CN117523857A - Non-motor vehicle detection and identification method and device, computer equipment and storage medium - Google Patents

Non-motor vehicle detection and identification method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN117523857A
CN117523857A CN202311498149.2A CN202311498149A CN117523857A CN 117523857 A CN117523857 A CN 117523857A CN 202311498149 A CN202311498149 A CN 202311498149A CN 117523857 A CN117523857 A CN 117523857A
Authority
CN
China
Prior art keywords
vehicle
motor vehicle
target
target vehicle
license plate
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
CN202311498149.2A
Other languages
Chinese (zh)
Inventor
曾壮
黎明
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.)
Shenzhen Jieshun Science and Technology Industry Co Ltd
Original Assignee
Shenzhen Jieshun Science and Technology Industry 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 Shenzhen Jieshun Science and Technology Industry Co Ltd filed Critical Shenzhen Jieshun Science and Technology Industry Co Ltd
Priority to CN202311498149.2A priority Critical patent/CN117523857A/en
Publication of CN117523857A publication Critical patent/CN117523857A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • 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
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a non-motor vehicle detection and identification method, a device, computer equipment and a storage medium, wherein the method is realized by the following steps: acquiring video data of a target detection area, and obtaining a vehicle detection frame of a target vehicle based on the video data; judging whether the vehicle detection frame collides with a wire or not; when the vehicle detects that the frame collides with the wire, judging whether the target vehicle is a non-motor vehicle or not; when the target vehicle is a non-motor vehicle, a non-motor vehicle identification event is generated. In the embodiment of the application, the target detection area is monitored in real time, the video data are collected, the collected video data are detected frame by frame to obtain the vehicle detection frame of the target vehicle, the virtual line is preset and can be used for controlling the vehicle playing time, and when the vehicle detection frame collides with the line, the recognition of the target vehicle can be triggered, so that whether the target vehicle is a non-motor vehicle or not is determined, the vehicle type recognition rate can be effectively improved, and the user experience is improved.

Description

Non-motor vehicle detection and identification method and device, computer equipment and storage medium
Technical Field
The present invention relates to the field of intelligent video monitoring, and in particular, to a method and apparatus for detecting and identifying a non-motor vehicle, a computer device, and a storage medium.
Background
To date, vehicle identification devices have been widely used in places such as parking lot entrances and exits, commercial building entrances and exits, toll gate entrances and exits, and lane parking space monitoring, but have been lacking in identification and management of non-motor vehicles. Because the variety and the appearance difference degree of the non-motor vehicles are large, such as electric vehicles, motorcycles, tricycles and the like, the non-motor vehicles cannot be accurately detected and identified by a simple detection and classification model based on deep learning, and therefore constraint supervision of the non-motor vehicles cannot be performed.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, apparatus, computer device and storage medium for detecting and identifying a non-motor vehicle, so as to solve at least one of the problems in the prior art.
In a first aspect, an embodiment of the present application provides a method for detecting and identifying a non-motor vehicle, including the following steps:
acquiring video data of a target detection area, and obtaining a vehicle detection frame of a target vehicle based on the video data;
judging whether the vehicle detection frame collides with a wire or not;
when the vehicle detects that the frame collides with a line, judging whether the target vehicle is a non-motor vehicle or not;
when the target vehicle is a non-motor vehicle, a non-motor vehicle identification event is generated.
In one embodiment, the determining whether the target vehicle is a non-motor vehicle includes:
acquiring a corresponding video frame image when the vehicle detection frame collides with a wire;
preprocessing the video frame image, and inputting the video frame image into a preset non-motor vehicle classification model for classification processing to obtain a classification result;
based on the classification result, it is determined whether the target vehicle is a non-motor vehicle.
In an embodiment, the determining whether the target vehicle is a non-motor vehicle based on the classification result includes:
and based on the classification result, when the confidence score of the target vehicle being the non-motor vehicle is higher than a preset score threshold value, determining that the target vehicle is the non-motor vehicle.
In one embodiment, the determining whether the vehicle detection frame collides with a wire includes:
tracking the vehicle detection frame to acquire the running track of the target vehicle;
judging whether an intersection is generated between the vehicle detection frame and the virtual line in the current video frame according to the running track;
if an intersection is generated, the vehicle detects a wire collision.
In one embodiment, after the determining whether the intersection between the vehicle detection frame and the virtual line in the current video frame is generated, the method includes:
if the intersection is generated, license plate voting is tried to obtain a first license plate recognition result of the target vehicle.
In an embodiment, after the attempting to vote for the license plate to obtain the first license plate identification result of the target vehicle, the method includes:
counting the number of line collision video frames with intersections between the vehicle detection frames and the virtual lines in the continuous video frames;
when the number of the line collision video frames reaches a preset trigger threshold, triggering and forcing license plate voting so as to obtain a second license plate recognition result.
In one embodiment, after the determining whether the target vehicle is a non-motor vehicle, the method includes:
when the target vehicle is not a non-motor vehicle, judging whether the license plate of the target vehicle is a non-motor vehicle license plate according to the first license plate identification result or the second license plate identification result;
if yes, the target vehicle is a non-motor vehicle.
In a second aspect, a non-motor vehicle detection and identification device is provided, comprising:
the vehicle detection frame determining unit is used for acquiring video data of a target detection area and obtaining a vehicle detection frame of a target vehicle based on the video data;
a wire collision judging unit for judging whether the vehicle detection frame collides with wires or not;
a non-motor vehicle judging unit configured to judge whether the target vehicle is a non-motor vehicle when the vehicle detects a wire collision;
and the non-motor vehicle identification event generating unit is used for generating a non-motor vehicle identification event when the target vehicle is a non-motor vehicle.
In a third aspect, there is provided a computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the computer program, when executed by the processor, causes the processor to perform the non-motor vehicle detection and identification method as described above.
In a fourth aspect, a computer readable storage medium is provided, storing a computer program, wherein the computer program, when executed by a processor, causes the processor to perform the non-motor vehicle detection and identification method as described above.
The method, the device, the computer equipment and the storage medium for detecting and identifying the non-motor vehicle are realized by the following steps: acquiring video data of a target detection area, and obtaining a vehicle detection frame of a target vehicle based on the video data; judging whether the vehicle detection frame collides with a wire or not; when the vehicle detects that the frame collides with a line, judging whether the target vehicle is a non-motor vehicle or not; when the target vehicle is a non-motor vehicle, a non-motor vehicle identification event is generated. In the embodiment of the application, the target detection area is monitored in real time, the video data are collected, the collected video data are detected frame by frame to obtain the vehicle detection frame of the target vehicle, the virtual line is preset and can be used for controlling the vehicle playing time, and when the vehicle detection frame collides with the line, the recognition of the target vehicle can be triggered, so that whether the target vehicle is a non-motor vehicle or not is determined, the vehicle type recognition rate can be improved, and the user experience is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting and identifying a non-motor vehicle according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a non-motor vehicle detection and identification device according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a computer device in accordance with an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the embodiment of the application, the target detection area is monitored in real time, the video data are collected, the collected video data are detected frame by frame to obtain the vehicle detection frame of the target vehicle, the virtual line is preset and can be used for controlling the vehicle playing time, and when the vehicle detection frame collides with the line, the recognition of the target vehicle can be triggered, so that whether the target vehicle is a non-motor vehicle or not is determined, the vehicle type recognition rate can be improved, and the user experience is improved.
In one embodiment, as shown in fig. 1, a method for detecting and identifying a non-motor vehicle is provided, which includes the following steps:
in step S110, video data of a target detection area is collected, and a vehicle detection frame of a target vehicle is obtained based on the video data;
in this embodiment of the present application, the target detection area may be a position of an entrance, an aisle, a parking space, or the like of the parking lot, and specifically, monitoring equipment may be preset, for monitoring the position of the entrance, the aisle, the parking space, or the like in real time, and collecting monitoring video data.
In the embodiment of the application, after the monitoring video data is collected, the vehicle detection can be performed on each frame of video frame through the preset vehicle detection model so as to obtain the vehicle detection frame of the target vehicle, and the vehicle detection frame can perform frame selection on the detected target vehicle.
The preset vehicle detection model may be a pre-trained yolov4 model, which is used for detecting and tracking a vehicle.
The vehicle detection frame may be a vertical detection frame, that is, it may perform frame selection on a vertical direction of a target vehicle, and it may be understood that the vehicle detection frame may be disposed at a position of a head of the target vehicle, so that a subsequent wire collision determination may be performed.
In the embodiment of the application, the target vehicle may include one or more vehicles, which may be understood that multiple vehicles may exist in a video frame image at the same time.
In step S120, it is determined whether the vehicle detection frame collides with a wire;
in this embodiment of the present application, determining whether the vehicle detection frame collides with a line may be understood as determining whether there is a coincidence between the vehicle detection frame and a virtual line, where the virtual line is an auxiliary line constructed based on a video image captured by a monitoring device, and is used to control a card-out time of a vehicle, and when a target vehicle travels to the virtual line, by determining coordinate information of the vehicle detection frame and coordinate information of the virtual line, a distance between the two is calculated, so as to determine whether the line collides. Because if the identification is too early, the identification rate is low because the license plate is smaller, the identification is too late, the time of opening the gate can be delayed, and the vehicle departure or arrival time is influenced, so that the vehicle owner experience is poor, and the license plate identification time can be better controlled by setting the virtual line to control the vehicle departure time, so that the vehicle can be released in time.
In step S130, when the vehicle detects a wire collision, it is determined whether the target vehicle is a non-motor vehicle;
in the embodiment of the application, when the vehicle detects wire collision, the target vehicle can be classified through a preset non-motor vehicle classification model, so that whether the target vehicle is a non-motor vehicle or not is determined according to a classification result.
Wherein the non-motor vehicle may include an electric vehicle, a motorcycle, a tricycle, and the like.
The non-motor vehicle classification model may be a pre-trained vgg, a resnet model, etc., and may output probabilities that the target vehicle belongs to different vehicle classes.
In step S140, when the target vehicle is a non-motor vehicle, a non-motor vehicle identification event is generated.
In an embodiment of the present application, when the target vehicle is a non-motor vehicle, a non-motor vehicle identification event may be generated, and when the target vehicle is a motor vehicle, a motor vehicle identification event may be generated. Based on the non-motor vehicle identification event and the motor vehicle identification event, a subsequent operation may be performed, for example, an opening may be performed to drive a target vehicle into or out of a parking lot, or a parking space lock may be opened to drive the vehicle into a parking space, or the like.
The embodiment of the application provides a non-motor vehicle detection and identification method, which comprises the following steps: acquiring video data of a target detection area, and obtaining a vehicle detection frame of a target vehicle based on the video data; judging whether the vehicle detection frame collides with a wire or not; when the vehicle detects that the frame collides with a line, judging whether the target vehicle is a non-motor vehicle or not; when the target vehicle is a non-motor vehicle, a non-motor vehicle identification event is generated. The method comprises the steps of monitoring a target detection area in real time, collecting video data, detecting the collected video data frame by frame to obtain a vehicle detection frame of a target vehicle, and presetting a virtual line which can be used for controlling the vehicle playing time when the vehicle detection frame collides with the line, so that the target vehicle can be triggered to be identified, whether the target vehicle is a non-motor vehicle or not is determined, the vehicle type identification rate can be improved, and the user experience is improved.
In an embodiment of the present application, the determining whether the vehicle detection frame collides with a wire includes:
tracking the vehicle detection frame to acquire the running track of the target vehicle;
judging whether an intersection is generated between the vehicle detection frame and the virtual line in the current video frame according to the running track;
if an intersection is generated, the vehicle detects a wire collision.
Specifically, the vehicle detection frame of the target vehicle in each frame of video frame image can be tracked and detected through the vehicle detection model, the running track of the target vehicle can be determined through connecting the center point position of the vehicle detection frame in each frame of video frame, and whether the intersection exists between the vehicle detection frame of the target vehicle and the virtual line can be determined according to the running track due to the position determination of the virtual line, and if the intersection exists, the collision of the vehicle detection frame can be described.
In an embodiment of the present application, after the determining whether the intersection between the vehicle detection frame and the virtual line in the current video frame is generated, the determining includes:
if the intersection is generated, license plate voting is tried to obtain a first license plate recognition result of the target vehicle.
The license plate voting is used for voting an optimal license plate, such as the license plate with the largest number or the highest confidence, identified by the license plate identification model, and caching, such as the license plate identified by the license plate identification model comprises Yue 1234, yue 2345 and Yue 1234, and then voting out Yue 1234, namely the Yue 1234 can be used as a first license plate identification result.
In the embodiment of the present application, the license plate recognition model may be an end-to-end classification model of the obtained ctc trained in advance, which is used for recognizing the license plate number in the video frame.
In the embodiment of the application, after the wire collision of the vehicle detection frame is detected, the license plate recognition model can be triggered to recognize the license plate of each frame of video frame image, and license plate voting is tried to be performed, so that a first license plate recognition result is obtained.
In an embodiment of the present application, after the attempting to vote on the license plate to obtain the first license plate identification result of the target vehicle, the method includes:
counting the number of line collision video frames with intersections between the vehicle detection frames and the virtual lines in the continuous video frames;
when the number of the line collision video frames reaches a preset trigger threshold, triggering and forcing license plate voting so as to obtain a second license plate recognition result.
In this embodiment of the present application, when it is detected that an intersection exists between a vehicle detection frame and a virtual line in a current video frame, the number of video frames of a collision line may be increased by 1, and by counting the number of video frames of a collision line in which the vehicle detection frame and the virtual line intersect in a continuous video frame, if the number of video frames of a collision line is greater than a preset trigger threshold, for example, 10 frames, forced license plate voting may be performed, and an optimal license plate may be selected by voting to be used as the second license plate recognition result.
Because the license plate recognition model can carry out license plate recognition on each video frame of the continuous video frames, the license plate recognition result is more accurate by voting on the recognized license plates in the line collision video frames of the continuous frames.
In an embodiment of the present application, the determining whether the target vehicle is a non-motor vehicle includes:
acquiring a corresponding video frame image when the vehicle detection frame collides with a wire;
preprocessing the video frame image, and inputting the video frame image into a preset non-motor vehicle classification model for classification processing to obtain a classification result;
based on the classification result, it is determined whether the target vehicle is a non-motor vehicle.
Specifically, since the wire collision process of the vehicle detection frame is a continuous process, a video frame image corresponding to a single frame of the vehicle detection frame when the wire collision is detected can be arbitrarily acquired and input into the preset non-motor vehicle classification model for classification processing, the video frame image can be subjected to feature extraction, the probability that the target vehicle belongs to different types of vehicles is calculated based on the extracted features, and the type with the highest probability can be selected as a classification result.
In an embodiment of the present application, the determining, based on the classification result, whether the target vehicle is a non-motor vehicle includes:
and based on the classification result, when the confidence score of the target vehicle being the non-motor vehicle is higher than a preset score threshold value, determining that the target vehicle is the non-motor vehicle.
Specifically, after the classification result of the target vehicle is obtained, the confidence that the target vehicle inputs the motorcycle may be 90, for example, the confidence that the target vehicle inputs the motorcycle belongs to the tricycle may be 10, and at this time, it may be determined whether the confidence score of the target vehicle input the motorcycle is greater than a preset score threshold, for example, 85, 90 is greater than 85, and the target vehicle may be considered to belong to the motorcycle, that is, it is determined that the target vehicle is a non-motor vehicle.
In an embodiment of the present application, after the determining whether the target vehicle is a non-motor vehicle, the method includes:
when the target vehicle is not a non-motor vehicle, judging whether the license plate of the target vehicle is a non-motor vehicle license plate according to the first license plate identification result or the second license plate identification result;
if yes, the target vehicle is a non-motor vehicle.
Specifically, when the non-motor vehicle classification model identifies that the target vehicle is not a non-motor vehicle, that is, the confidence score is smaller than the preset score threshold, the license plate recognition result in each frame of video frame image identified by the vehicle identification model can be further used for determining whether the license plate of the target vehicle is a non-motor vehicle license plate, if the license plate is a non-motor vehicle license plate, the target vehicle can be indicated to be a non-motor vehicle, otherwise, the target vehicle is indicated to be a motor vehicle. And whether the vehicle is a non-motor vehicle or not is judged through the combination of the vehicle detection model, the license plate recognition model and the non-motor vehicle classification model, so that the accuracy of non-motor vehicle detection can be effectively improved.
In an embodiment of the present application, the vehicle detection model may identify the type of the target vehicle, that is, the vehicle detection model may primarily determine whether the target vehicle is a non-motor vehicle, and then correct the detection result of the vehicle detection model according to the identification result of the license plate recognition model and the classification result of the non-motor vehicle classification model, so as to achieve faster, more accurate and more intelligent non-motor vehicle recognition.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In one embodiment, a non-motor vehicle detecting and identifying device is provided, and the non-motor vehicle detecting and identifying device corresponds to the non-motor vehicle detecting and identifying method in the embodiment. As shown in fig. 2, the non-motor vehicle detection and recognition apparatus includes a vehicle detection frame determination unit 10, a wire collision determination unit 20, a non-motor vehicle determination unit 30, and a non-motor vehicle recognition event generation unit 40. The functional modules are described in detail as follows:
a vehicle detection frame determining unit 10, configured to acquire video data of a target detection area, and obtain a vehicle detection frame of a target vehicle based on the video data;
a wire collision judging unit 20 for judging whether the vehicle detection frame collides with a wire;
a non-motor vehicle judging unit 30 for judging whether the target vehicle is a non-motor vehicle when the vehicle detects a wire collision;
a non-motor vehicle identification event generating unit 40 for generating a non-motor vehicle identification event when the target vehicle is a non-motor vehicle.
In an embodiment, the non-motor vehicle determination unit 30 is further configured to:
acquiring a corresponding video frame image when the vehicle detection frame collides with a wire;
preprocessing the video frame image, and inputting the video frame image into a preset non-motor vehicle classification model for classification processing to obtain a classification result;
based on the classification result, it is determined whether the target vehicle is a non-motor vehicle.
In an embodiment, the non-motor vehicle determination unit 30 is further configured to:
and based on the classification result, when the confidence score of the target vehicle being the non-motor vehicle is higher than a preset score threshold value, determining that the target vehicle is the non-motor vehicle.
In an embodiment, the wire collision judging unit 20 is further configured to:
tracking the vehicle detection frame to acquire the running track of the target vehicle;
judging whether an intersection is generated between the vehicle detection frame and the virtual line in the current video frame according to the running track;
if an intersection is generated, the vehicle detects a wire collision.
In an embodiment, the device further comprises a license plate recognition unit for:
if the intersection is generated, license plate voting is tried to obtain a first license plate recognition result of the target vehicle.
In an embodiment, the device further comprises a license plate recognition unit for:
counting the number of line collision video frames with intersections between the vehicle detection frames and the virtual lines in the continuous video frames;
when the number of the line collision video frames reaches a preset trigger threshold, triggering and forcing license plate voting so as to obtain a second license plate recognition result.
In an embodiment, the non-motor vehicle determination unit 30 is further configured to: when the target vehicle is not a non-motor vehicle, judging whether the license plate of the target vehicle is a non-motor vehicle license plate according to the first license plate identification result or the second license plate identification result;
if yes, the target vehicle is a non-motor vehicle.
In the embodiment of the application, the target detection area is monitored in real time, the video data are collected, the collected video data are detected frame by frame to obtain the vehicle detection frame of the target vehicle, the virtual line is preset and can be used for controlling the vehicle playing time, and when the vehicle detection frame collides with the line, the recognition of the target vehicle can be triggered, so that whether the target vehicle is a non-motor vehicle or not is determined, the vehicle type recognition rate can be improved, and the user experience is improved.
For specific limitations on the non-motor vehicle detection and identification device, reference may be made to the above limitations on the non-motor vehicle detection and identification method, and no further description is given here. The above-described respective modules in the non-motor vehicle detection and recognition apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal device, and the internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer readable instructions. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions when executed by the processor implement a non-motor vehicle detection and identification method. The readable storage medium provided by the present embodiment includes a nonvolatile readable storage medium and a volatile readable storage medium.
In an embodiment of the present application, a computer device is provided, including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor implementing the steps of the non-motor vehicle detection and identification method as described above when executing the computer readable instructions.
In an embodiment of the application, a readable storage medium is provided, storing computer readable instructions that when executed by a processor implement the steps of the non-motor vehicle detection and identification method as described above.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by instructing the associated hardware by computer readable instructions stored on a non-volatile readable storage medium or a volatile readable storage medium, which when executed may comprise the above described embodiment methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims (10)

1. A method for detecting and identifying a non-motor vehicle, the method comprising:
collecting video data of a target detection area, based on which ， Obtaining a vehicle detection frame of a target vehicle;
judging whether the vehicle detection frame collides with a wire or not;
when the vehicle detects that the frame collides with a line, judging whether the target vehicle is a non-motor vehicle or not;
when the target vehicle is a non-motor vehicle, a non-motor vehicle identification event is generated.
2. The non-motor vehicle detection and identification method as claimed in claim 1, wherein said determining whether the target vehicle is a non-motor vehicle comprises:
acquiring a corresponding video frame image when the vehicle detection frame collides with a wire;
preprocessing the video frame image, and inputting the video frame image into a preset non-motor vehicle classification model for classification processing to obtain a classification result;
based on the classification result, it is determined whether the target vehicle is a non-motor vehicle.
3. The non-motor vehicle detection and identification method according to claim 2, wherein the determining whether the target vehicle is a non-motor vehicle based on the classification result includes:
and based on the classification result, when the confidence score of the target vehicle being the non-motor vehicle is higher than a preset score threshold value, determining that the target vehicle is the non-motor vehicle.
4. The non-motor vehicle detection and recognition method according to any one of claims 1 or 2, wherein the determining whether the vehicle detection frame collides with a wire includes:
tracking the vehicle detection frame to acquire the running track of the target vehicle;
judging whether an intersection is generated between the vehicle detection frame and the virtual line in the current video frame according to the running track;
if an intersection is generated, the vehicle detects a wire collision.
5. The method for detecting and identifying a non-motor vehicle as defined in claim 4, wherein said determining whether an intersection between said vehicle detection frame and a virtual line in a current video frame is generated comprises:
if the intersection is generated, license plate voting is tried to obtain a first license plate recognition result of the target vehicle.
6. The method of claim 5, wherein said attempting to vote for a first license plate recognition result of said target vehicle comprises:
counting the number of line collision video frames with intersections between the vehicle detection frames and the virtual lines in the continuous video frames;
when the number of the line collision video frames reaches a preset trigger threshold, triggering and forcing license plate voting so as to obtain a second license plate recognition result.
7. The non-motor vehicle detection and identification method as set forth in claim 6, wherein after said determining whether said target vehicle is a non-motor vehicle, comprising:
when the target vehicle is not a non-motor vehicle, judging whether the license plate of the target vehicle is a non-motor vehicle license plate according to the first license plate identification result or the second license plate identification result;
if yes, the target vehicle is a non-motor vehicle.
8. A non-motor vehicle detection and identification device, said device comprising:
the vehicle detection frame determining unit is used for acquiring video data of a target detection area and obtaining a vehicle detection frame of a target vehicle based on the video data;
a wire collision judging unit for judging whether the vehicle detection frame collides with wires or not;
a non-motor vehicle judging unit configured to judge whether the target vehicle is a non-motor vehicle when the vehicle detects a wire collision;
and the non-motor vehicle identification event generating unit is used for generating a non-motor vehicle identification event when the target vehicle is a non-motor vehicle.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein execution of the computer program by the processor causes the processor to perform the non-motor vehicle detection and identification method of any one of claims 1-7.
10. A computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, causes the processor to perform the non-motor vehicle detection and identification method according to any one of claims 1-7.
CN202311498149.2A 2023-11-10 2023-11-10 Non-motor vehicle detection and identification method and device, computer equipment and storage medium Pending CN117523857A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311498149.2A CN117523857A (en) 2023-11-10 2023-11-10 Non-motor vehicle detection and identification method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311498149.2A CN117523857A (en) 2023-11-10 2023-11-10 Non-motor vehicle detection and identification method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117523857A true CN117523857A (en) 2024-02-06

Family

ID=89754480

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311498149.2A Pending CN117523857A (en) 2023-11-10 2023-11-10 Non-motor vehicle detection and identification method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117523857A (en)

Similar Documents

Publication Publication Date Title
CN110533925B (en) Vehicle illegal video processing method and device, computer equipment and storage medium
CN110533923B (en) Parking management method and device, computer equipment and storage medium
CN110706261A (en) Vehicle violation detection method and device, computer equipment and storage medium
CN112434627B (en) Method and device for detecting pedestrian crossing road guardrail and storage medium
CN111539317A (en) Vehicle illegal driving detection method and device, computer equipment and storage medium
CN110895662A (en) Vehicle overload alarm method and device, electronic equipment and storage medium
CN113160509B (en) Risk sensing method and system suitable for communities and construction sites
CN112530159B (en) Self-calibration type multi-lane-level traffic flow detection method and electronic equipment
CN112434566A (en) Passenger flow statistical method and device, electronic equipment and storage medium
CN113516099A (en) Traffic behavior recognition method and device, electronic equipment and storage medium
CN117831177B (en) Multi-license-plate barrier gate control method, device and equipment for parking lot and storage medium
CN111178224B (en) Object rule judging method, device, computer equipment and storage medium
CN112733598A (en) Vehicle law violation determination method and device, computer equipment and storage medium
CN113674317B (en) Vehicle tracking method and device for high-level video
CN108921962B (en) Parking lot entrance and exit management method and parking lot management server
CN112396708B (en) Parking management method, parking management device, computer equipment and storage medium
CN117523857A (en) Non-motor vehicle detection and identification method and device, computer equipment and storage medium
CN111985413A (en) Intelligent building monitoring terminal, monitoring system and monitoring method
CN112153329A (en) Configuration method, system, computer equipment and storage medium for event monitoring
CN116416796A (en) Unmanned vehicle traffic accident responsibility identification method, device, medium and equipment
CN115713726A (en) Method, device, equipment and medium for detecting pedestrian crossing traffic guardrail
CN114150963B (en) Front-rear linkage automatic door control method and device, vehicle and storage medium
CN114882441A (en) Pedestrian re-identification method and system based on deep learning
CN110659384B (en) Video structured analysis method and device
CN112767449A (en) Vehicle driving-out parking space detection method and device, electronic equipment and storage medium

Legal Events

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