track information.
Optionally, the end time is a time of a current frame at the end time.
Optionally, the manner in which the position and time determining module 34 records the initial position information, the end position information, the initial time information, and the end time information of the target vehicle according to the tracking track information includes:
storing and acquiring initial position information and initial time of the target vehicle according to the tracking track information;
and when the ECO algorithm finds that the target vehicle runs out of the detection site in the tracking process or no video frame exists after the video is finished, stopping the tracking process of the target vehicle.
And when the ECO tracking algorithm stops tracking the target vehicle, saving end position information and end time information when the target vehicle does not appear in the video data according to the tracking track information.
Optionally, the vehicle chassis dynamic detection result module 35 determines whether the target vehicle moves according to the initial position information and the end position information, and if so, the manner of determining whether the inspection duration of the chassis dynamic state meets the specification according to the initial time information and the end time information includes:
obtaining the coordinates of the center point of the initial position target vehicle and the coordinates of the center point of the end position target vehicle according to the initial position information and the end position information;
obtaining the distance between the initial position and the end position according to the coordinates of the central point of the initial position target vehicle and the coordinates of the central point of the end position target vehicle;
determining that the target vehicle moves according to the distance between the initial position and the end position;
obtaining the total dynamic detection time of the target vehicle chassis according to the initial time and the end time;
when the total duration is longer than the required duration, the dynamic detection result of the vehicle annual inspection chassis is a qualified detection result; otherwise, the result is a detection failure result.
Optionally, the manner that the vehicle chassis dynamic detection result module 35 obtains the coordinates of the center point of the initial position target vehicle and the coordinates of the center point of the end position target vehicle according to the initial position information and the end position information includes:
initial position information r1(x1, y1, w1, h1) of the target vehicle is saved, while end position information r2(x2, y2, w2, h2) at the last occurrence of the target vehicle is saved when the ECO tracking algorithm ends tracking the target vehicle. X and y are coordinates of a fixed point at the upper left corner of the rectangular frame of the target vehicle respectively, and w and h are the width and the height of the rectangular frame of the target vehicle;
the coordinates p1(x3, y3) and p2(x4, y4) of the center point of the rectangular frame of the target vehicle at the initial position and the end position can be obtained through r1 and r2 respectively.
Optionally, the manner that the vehicle chassis dynamic detection result module 35 obtains the distance between the initial position and the end position according to the initial position target vehicle center point coordinate and the end position target vehicle center point coordinate includes:
the distance between p1 and p2 is calculated as follows:
Figure BDA0002341680600000151
wherein the coordinates of the center point of the initial position and the end position target vehicle rectangular frame are p1(x3, y3) and p2(x4, y 4).
Optionally, the vehicle chassis dynamic detection result module 35 specifies that the inspection duration meets the specification when the total duration of the vehicle chassis dynamic detection is greater than 60 seconds; and if the total dynamic detection time of the vehicle chassis is less than 60 seconds, judging that the detection time does not meet the standard.
As shown in fig. 4, a schematic structural diagram of an inspection terminal 40 for vehicle annual inspection chassis dynamics in the embodiment of the present application is shown.
The vehicle annual inspection chassis dynamic inspection terminal 40 comprises: a memory 41 and a processor 42, the memory 41 being for storing computer programs; the processor 42 runs a computer program to implement the dynamic checking method of the vehicle chassis as described in fig. 2.
Alternatively, the number of the memories 41 may be one or more, the number of the processors 42 may be one or more, and fig. 4 illustrates one example.
Optionally, the processor 42 in the vehicle annual inspection chassis dynamic inspection terminal 40 may load one or more instructions corresponding to the progress of the application program into the memory 41 according to the steps described in fig. 2, and the processor 42 executes the application program stored in the first memory 41, thereby implementing various functions in the vehicle annual inspection chassis dynamic inspection method described in fig. 2.
Optionally, the memory 41 may include, but is not limited to, a high speed random access memory, a non-volatile memory. Such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid-state storage devices; the Processor 42 may include, but is not limited to, a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
Optionally, the Processor 42 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
The present application also provides a computer-readable storage medium storing a computer program which, when executed, implements the method for dynamic inspection of a vehicle chassis as shown in fig. 2. The computer-readable storage medium may include, but is not limited to, floppy diskettes, optical disks, CD-ROMs (compact disc-read only memories), magneto-optical disks, ROMs (read-only memories), RAMs (random access memories), EPROMs (erasable programmable read only memories), EEPROMs (electrically erasable programmable read only memories), magnetic or optical cards, flash memory, or other type of media/machine-readable medium suitable for storing machine-executable instructions. The computer readable storage medium may be a product that is not accessed by the computer device or may be a component that is used by an accessed computer device.
In conclusion, the dynamic inspection method, the dynamic inspection system, the dynamic inspection terminal and the modification judgment method for the vehicle chassis solve the problem that the dynamic inspection efficiency of the annual inspection chassis is low due to the fact that the annual inspection workload of vehicles of related departments and mechanisms is increased sharply along with the increase of the vehicle holding capacity year by year in the prior art, and further human negligence and loopholes exist in the manual inspection process. Therefore, the application effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the application. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical concepts disclosed in the present application shall be covered by the claims of the present application.

Claims (10)

1. A method for dynamic verification of a vehicle chassis, comprising:
collecting video data of a chassis station of a vehicle to be detected;
acquiring license plate number information of the vehicle to be detected according to the video data;
comparing the license plate number information with license plate number information of a target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, acquiring tracking track information of the target vehicle according to the video data;
acquiring initial position information, end position information, initial time information and end time information of the target vehicle according to the tracking track information;
and judging whether the target vehicle moves or not according to the initial position information and the end position information, and if so, judging whether the dynamic inspection duration of the chassis meets the regulation or not according to the initial time information and the end time information.
2. The dynamic vehicle chassis inspection method according to claim 1, wherein the obtaining of the license plate number information of the vehicle to be inspected from the video data comprises:
respectively inputting each frame image included in the video data into a vehicle detection model based on deep learning so as to output an image including the vehicle to be detected;
extracting the vehicle to be detected according to the image of the vehicle to be detected;
inputting the extracted vehicle to be detected into a license plate detection model based on deep learning so as to output license plate position information of the vehicle to be detected;
and identifying the license plate number information according to the license plate position information of the vehicle to be detected.
3. The method for dynamically inspecting a vehicle chassis according to claim 2, wherein the step of inputting the extracted vehicle to be inspected into a license plate inspection model based on deep learning to output license plate position information of the vehicle to be inspected comprises:
when the number of the vehicles to be detected is multiple, storing each vehicle to be detected, and inputting each vehicle to be detected into a license plate detection model based on deep learning respectively so as to output license plate position information corresponding to each vehicle to be detected respectively;
according to wait to examine the license plate position information discernment of vehicle license plate number information specifically does: and identifying the license plate number information according to the license plate position information of the vehicle to be detected.
4. The method for dynamically inspecting a vehicle chassis according to claim 1, wherein the obtaining tracking trajectory information of the target vehicle based on the video data comprises:
acquiring coordinate information of the target vehicle in a target frame image of the video data; wherein the output image of the frame corresponding to the image of the vehicle to be detected is a target frame image;
and obtaining the tracking track information of the target vehicle according to the coordinate information.
5. The method for dynamically inspecting a vehicle chassis according to claim 4, wherein obtaining tracking trajectory information of the target vehicle based on the coordinate information comprises:
acquiring a preset target tracking algorithm;
and obtaining the tracking track information of the target vehicle according to the target tracking algorithm and the coordinate information.
6. The method for dynamically inspecting a vehicle chassis according to claim 1, wherein the manner of obtaining the end position information and the end time information of the target vehicle based on the tracking trajectory information includes:
when the target vehicle runs out of a detection site or the video for the target vehicle is finished, stopping tracking the target vehicle, and recording the position and the current time of the target vehicle when the tracking of the target vehicle is stopped;
taking the position of the target vehicle when the tracking of the target vehicle is stopped as the end position information;
and taking the current time as the end time information.
7. The method of claim 1, wherein the step of determining whether the target vehicle is moving according to the initial position information and the end position information, and if so, the step of determining whether the inspection duration of the chassis dynamics meets the specification according to the initial time information and the end time information comprises:
obtaining the coordinates of the center point of the initial position target vehicle and the coordinates of the center point of the end position target vehicle according to the initial position information and the end position information;
obtaining the distance between the initial position and the end position according to the coordinates of the central point of the initial position target vehicle and the coordinates of the central point of the end position target vehicle;
determining that the target vehicle moves according to the distance between the initial position and the end position;
obtaining the total dynamic detection time of the target vehicle chassis according to the initial time and the end time;
when the total duration is longer than the required duration, the dynamic detection result of the vehicle annual inspection chassis is a qualified detection result; otherwise, the result is a detection failure result.
8. A system for vehicle annual inspection chassis dynamics verification, comprising:
the video data acquisition module is used for acquiring video data of a chassis station of the vehicle to be detected;
the license plate number information module is used for acquiring license plate number information of the vehicle to be detected according to the video data;
the tracking track module is used for comparing the license plate number information with license plate number information of a target vehicle, and if the vehicle to be detected is determined to be the target vehicle according to the comparison result information of the license plate number information, the tracking track information of the target vehicle is obtained according to the video data;
the position and time determining module is used for acquiring initial position information, end position information, initial time information and end time information of the target vehicle according to the tracking track information;
and the vehicle chassis dynamic detection result module is used for judging whether the target vehicle moves according to the initial position information and the end position information, and if so, judging whether the chassis dynamic detection duration meets the specification according to the initial time information and the end time information.
9. An inspection terminal for vehicle annual inspection chassis dynamics, comprising:
a memory for storing a computer program;
a processor for running the computer program to perform the method of dynamic inspection of a vehicle chassis according to any one of claims 1 to 7.
10. A computer storage medium, characterized in that a computer program is stored which, when running, implements a method for dynamic verification of a vehicle chassis according to any one of claims 1 to 7.
CN201911378637.3A 2019-12-27 2019-12-27 Dynamic inspection method, system, terminal and medium for vehicle chassis Pending CN111126397A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911378637.3A CN111126397A (en) 2019-12-27 2019-12-27 Dynamic inspection method, system, terminal and medium for vehicle chassis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911378637.3A CN111126397A (en) 2019-12-27 2019-12-27 Dynamic inspection method, system, terminal and medium for vehicle chassis

Publications (1)

Publication Number Publication Date
CN111126397A true CN111126397A (en) 2020-05-08

Family

ID=70504122

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911378637.3A Pending CN111126397A (en) 2019-12-27 2019-12-27 Dynamic inspection method, system, terminal and medium for vehicle chassis

Country Status (1)

Country Link
CN (1) CN111126397A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005016949A (en) * 2003-04-28 2005-01-20 Tsubasa System Co Ltd Method, program, and system for supporting vehicle inspection
WO2016024680A1 (en) * 2014-08-11 2016-02-18 주식회사 엠브레인 Vehicle black box capable of real-time recognition of license plate of moving vehicle
WO2016107301A1 (en) * 2014-12-30 2016-07-07 北京握奇智能科技有限公司 Method and system for inspecting static vehicles
CN108091141A (en) * 2017-10-12 2018-05-29 西安天和防务技术股份有限公司 Vehicle License Plate Recognition System
CN108510734A (en) * 2018-03-30 2018-09-07 深圳市金溢科技股份有限公司 A kind of information of vehicles matching process of roadside unit and a kind of roadside unit
CN109784326A (en) * 2018-11-27 2019-05-21 上海眼控科技股份有限公司 A kind of vehicle chassis detection method based on deep learning
CN109800696A (en) * 2019-01-09 2019-05-24 深圳中兴网信科技有限公司 Monitoring method, system and the computer readable storage medium of target vehicle

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005016949A (en) * 2003-04-28 2005-01-20 Tsubasa System Co Ltd Method, program, and system for supporting vehicle inspection
WO2016024680A1 (en) * 2014-08-11 2016-02-18 주식회사 엠브레인 Vehicle black box capable of real-time recognition of license plate of moving vehicle
WO2016107301A1 (en) * 2014-12-30 2016-07-07 北京握奇智能科技有限公司 Method and system for inspecting static vehicles
CN108091141A (en) * 2017-10-12 2018-05-29 西安天和防务技术股份有限公司 Vehicle License Plate Recognition System
CN108510734A (en) * 2018-03-30 2018-09-07 深圳市金溢科技股份有限公司 A kind of information of vehicles matching process of roadside unit and a kind of roadside unit
CN109784326A (en) * 2018-11-27 2019-05-21 上海眼控科技股份有限公司 A kind of vehicle chassis detection method based on deep learning
CN109800696A (en) * 2019-01-09 2019-05-24 深圳中兴网信科技有限公司 Monitoring method, system and the computer readable storage medium of target vehicle

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
VICTORIA J. HODGE ET AL.: "Wireless Sensor Networks for Condition Monitoring in the Railway Industry: A Survey", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 *
宋焕生;李莹;杨瑾;云旭;张韫;解熠;: "基于高速公路场景的车辆目标跟踪", 计算机系统应用, no. 06 *
汤一平;陈耀宇;: "基于计算机视觉的违章停车智能监控系统", 计算机测量与控制, no. 08 *

Similar Documents

Publication Publication Date Title
CN110751022B (en) Urban pet activity track monitoring method based on image recognition and related equipment
CN110807385A (en) Target detection method and device, electronic equipment and storage medium
WO2019033572A1 (en) Method for detecting whether face is blocked, device and storage medium
US11189019B2 (en) Method for detecting defects, electronic device, and computer readable medium
CN110276295B (en) Vehicle identification number detection and identification method and device
CN109344824B (en) Text line region detection method, device, medium and electronic equipment
CN111539358A (en) Working state determination method and device, computer equipment and storage medium
CN110533699A (en) The dynamic multiframe speed-measuring method of pixel variation based on optical flow method
CN112989901A (en) Deep learning-based liquid level meter reading identification method
CN111126397A (en) Dynamic inspection method, system, terminal and medium for vehicle chassis
CN111126286A (en) Vehicle dynamic detection method and device, computer equipment and storage medium
CN111340837A (en) Image processing method, device, equipment and storage medium
CN111898555A (en) Book checking identification method, device, equipment and system based on images and texts
EP3639203B1 (en) Out-of-bounds detection of a document in a live camera feed
AU2017418995B2 (en) Detecting long documents in a live camera feed
CN111383457A (en) Parking space state detection method and device, equipment and storage medium
US20210012472A1 (en) Adaptive video subsampling for energy efficient object detection
CN110796129A (en) Text line region detection method and device
CN114973287A (en) Information extraction method, system, storage medium and equipment based on construction drawing
CN113869364A (en) Image processing method, image processing apparatus, electronic device, and medium
CN113674350A (en) Parking space state detection method and device, computer equipment and storage medium
CN113392455A (en) House type graph scale detection method and device based on deep learning and electronic equipment
CN112199975A (en) Identity verification method and device based on human face features
CN115424095B (en) Quality analysis method and device based on waste materials
CN114219978B (en) Target multi-part association method and device, terminal and computer readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination