CN112489436B - Vehicle identity recognition method, device and system and electronic device - Google Patents

Vehicle identity recognition method, device and system and electronic device Download PDF

Info

Publication number
CN112489436B
CN112489436B CN202011181176.3A CN202011181176A CN112489436B CN 112489436 B CN112489436 B CN 112489436B CN 202011181176 A CN202011181176 A CN 202011181176A CN 112489436 B CN112489436 B CN 112489436B
Authority
CN
China
Prior art keywords
vehicle
time
information
license plate
identity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011181176.3A
Other languages
Chinese (zh)
Other versions
CN112489436A (en
Inventor
郑永宏
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.)
Zhejiang Yuce Technology Co ltd
Original Assignee
Zhejiang Yuce 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 Zhejiang Yuce Technology Co ltd filed Critical Zhejiang Yuce Technology Co ltd
Priority to CN202011181176.3A priority Critical patent/CN112489436B/en
Publication of CN112489436A publication Critical patent/CN112489436A/en
Application granted granted Critical
Publication of CN112489436B publication Critical patent/CN112489436B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • 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

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to a vehicle identity recognition method, a device, a system, an electronic device and a storage medium, wherein the method comprises the steps of acquiring first-time license plate information and first-time vehicle pattern information of a vehicle when the vehicle enters a vehicle entrance, generating an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information, and recording the identity ID of the vehicle into a vehicle database; when the vehicle exits from the vehicle exit, acquiring second time license plate information of the vehicle, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information; when the license plate information at the second time fails to be matched with the identity ID of the vehicle in the vehicle database, acquiring the license plate information at the second time of the vehicle; and determining the identity ID of the vehicle according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information. The method and the device solve the problem that the identification rate of the vehicle identity information at the entrance and exit is low.

Description

Vehicle identity recognition method, device and system and electronic device
Technical Field
The present disclosure relates to the field of camera monitoring, and in particular, to a method, an apparatus, a system, an electronic apparatus, and a storage medium for vehicle identification.
Background
Along with the urban area continues to expand, population is constantly growing, and in order to satisfy the demand of going on a journey, the car reserves are also constantly growing, and more living, official working and consumption entertainment place have all built the parking place and have satisfied masses' parking demand, and traffic jam in the region has been avoided in the normal parking management.
With the popularization and construction of intelligent transportation, license plate recognition technology and self-service parking payment technology are widely applied to intelligent parking lot systems of various cities. The system automatically controls the barrier gate platform rod to release the vehicle by utilizing the license plate recognition technology, effectively omits the action of taking a card for payment, shortens the time required for getting in and out of a parking place, and relieves the problem of congestion at an entrance and an exit. Under the conditions that a plurality of vehicles are not provided with a suspended license plate, the license plate is not suspended normally, the license plate is seriously polluted and the like, the clear license plate is difficult to identify under the conditions, so that the identity information of the vehicles is difficult to confirm, the identification rate of the vehicles is low, the traffic jam of nearby roads is caused, and the result of the high-efficiency running of urban road traffic is seriously influenced.
At present, no effective solution is provided for the problem of low vehicle identity information identification rate at the entrance and exit in the related art.
Disclosure of Invention
The embodiment of the application provides a vehicle identity identification method, a vehicle identity identification device, a vehicle identity identification system, an electronic device and a storage medium, and aims to at least solve the problem that the identification rate of vehicle identity information at an entrance is low in the related art.
In a first aspect, an embodiment of the present application provides a vehicle identification method, including: when a vehicle enters a vehicle entrance, acquiring first-time license plate information and first-time vehicle pattern information of the vehicle, generating an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information, and recording the identity ID of the vehicle into a vehicle database; when the vehicle exits from a vehicle exit, acquiring second time license plate information of the vehicle, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information; when the identity ID of the vehicle is matched in the vehicle database according to the license plate information at the second time and fails, acquiring the license plate information at the second time of the vehicle; and determining the identity ID of the vehicle according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information.
In some embodiments, the obtaining first-time license plate information and first-time fingerprint information of a vehicle when the vehicle enters a vehicle entrance, generating an identity ID of the vehicle according to the first-time license plate information and the first-time fingerprint information, and recording the identity ID of the vehicle in a vehicle database includes: acquiring video information of the vehicle entrance, and detecting, tracking and matching the vehicle according to the video information of the vehicle entrance to obtain a tracking track of the vehicle; judging the access state of the vehicle according to the tracking track of the vehicle; when the in-out state of the vehicle is judged to be that the vehicle enters the vehicle entrance, screening out a video frame containing the vehicle attribute information from the tracking track; the vehicle attribute information comprises license plate information and vehicle pattern information; and identifying a first-time license plate and first-time vehicle pattern information of the vehicle based on the video frame, generating an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information, and recording the identity ID into the vehicle database.
In some embodiments, the obtaining license plate information of the vehicle at a second time when the vehicle exits the vehicle exit, and matching the identity ID of the vehicle in the vehicle database according to the license plate information at the second time includes: acquiring video information of the vehicle exit, and detecting, tracking and matching the vehicle according to the video information of the vehicle exit to obtain a tracking track of the vehicle; judging the access state of the vehicle according to the tracking track of the vehicle; when the vehicle is judged to be in and out of the vehicle exit, screening out the video frame of the vehicle attribute information from the tracking track; the vehicle attribute information comprises license plate information and vehicle pattern information; and identifying second time license plate information of the vehicle based on the video frame, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information.
In some embodiments, the screening out the video frame containing the vehicle attribute information from the tracking track includes: and selecting a video frame which contains the vehicle attribute information and has a larger vehicle position frame, higher vehicle attitude consistency and higher image definition from the tracking track.
In some of these embodiments, the first time vehicle pattern information and the second time vehicle pattern information include vehicle type vehicle style, vehicle body color, license plate type, sunroof, age chart, pendant, ornament, and paint information.
In some embodiments, the determining the identity ID of the vehicle according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information includes: determining the similarity between the second time vehicle pattern information and the first time vehicle pattern information according to the cosine similarity between the N-dimensional floating point vectors of the second time vehicle pattern information and the first time vehicle pattern information; and when the similarity between the second time vehicle pattern information and the first time vehicle pattern information meets a set threshold, the identity ID of the vehicle corresponding to the second time vehicle pattern information is the same as the identity ID of the vehicle corresponding to the first time vehicle pattern information stored in the vehicle database.
In a second aspect, an embodiment of the present application provides a vehicle identification device, including: the device comprises an acquisition module, a first identification module and a second identification module: the acquisition module is used for acquiring first-time license plate information and first-time vehicle pattern information of a vehicle when the vehicle enters a vehicle entrance, generating an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information, and recording the identity ID of the vehicle into a vehicle database; the first identification module is used for acquiring license plate information of the vehicle at a second time when the vehicle exits from a vehicle outlet, and matching the identity ID of the vehicle in the vehicle database according to the license plate information at the second time; the second identification module is used for acquiring the second time license print information of the vehicle when the identity ID of the vehicle is failed to be matched in the vehicle database according to the second time license plate information; and determining the identity ID of the vehicle according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information.
In a third aspect, an embodiment of the present application provides a vehicle identification system, including: an image pickup apparatus, a transmission apparatus, and a server apparatus; the camera equipment is connected with the server equipment through the transmission equipment; the camera equipment is used for acquiring first-time license plate information and first-time vehicle pattern information of the vehicle when the vehicle enters a vehicle entrance; the transmission equipment is used for transmitting the first-time license plate information and the first-time vehicle pattern information of the vehicle to the server equipment; the server equipment is used for generating the identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information and recording the identity ID of the vehicle into a vehicle database; the camera equipment is further used for acquiring license plate information of the vehicle at a second time when the vehicle exits from a vehicle exit; the transmission equipment is further used for transmitting the license plate information of the vehicle at the second time to the server equipment; the server device is further configured to match the identity ID of the vehicle in the vehicle database according to the license plate information at the second time; the camera device is further configured to acquire second time license print information of the vehicle when matching of the identity ID of the vehicle in the vehicle database according to the second time license plate information fails; the transmission device is further used for transmitting the second time vehicle pattern information of the vehicle to the server device; the server device is further configured to determine the identity ID of the vehicle according to the similarity between the second time fingerprint information and the first time fingerprint information.
In a fourth aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement a vehicle identification method according to the first aspect.
In a fifth aspect, the present application provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement a vehicle identification method as described in the first aspect.
Compared with the related art, the vehicle identity recognition method, the device, the system, the electronic device and the storage medium provided by the embodiment of the application acquire the first-time license plate information and the first-time fingerprint information of the vehicle when the vehicle enters the vehicle entrance, generate the identity ID of the vehicle according to the first-time license plate information and the first-time fingerprint information, and record the identity ID of the vehicle into the vehicle database; when the vehicle exits from the vehicle exit, acquiring second time license plate information of the vehicle, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information; when the license plate information at the second time fails to be matched with the identity ID of the vehicle in the vehicle database, acquiring the license plate information at the second time of the vehicle; and determining the identity ID of the vehicle according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information, thereby solving the problem of low vehicle identity information identification rate at the entrance and the exit and avoiding traffic jam caused by the fact that the vehicle identity cannot be identified at the entrance and the exit.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic diagram of an application scenario of a vehicle identification system according to an embodiment of the present application;
FIG. 2 is a flow chart of a method of vehicle identification according to an embodiment of the present application;
FIG. 3 is a flowchart of a method for identifying a vehicle identity according to an embodiment of the present application, in which license plate information is recorded in a vehicle database;
FIG. 4 is a flowchart illustrating matching of vehicle ID according to license plate information in a vehicle identification method according to an embodiment of the present application;
fig. 5 is a block diagram of a vehicle identification apparatus according to an embodiment of the present application;
fig. 6 is a block diagram of a computer-readable storage medium according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference herein to "a plurality" means greater than or equal to two. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
In this embodiment, an application scenario of a vehicle identification system is provided, and fig. 1 is a schematic view of an application scenario of a vehicle identification system according to an embodiment of the present application, as shown in fig. 1, the system includes: an image pickup apparatus 10, a transmission apparatus (not shown), and a server apparatus 12; wherein the content of the first and second substances,
the camera device 10 is used for acquiring first time license plate information and first time vehicle pattern information of a vehicle when the vehicle enters a vehicle entrance;
the first-time license plate information and the first-time vehicle pattern information are license plate information and vehicle pattern information with an entry time mark, which are acquired by the camera device 10 when a vehicle enters the vehicle entrance.
Further, the vehicle entrance is not limited to any gateway that needs to manage the entrance and exit of vehicles, such as a parking lot entrance, a gas station entrance, a mall parking lot entrance, a park vehicle entrance, and a community vehicle entrance.
The transmission device is configured to transmit first time license plate information and first time vehicle pattern information of the vehicle to the server device 12;
wherein the transmission device is not limited to a wired device and a wireless device.
The server device 12 is configured to generate an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle print information, and record the identity ID of the vehicle in a vehicle database;
the server device 12 is configured to record the information, which is equivalent to acquiring feature information of a vehicle entering a vehicle entrance, to generate an identity ID for verifying an identity of the vehicle from the feature information of the vehicle, record the identity ID of the vehicle in a vehicle database, and identify the identity ID of the vehicle when the vehicle leaves.
Further, the vehicle database may also record information not limited to the time when the vehicle enters, the location of the vehicle, and the video segment.
The camera device 10 is further configured to acquire second time license plate information of the vehicle when the vehicle exits from the vehicle exit.
Wherein, the second time license plate information is the license plate information with the exit time stamp acquired by the camera device 10 when the vehicle exits from the vehicle exit.
Correspondingly, the vehicle exit is not limited to any exit required to manage vehicle entrance and exit, such as a parking lot exit, a gas station exit, a mall parking lot exit, a park vehicle exit, and a community vehicle exit.
It should be noted here that the image pickup apparatus 10 is not limited to one apparatus. For a place where a vehicle entrance and a vehicle exit are set in the same area, for example, a cell having only one vehicle entrance, one image pickup apparatus 10 is used to acquire first-time license plate information, first-time license pattern information, and second-time license plate information. For a place where a vehicle entrance and a vehicle exit are not located in the same area, such as a large parking lot with a plurality of vehicle entrances and exits, the camera device 10 may need to be located in a plurality, and the plurality of camera devices 10 are monitored in a network.
The transmission equipment is also used for transmitting the license plate information of the vehicle at the second time to the server equipment;
the server device 12 is further configured to match the identity ID of the vehicle in the vehicle database according to the license plate information at the second time;
the license plate information of the vehicle is acquired when the vehicle exits from the vehicle exit, and the license plate information is acquired once when the vehicle enters from the vehicle entrance, so that the license plate information acquired when the vehicle exits from the vehicle exit is marked as the license plate information at the second time, the license plate detection is carried out according to the license plate information at the second time, and the vehicle identity ID of the vehicle is matched from the vehicle database.
The camera device 10 is further configured to obtain second time license print information of the vehicle when matching the identity ID of the vehicle in the vehicle database according to the second time license plate information fails.
Similarly, the second time vehicle pattern information is the vehicle pattern information with the exit time stamp acquired by the image pickup apparatus 10 when the vehicle exits the vehicle exit.
Due to the facts that the photographed license plate image is unclear, the license plate is stained, or the license plate is shielded and the like, the detection rate of the license plate information detection is low, and the license plate information detection is not dependent on the license plate information, and the probability of non-recognition is high to a certain extent, the situation that matching fails can be caused. In this case, the image pickup apparatus 10 acquires the vehicle pattern information again to perform the vehicle pattern information matching, so as to improve the vehicle recognition rate.
The transmission device is further configured to transmit second time pattern information of the vehicle to the server device.
The server device 12 is further configured to determine the identity ID of the vehicle according to the similarity between the second time fingerprint information and the first time fingerprint information.
The vehicle pattern information at the second time is matched with the vehicle pattern information at the first time stored in the vehicle database, and the vehicle identity ID can be determined again according to the vehicle pattern information at the second time because the vehicle pattern information is easier to identify than the license plate information.
Further, under the condition that the time is allowed, the preset identification time can be set, if the result of the first time vehicle pattern information with higher similarity to the second time vehicle pattern information is matched in the vehicle database within the preset identification time, the identity ID of the vehicle is determined again, and the identity ID of the vehicle is determined according to the result with the highest matching degree.
To be more specific, if the identity ID of the vehicle cannot be determined according to the similarity between the second time fingerprint information and the first time fingerprint information, the video frames may be pushed to the display terminal in the order of decreasing the similarity, and the identity ID of the vehicle may be manually determined.
According to the method, a video at an entrance and an exit of a vehicle is obtained, a vehicle frame in a video image is detected, first-time license plate information and first-time vehicle pattern information of the vehicle are obtained, an identity ID of the vehicle is generated according to the first-time license plate information and the first-time vehicle pattern information, and the only vehicle can be determined according to the identity ID of the vehicle; after the vehicle ID is generated, other information of the vehicle and the vehicle ID are stored in a vehicle database. When a vehicle exits from the vehicle outlet, the license plate information of the current vehicle at the second time is obtained, the license plate information at the second time is compared with the license plate information at the first time stored in the vehicle database, and the license plate information of the vehicle is identified. In reality, the conditions that a plurality of vehicles do not hang license plates, hang the license plates irregularly, and the license plates are seriously stained exist, so when the matching of the license plates of the current vehicles and the license plate information in the vehicle database fails, the step-by-step traffic pattern matching is further carried out.
The vehicle pattern matching can be combined with the overall characteristics of the vehicle, is more accurate, and can accurately identify the identity ID of the vehicle. Therefore, the identification of the ID of the vehicle by using the method does not need to enter or exit the vehicle for deceleration and stop, and the ID of the vehicle can be identified by passing the normal speed. The conditions that the accuracy of license plate recognition is low and the identity ID of the vehicle cannot be matched due to the conditions that the license plate is not hung, the license plate is not hung normally, the license plate is seriously stained and the like can be avoided, the passing efficiency of the vehicle at the entrance and the exit is improved, and the road passing congestion caused by queuing is avoided. The embodiment of the application solves the problem of low vehicle identity information recognition rate at the entrance and the exit, and avoids traffic jam caused by the fact that the vehicle identity cannot be recognized at the entrance and the exit.
The present embodiment provides a method for vehicle entry and exit identification, and fig. 2 is a flowchart of a vehicle identification method according to an embodiment of the present application, and as shown in fig. 2, the flowchart includes the following steps:
step S201, when a vehicle enters a vehicle entrance, acquiring first time license plate information and first time vehicle pattern information of the vehicle, generating an identity ID of the vehicle according to the first time license plate information and the first time vehicle pattern information, and recording the identity ID of the vehicle into a vehicle database;
the first time license plate information and the first time vehicle pattern information are license plate information and vehicle pattern information with an entrance time mark, which are acquired when a vehicle enters a vehicle entrance; the recording of the information is equivalent to the acquisition of the characteristic information of the vehicle entering the vehicle entrance, and is used for generating the vehicle ID for verifying the vehicle identity from the characteristic information of the vehicle, then recording the vehicle ID into a vehicle database, and identifying the vehicle ID when the vehicle leaves.
Further, the vehicle entrance is not limited to any gateway that needs to manage the entrance and exit of vehicles, such as a parking lot entrance, a gas station entrance, a mall parking lot entrance, a park vehicle entrance, and a community vehicle entrance.
Further, the vehicle database may also record information not limited to the time when the vehicle enters, the location of the vehicle, and the video segment.
Step S202, when the vehicle exits from the vehicle exit, acquiring second time license plate information of the vehicle, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information;
the license plate information at the second time is the license plate information with the exit time mark acquired when the vehicle exits from the vehicle exit; and acquiring the license plate information of the vehicle when the vehicle exits from the vehicle exit, marking the license plate information acquired when the vehicle exits from the vehicle exit as the license plate information at the second time because the license plate information is acquired once when the vehicle enters the vehicle entrance, performing license plate detection according to the license plate information at the second time, and matching the vehicle identity ID of the vehicle from the vehicle database.
Correspondingly, the vehicle exit is not limited to any exit required to manage vehicle entrance and exit, such as a parking lot exit, a gas station exit, a mall parking lot exit, a park vehicle exit, and a community vehicle exit.
Step S203, when the identity ID of the vehicle is failed to be matched in the vehicle database according to the license plate information at the second time, obtaining the license plate information at the second time of the vehicle;
similarly, the second time vehicle pattern information is the vehicle pattern information with the exit time mark obtained when the vehicle exits the vehicle exit.
Due to the facts that the photographed license plate image is unclear, the license plate is stained, or the license plate is shielded and the like, the detection rate of the license plate information detection is low, and the license plate information detection is not dependent on the license plate information, and the probability of non-recognition is high to a certain extent, the situation that matching fails can be caused. Under the condition, the vehicle pattern information of the vehicle can be acquired again to match the vehicle pattern information, so that the vehicle identification rate is improved.
Step S204, the identity ID of the vehicle is determined according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information.
The vehicle identification ID can be determined again according to the vehicle pattern information at the second time because the vehicle pattern information at the second time is easier to identify than the license plate information by matching the vehicle pattern information at the second time with the vehicle pattern information at the first time stored in the vehicle database.
Further, under the condition that time is allowed, preset identification time can be set, if a result of the first time vehicle pattern information with higher similarity to the second time vehicle pattern information is matched in the vehicle database within the preset identification time, the identity ID of the vehicle is determined again, and the identity ID of the vehicle is determined according to the structure with the highest matching degree.
Further, if the identity ID of the vehicle cannot be determined according to the similarity between the second time fingerprint information and the first time fingerprint information, the video frames are pushed to the display terminal from large to small according to the similarity, and the identity ID of the vehicle is determined manually.
Through the steps S201 to S203, the video at the entrance and the exit of the vehicle is obtained, the vehicle frame in the video image is detected, the first-time license plate information and the first-time vehicle pattern information of the vehicle are obtained, the identity ID of the vehicle is generated according to the first-time license plate information and the first-time vehicle pattern information, and the only vehicle can be determined according to the identity ID of the vehicle; after the vehicle ID is generated, other information of the vehicle and the vehicle ID are stored in a vehicle database. When a vehicle exits from the vehicle outlet, the license plate information of the current vehicle at the second time is obtained, the license plate information at the second time is compared with the license plate information at the first time stored in the vehicle database, and the license plate information of the vehicle is identified. In reality, the conditions that a plurality of vehicles do not hang license plates, hang the license plates irregularly, and the license plates are seriously stained exist, so when the matching of the license plates of the current vehicles and the license plate information in the vehicle database fails, the step-by-step traffic pattern matching is further carried out.
The vehicle pattern matching can be combined with the overall characteristics of the vehicle, is more accurate, and can accurately identify the identity ID of the vehicle. Therefore, the identification of the ID of the vehicle by using the method does not need to enter or exit the vehicle for deceleration and stop, and the ID of the vehicle can be identified by passing the normal speed. The conditions that the accuracy of license plate recognition is low and the identity ID of the vehicle cannot be matched due to the conditions that the license plate is not hung, the license plate is not hung normally, the license plate is seriously stained and the like can be avoided, the passing efficiency of the vehicle at the entrance and the exit is improved, and the road passing congestion caused by queuing is avoided. The embodiment of the application solves the problem of low vehicle identity information recognition rate at the entrance and the exit, and avoids traffic jam caused by the fact that the vehicle identity cannot be recognized at the entrance and the exit.
In some embodiments, in step S201, when the vehicle enters the vehicle entrance, acquiring first-time license plate information and first-time vehicle pattern information of the vehicle, generating an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information, and recording the identity ID of the vehicle in a vehicle database, as shown in fig. 3, specifically including the following steps:
step S301, obtaining video information of the vehicle entrance, and detecting, tracking and matching the vehicle according to the video information of the vehicle entrance to obtain a tracking track of the vehicle.
The specific steps of detecting, tracking and matching the vehicle according to the video information of the vehicle entrance are as follows: the method comprises the steps of taking a video Shot right at an entrance as input video information, detecting each frame of image in the video information by using a Single-frame multi-box Detector (SSD for short) in a deep learning detection algorithm, and obtaining a position frame of a vehicle target in each frame of image, wherein the position frame is represented as [ (x) andlt,ylt)，(xrb,yrb)]matching and tracking the target frame between the video information frames by combining the position frame of the vehicle target in each frame and a related filtering tracking algorithm, thereby obtaining the tracking track of the vehicle target in the video.
Wherein x isltIs the coordinate, x, of the horizontal direction of the upper left corner point of the position framerbFor watering the lower right corner of the position frameCoordinate in the horizontal direction, yltIs the coordinate of the vertical direction of the upper left corner point of the position frame, yrbIs the coordinate of the lower right corner of the position frame in the vertical direction.
The tracking trajectory of the vehicle target in the video, that is, a point sequence formed by coordinates of a center point of a position frame of the vehicle in each frame of video information, may be represented as: { (x _0, y _0, t _0), (x _1, y _1, t _1), (x _2, y _2, t _2), … … (x _2, y _2, t _ 2)), (x _1, y _1, t _ 1)), (x _ n, y _ n, t _ n).
Step S302 is performed to determine the entrance/exit state of the vehicle based on the tracking trajectory of the vehicle.
The concrete steps of judging the access state of the vehicle according to the running track of the vehicle are as follows:
firstly, projecting a tracking track of a vehicle into a single frame video picture, and then completing communication of track points between two frames of track points through linear interpolation, namely realizing the tracking track;
then, judging the main direction of the tracking track, calculating an included angle theta between the main direction of the tracking track and the entrance direction of the crossing line of the entrance and the exit, if the included angle theta is less than 90 degrees, driving the vehicle along the entrance direction, if the included angle theta is greater than 90 degrees, driving the vehicle along the exit direction, and then judging whether the vehicle passes through the entrance or the exit according to whether the driving track of the vehicle is intersected with the crossing line.
Wherein the tracking track can be labeled Tr { (x)0,y0),(x1,y1),(x2,y2),...,(xn-2,yn-2),(xn-1,yn-1),(xn,yn)}；
The main direction of the tracking trajectory can be marked as: TrD (x)TrDe-xTrDs,yTrDe-yTrDs)；
The doorway crossing line may be labeled: l [ (x)0,y0),(x1,y1)]；
The entry direction may be labeled: DirIn (x)DirIne-xDirIns,yDirIne-yDirIns)
The calculation formula of the included angle theta between the main direction of the tracking track and the entrance direction of the entrance and exit crossing line is as follows:
Figure BDA0002750225460000101
wherein: x is the number ofTrDComponent of horizontal direction representing main direction of track
yTrDComponent of vertical direction representing main direction of track
xDirInComponent of horizontal direction representing entry direction of entrance
yDirInRepresenting the component of the vertical direction of the entry direction of the doorway
The main direction of the vehicle tracking track is the track starting point (x)0,y0) And the vector mean value is formed by other points on the track, and the calculation formula of the vector mean value formula is as follows:
Figure BDA0002750225460000111
wherein: n represents that the number of the track points is n;
(xi,yi) Coordinates representing the ith trace point;
Figure BDA0002750225460000112
indicates the starting point (x)0,y0) And end point (x)i,yi) The constructed vector.
Step S303, when the vehicle is judged to be in and out of the entrance of the vehicle, screening out a video frame containing the vehicle attribute information from the tracking track; the vehicle attribute information includes license plate information and vehicle pattern information.
The purpose of screening the video frames containing the vehicle attribute information from the tracking track is to more clearly express images of the vehicle attribute information, and the video frames with larger vehicle position frames, higher vehicle posture consistency and higher image definition can be selected, and more standard and multidimensional screening video frames can be set.
In an embodiment, in step S202, when the vehicle exits the vehicle exit, obtaining second time license plate information of the vehicle, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information, as shown in fig. 4, specifically includes:
step S401, obtaining the video information of the vehicle exit, and detecting, tracking and matching the vehicle according to the video information of the vehicle exit to obtain the tracking track of the vehicle.
The method comprises the following specific steps of detecting and tracking the vehicle target: the method comprises the steps of taking a video Shot right at an entrance as input video information, detecting a vehicle target in each frame of image in the video information by using a Single Shot multi box Detector (SSD for short) in a deep learning detection algorithm, and obtaining a position frame [ (x) of the vehicle target in each frame of imagelt,ylt),(xrb,yrb)]Matching and tracking the target frame between the video information frames by combining the position frame of the vehicle target in each frame and a related filtering tracking algorithm, thereby obtaining the tracking track of the vehicle target in the video.
The tracking trajectory of the vehicle target in the video is a point sequence formed by coordinates of a central point of a position frame of the vehicle in each frame of video information, and the point sequence can be expressed as: { (x)0,y0,t0),(x1,y1,t1),(x2,y2,t2),...,(xn-2,yn-2,tn-2),(xn-1,yn-1,tn-1),(xn,yn,tn)}。
Step S402, judging the access state of the vehicle according to the tracking track of the vehicle;
the concrete steps of judging the access state of the vehicle according to the running track of the vehicle are as follows:
firstly, projecting a tracking track of a vehicle into a single frame video picture, and then completing communication of track points between two frames of track points through linear interpolation, namely realizing the tracking track;
then, judging the main direction of the tracking track, calculating an included angle theta between the main direction of the tracking track and the entrance direction of the crossing line of the entrance and the exit, if the included angle theta is less than 90 degrees, driving the vehicle along the entrance direction, if the included angle theta is greater than 90 degrees, driving the vehicle along the exit direction, and then judging whether the vehicle passes through the entrance or the exit according to whether the driving track of the vehicle is intersected with the crossing line.
Wherein the tracking track can be labeled Tr { (x)0,y0),(x1,y1),(x2,y2)，...，(xn-2,yn-2),(xn-1,yn-1),(xn,yn)}；
The main direction of the tracking trajectory can be marked as: TrD (x)TrDe-xTrDs,yTrDe-yTrDs)；
The doorway crossing line may be labeled: l [ (x)0,y0),(x1,y1)]；
The entry direction may be labeled: DirIn (x)DirIne-xDirIns,yDirIne-yDirIns)
The calculation formula of the included angle theta between the main direction of the tracking track and the entrance direction of the entrance and exit crossing line is as follows:
Figure BDA0002750225460000121
the main direction of the vehicle tracking track is the track starting point (x)0,y0) And the vector mean value is formed by other points on the track, and the calculation formula of the vector formula is as follows:
Figure BDA0002750225460000122
step S403, when the vehicle exit and entrance state is judged to be the exit of the vehicle, screening out the video frame of the vehicle attribute information from the tracking track; the vehicle attribute information comprises license plate information and vehicle pattern information;
step S404, identifying second time license plate information of the vehicle based on the video frame, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information.
The basic processes of license plate recognition are license plate detection, license plate character segmentation and character recognition. The method uses a position frame of a vehicle detection result in license plate detection and combines a regression method of license plate positions. By the method, the accuracy of detecting the license plate is improved, and the detection efficiency is enhanced.
It should be noted that, because license plates are manufactured strictly according to the standard, the position of each character is regressed by using the whole-license global constraint based on deep learning in the character segmentation process, and the accuracy of the character position is also greatly improved.
In one embodiment, screening the video frames containing the vehicle attribute information from the tracking trajectory includes:
and selecting a video frame which contains the vehicle attribute information and has a larger vehicle position frame, higher vehicle attitude consistency and higher image definition from the tracking track.
The video frames containing the vehicle attribute information are screened from the tracking track, so that the images of the vehicle attribute information can be more clearly expressed, and the more clear license plate information and the more clear vehicle pattern information can be obtained through the steps.
Specifically, an image sequence having a specific length is generated by comprehensively selecting and sampling in combination with the following three factors, which are explained below:
in a first aspect, a video frame of a larger vehicle position frame is selected.
Further, since the pixel area occupied by the vehicle object in the video image is very large and can be represented by using the area size of the position frame of the vehicle in the detection result, the larger the area of the position frame is, the more appropriate the video frame is.
And then normalizing the size of each frame of target in the track according to the size of the area of the vehicle position frame in the track, and screening the video frames.
The area formula of the position frame can be expressed as:
Figure BDA0002750225460000131
wherein: sminRepresenting the smallest area value of the target position box in the track;
Smaxindicating the largest area value of the target location box in the trajectory.
In the second aspect, a video frame with a high vehicle posture consistency is selected.
Further, the license plates are hung on the head and tail of the vehicle, so that the smaller the included angle between the driving track of the vehicle and the shooting visual angle is, the better the license plate information of the vehicle can be accurately identified, and the smaller the difference between the same vehicles in the comparison of the vehicle pattern information is, the better the difference is, and therefore the video frames under the gesture sequence with higher consistency are selected.
And in the third aspect, selecting a video frame with higher image definition.
Further, the higher the image quality of the video frame is, the more accurate the vehicle information is, so that the image sharpness index is obtained by using the image sharpness evaluation based on the reference-free image of the secondary blur, and the specific flow is as follows:
step S1, selecting an image to be evaluated, and performing low-pass filtering to obtain a blurred image;
step S2, calculating the change of the gray value of the adjacent pixel of the image to be evaluated and the blurred image;
step S3, comparing the change of the adjacent pixel gray value of the image to be evaluated and the blurred image;
and step S3, carrying out normalization processing on the comparison result to obtain an image definition index.
In one embodiment, the first time vehicle pattern information and the second time vehicle pattern information include vehicle type vehicle style, vehicle body color, license plate type, sunroof, age chart, pendant, ornament, and painting information.
The information of a driver can be recorded when the vehicle pattern is identified, so that the vehicle judgment information is more comprehensive, and the data accuracy is higher.
In one embodiment, the step S204 of determining the identity ID of the vehicle according to the similarity between the second time fingerprint information and the first time fingerprint information includes:
determining the similarity between the second time vehicle pattern information and the first time vehicle pattern information according to the cosine similarity between the N-dimensional floating point vectors of the second time vehicle pattern information and the first time vehicle pattern information;
and when the similarity between the second time vehicle pattern information and the first time vehicle pattern information meets a set threshold, the identity ID of the vehicle corresponding to the second time vehicle pattern information is the same as the identity ID of the vehicle corresponding to the first time vehicle pattern information stored in the vehicle database.
The vehicle pattern information comprises attribute characteristics such as vehicle type, vehicle body color, license plate type, skylight, annual inspection marks, pendants, ornaments and spraying, and the attribute characteristics in the image are extracted through a convolutional neural network model to obtain a group of N-dimensional floating point numbers.
The training process of the convolutional neural network model mainly comprises several main modules of preparation of original training data, generation of iterative training samples and iterative training of the model, wherein the preparation process of the original training data comprises the following steps:
step S1, acquiring video segments of the same vehicle in different scenes;
step S2, obtaining the vehicle track frame sample according to the detection and the tracking;
step S4, obtaining the image sequence of the vehicle according to the sampling of the vehicle track frame;
step S5, cutting the detection frame in the image sequence to obtain a sample image sequence of the vehicle;
and step S6, generating a label matched with the license plate according to the sample image sequence of the vehicle, and obtaining a training sample set of the vehicle.
After an original training sample preparation process is performed to generate an image sequence with a vehicle as a unit and an original training sample set with a license plate as a label, because the dimension of input data of a deep convolutional neural network is fixed, and the length of the image sequence in each sample in the original training sample set is not the same, the iterative training sample generation process is as follows:
step S1, randomly sampling and selecting an image sequence with the designated length of L sheets;
step S2, randomly carrying out disturbance operations such as cutting, rotation, noise superposition and the like on each image in the image sequence;
and step S3, generating an image sequence with the length of L and an iterative training sample with a license plate mapping digital result as a label.
Then, the iterative training process of the model is based on the feedback neural network training principle, and the iterative training sample is iteratively trained and optimized by a random gradient descent method, so that the pattern feature extraction model is obtained.
And finally, passing the image sequence of the vehicle entering and exiting through the vehicle pattern feature extraction model to obtain an N-dimensional floating point vector, and representing the vehicle pattern information of the vehicle by using the N-dimensional floating point vector.
The representation form of the moire information represented by one N-dimensional floating point vector may be F ═ F0,f1,f2,…fn}。
In addition, because the vehicle-line information of each vehicle is an N-dimensional floating-point vector, the similarity between two pieces of vehicle-line information can be characterized by using the cosine similarity between two N-dimensional floating-point vectors.
To explain further, the similarity between two pieces of vehicle-track information is represented by taking a cosine value of an included angle between two vectors in a vector space as a measure of the difference between the two vehicles. If the two vectors are closer, the difference is smaller, the similarity of the pattern information is higher, and the cosine value is 1.
For example, assume that F ═ { F ═ F0,f1,f2,…fnG ═ G0,g1,g2,…gnN-dimensional floating point directions respectively representing two different pieces of vehicle pattern informationQuantity, the formula for calculating the cosine similarity of the N-dimensional floating point vectors representing two different pieces of moire information is:
Figure BDA0002750225460000151
the embodiment also provides a device for vehicle entering and exiting identification, which is used for implementing the embodiment and the preferred embodiment of the method for vehicle identity identification, and the description of the embodiment and the preferred embodiment is omitted. As used hereinafter, the terms "module," "unit," "subunit," and the like may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram of a vehicle identification apparatus according to an embodiment of the present application, and as shown in fig. 5, the apparatus includes: the acquisition module 51, the first recognition module 52 and the second recognition module 53: (ii) a
The obtaining module 51 is configured to obtain first-time license plate information and first-time vehicle pattern information of a vehicle when the vehicle enters a vehicle entrance, generate an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information, and record the identity ID of the vehicle in a vehicle database;
the first identification module 52 is configured to obtain license plate information of the vehicle at a second time when the vehicle exits from the vehicle exit, and match the identity ID of the vehicle in the vehicle database according to the license plate information at the second time;
the second identification module 53 is configured to obtain the second time license information of the vehicle when the license plate information fails to match the identity ID of the vehicle in the vehicle database according to the second time license plate information; and determining the identity ID of the vehicle according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.
The present embodiment also provides an electronic device comprising a memory having a computer program stored therein and a processor configured to execute the computer program to perform the steps of any of the above method embodiments.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
step S1, when the vehicle enters the vehicle entrance, acquiring the first time license plate information and the first time vehicle pattern information of the vehicle, generating the identity ID of the vehicle according to the first time license plate information and the first time vehicle pattern information, and recording the identity ID of the vehicle into a vehicle database.
Step S2, when the vehicle exits the vehicle exit, obtaining the license plate information of the vehicle at the second time, and matching the identity ID of the vehicle in the vehicle database according to the license plate information at the second time;
step S3, when the identity ID of the vehicle is failed to be matched in the vehicle database according to the license plate information at the second time, the license plate information at the second time of the vehicle is obtained;
step S4, determining the identity ID of the vehicle according to the similarity between the second time fingerprint information and the first time fingerprint information.
It should be noted that, for specific examples in this embodiment, reference may be made to examples described in the foregoing embodiments and optional implementations, and details of this embodiment are not described herein again.
In one embodiment, a computer-readable storage medium is provided, and fig. 6 is a block diagram of a computer-readable storage medium according to an embodiment of the present application, as shown in fig. 6, on which a computer program is stored, and the computer program is executed by a processor to implement the steps in a vehicle identification method provided by the above embodiments, and the steps are as follows:
step S1, when the vehicle enters the vehicle entrance, acquiring the first time license plate information and the first time vehicle pattern information of the vehicle, generating the identity ID of the vehicle according to the first time license plate information and the first time vehicle pattern information, and recording the identity ID of the vehicle into a vehicle database.
Step S2, when the vehicle exits the vehicle exit, obtaining the license plate information of the vehicle at the second time, and matching the identity ID of the vehicle in the vehicle database according to the license plate information at the second time;
step S3, when the identity ID of the vehicle is failed to be matched in the vehicle database according to the license plate information at the second time, the license plate information at the second time of the vehicle is obtained;
step S4, determining the identity ID of the vehicle according to the similarity between the second time fingerprint information and the first time fingerprint information.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to serve as a limitation on the computer-readable storage media on which the disclosed aspects may be implemented, as a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile 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), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (9)

1. A vehicle identification method, comprising:
acquiring video information of a vehicle entrance, and detecting, tracking and matching the vehicle according to the video information of the vehicle entrance to obtain a tracking track of the vehicle; judging the access state of the vehicle according to the tracking track of the vehicle; when the in-out state of the vehicle is judged to be that the vehicle enters the vehicle entrance, screening out a video frame containing the vehicle attribute information from the tracking track; the vehicle attribute information comprises license plate information and vehicle pattern information; identifying a first-time license plate and first-time vehicle pattern information of the vehicle based on the video frame, generating an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information, and recording the identity ID into a vehicle database;
when the vehicle exits from a vehicle exit, acquiring second time license plate information of the vehicle, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information;
when the identity ID of the vehicle is matched in the vehicle database according to the license plate information at the second time and fails, acquiring the license plate information at the second time of the vehicle;
and determining the identity ID of the vehicle according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information.
2. The method of claim 1, wherein obtaining license plate information of the vehicle at a second time when the vehicle exits the vehicle exit and matching the identity ID of the vehicle in the vehicle database according to the license plate information at the second time comprises:
acquiring video information of the vehicle exit, and detecting, tracking and matching the vehicle according to the video information of the vehicle exit to obtain a tracking track of the vehicle;
judging the access state of the vehicle according to the tracking track of the vehicle;
when the vehicle is judged to be in and out of the vehicle exit, screening out the video frame of the vehicle attribute information from the tracking track; the vehicle attribute information comprises license plate information and vehicle pattern information;
and identifying second time license plate information of the vehicle based on the video frame, and matching the identity ID of the vehicle in the vehicle database according to the second time license plate information.
3. The method of claim 1 or 2, wherein the screening out the video frames containing the vehicle attribute information from the tracking trajectory comprises:
and selecting a video frame which contains the vehicle attribute information and has a larger vehicle position frame, higher vehicle attitude consistency and higher image definition from the tracking track.
4. The method of claim 1 or 2, wherein the first time vehicle pattern information and the second time vehicle pattern information comprise vehicle type vehicle money, vehicle body color, license plate type, skylight, age list, pendant, ornament, and painting information.
5. The method according to claim 1 or 2, wherein the determining the identity ID of the vehicle according to the similarity of the second time fingerprint information and the first time fingerprint information comprises:
determining the similarity between the second time vehicle pattern information and the first time vehicle pattern information according to the cosine similarity between the N-dimensional floating point vectors of the second time vehicle pattern information and the first time vehicle pattern information;
and when the similarity between the second time vehicle pattern information and the first time vehicle pattern information meets a set threshold, the identity ID of the vehicle corresponding to the second time vehicle pattern information is the same as the identity ID of the vehicle corresponding to the first time vehicle pattern information stored in the vehicle database.
6. A vehicle identification device, comprising: the device comprises an acquisition module, a first identification module and a second identification module:
the acquisition module is used for acquiring video information of a vehicle entrance, and detecting, tracking and matching the vehicle according to the video information of the vehicle entrance to obtain a tracking track of the vehicle; judging the access state of the vehicle according to the tracking track of the vehicle; when the in-out state of the vehicle is judged to be that the vehicle enters the vehicle entrance, screening out a video frame containing the vehicle attribute information from the tracking track; the vehicle attribute information comprises license plate information and vehicle pattern information; identifying a first-time license plate and first-time vehicle pattern information of the vehicle based on the video frame, generating an identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information, and recording the identity ID into a vehicle database;
the first identification module is used for acquiring license plate information of the vehicle at a second time when the vehicle exits from a vehicle outlet, and matching the identity ID of the vehicle in the vehicle database according to the license plate information at the second time;
the second identification module is used for acquiring the second time license print information of the vehicle when the identity ID of the vehicle is failed to be matched in the vehicle database according to the second time license plate information; and determining the identity ID of the vehicle according to the similarity between the second time vehicle pattern information and the first time vehicle pattern information.
7. A vehicle identification system, comprising: an image pickup apparatus, a transmission apparatus, and a server apparatus; the camera equipment is connected with the server equipment through the transmission equipment;
the camera device is used for acquiring video information of the vehicle entrance, and detecting, tracking and matching the vehicle according to the video information of the vehicle entrance to obtain a tracking track of the vehicle; judging the access state of the vehicle according to the tracking track of the vehicle; when the in-out state of the vehicle is judged to be that the vehicle enters the vehicle entrance, screening out a video frame containing the vehicle attribute information from the tracking track; the vehicle attribute information comprises license plate information and vehicle pattern information; identifying a first time license plate and the first time vehicle pattern information of the vehicle based on the video frame;
the transmission equipment is used for transmitting the first-time license plate information and the first-time vehicle pattern information of the vehicle to the server equipment;
the server equipment is used for generating the identity ID of the vehicle according to the first-time license plate information and the first-time vehicle pattern information and recording the identity ID of the vehicle into a vehicle database;
the camera device is further used for acquiring license plate information of the vehicle at a second time when the vehicle exits from a vehicle exit;
the transmission equipment is further used for transmitting the license plate information of the vehicle at the second time to the server equipment;
the server device is further configured to match the identity ID of the vehicle in the vehicle database according to the license plate information at the second time;
the camera device is further configured to acquire second time license print information of the vehicle when matching of the identity ID of the vehicle in the vehicle database according to the second time license plate information fails;
the transmission device is further used for transmitting the second time vehicle pattern information of the vehicle to the server device;
the server device is further configured to determine the identity ID of the vehicle according to the similarity between the second time fingerprint information and the first time fingerprint information.
8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to perform a vehicle identification method according to any one of claims 1 to 5.
9. A storage medium, in which a computer program is stored, wherein the computer program is configured to execute a vehicle identification method according to any one of claims 1 to 5 when running.
CN202011181176.3A 2020-10-29 2020-10-29 Vehicle identity recognition method, device and system and electronic device Active CN112489436B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011181176.3A CN112489436B (en) 2020-10-29 2020-10-29 Vehicle identity recognition method, device and system and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011181176.3A CN112489436B (en) 2020-10-29 2020-10-29 Vehicle identity recognition method, device and system and electronic device

Publications (2)

Publication Number Publication Date
CN112489436A CN112489436A (en) 2021-03-12
CN112489436B true CN112489436B (en) 2022-05-03

Family

ID=74927611

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011181176.3A Active CN112489436B (en) 2020-10-29 2020-10-29 Vehicle identity recognition method, device and system and electronic device

Country Status (1)

Country Link
CN (1) CN112489436B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112990048B (en) * 2021-03-26 2021-11-23 中科视语(北京)科技有限公司 Vehicle pattern recognition method and device
CN115294560B (en) * 2022-08-10 2024-03-01 青岛文达通科技股份有限公司 Vehicle tracking method and system based on attribute matching and motion trail prediction

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB9825776D0 (en) * 1998-11-26 1999-01-20 Roke Manor Research Method of and apparatus for vehicle indentification
KR20110084799A (en) * 2010-01-18 2011-07-26 고려대학교 산학협력단 NOVEL INHIBITORS FOR BLOCKING INTERACTION OF BLT2-GαI3
CN103150904A (en) * 2013-02-05 2013-06-12 中山大学 Bayonet vehicle image identification method based on image features
CN104766479A (en) * 2015-01-27 2015-07-08 公安部交通管理科学研究所 Automobile identity recognition method and device based on ultrahigh frequency radio frequency and video image dual-recognition matching
CN109544712A (en) * 2018-12-15 2019-03-29 深圳壹账通智能科技有限公司 Highway automatic fees-collecting method, system, computer equipment and storage medium

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102567380A (en) * 2010-12-28 2012-07-11 沈阳聚德视频技术有限公司 Method for searching vehicle information in video image
JP2015201018A (en) * 2014-04-07 2015-11-12 富士通株式会社 Vehicle identification device, vehicle identification system, vehicle identification method and vehicle identification program
CN105096653B (en) * 2015-08-10 2018-01-19 电子科技大学 A kind of parking guide method and system
CN105279971B (en) * 2015-10-09 2017-11-14 北京易华录信息技术股份有限公司 A kind of information of vehicles matching process, system and supervising device
CN106778648B (en) * 2016-12-26 2020-02-07 江苏盛世华安互联网科技股份有限公司 Vehicle track tracking and license plate recognition method
CN106971557B (en) * 2017-05-18 2019-10-15 北京宏恺安营停车管理有限公司 A kind of vehicle identification method and system
CN107633687A (en) * 2017-09-08 2018-01-26 绵阳西真科技有限公司 A kind of vehicle identification method and system for parking lot
CN108090975A (en) * 2017-12-14 2018-05-29 深圳市捷顺科技实业股份有限公司 Parking management method and system, computer installation and readable storage medium storing program for executing
CN108288307A (en) * 2018-01-19 2018-07-17 北京悦畅科技有限公司 A kind of parking lot management method, server, video camera and terminal device
CN109214345B (en) * 2018-09-17 2022-05-31 公安部交通管理科学研究所 Method for searching driving track of card-changing vehicle based on similarity comparison
CN111027558A (en) * 2019-10-23 2020-04-17 中电科新型智慧城市研究院有限公司 Method for recognizing type and license plate of violation vehicle
CN110738198A (en) * 2019-11-20 2020-01-31 北京宜世通信息技术有限公司 Railway coal transportation is lost and is spilt monitoring system
CN111563469A (en) * 2020-05-13 2020-08-21 南京师范大学 Method and device for identifying irregular parking behaviors

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB9825776D0 (en) * 1998-11-26 1999-01-20 Roke Manor Research Method of and apparatus for vehicle indentification
KR20110084799A (en) * 2010-01-18 2011-07-26 고려대학교 산학협력단 NOVEL INHIBITORS FOR BLOCKING INTERACTION OF BLT2-GαI3
CN103150904A (en) * 2013-02-05 2013-06-12 中山大学 Bayonet vehicle image identification method based on image features
CN104766479A (en) * 2015-01-27 2015-07-08 公安部交通管理科学研究所 Automobile identity recognition method and device based on ultrahigh frequency radio frequency and video image dual-recognition matching
CN109544712A (en) * 2018-12-15 2019-03-29 深圳壹账通智能科技有限公司 Highway automatic fees-collecting method, system, computer equipment and storage medium

Also Published As

Publication number Publication date
CN112489436A (en) 2021-03-12

Similar Documents

Publication Publication Date Title
CN108596277B (en) Vehicle identity recognition method and device and storage medium
CN109087510B (en) Traffic monitoring method and device
CN105702048B (en) Highway front truck illegal road occupation identifying system based on automobile data recorder and method
US11709282B2 (en) Asset tracking systems
CN105512660B (en) License plate number identification method and device
CN109740424A (en) Traffic violations recognition methods and Related product
CN111079751B (en) Method and device for identifying authenticity of license plate, computer equipment and storage medium
CN108229256B (en) Road construction detection method and device
CN112489436B (en) Vehicle identity recognition method, device and system and electronic device
CN111491093B (en) Method and device for adjusting field angle of camera
CN105930768A (en) Spatial-temporal constraint-based target re-identification method
CN109284705B (en) Anomaly detection method for traffic monitoring video
CN112434566B (en) Passenger flow statistics method and device, electronic equipment and storage medium
CN111898491B (en) Identification method and device for reverse driving of vehicle and electronic equipment
CN111256693B (en) Pose change calculation method and vehicle-mounted terminal
CN111311766A (en) Roadside parking intelligent charging system and method based on license plate recognition and tracking technology
CN110826484A (en) Vehicle weight recognition method and device, computer equipment and model training method
CN113011331B (en) Method and device for detecting whether motor vehicle gives way to pedestrians, electronic equipment and medium
CN112488042B (en) Pedestrian traffic bottleneck discrimination method and system based on video analysis
CN111078946A (en) Bayonet vehicle retrieval method and system based on multi-target regional characteristic aggregation
CN114708547A (en) Vehicle weight recognition method and device, computer equipment and storage medium
CN112699711B (en) Lane line detection method and device, storage medium and electronic equipment
CN112101114A (en) Video target detection method, device, equipment and storage medium
CN114360261B (en) Vehicle reverse running identification method and device, big data analysis platform and medium
CN110879990A (en) Method for predicting queuing waiting time of security check passenger in airport and application thereof

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant