CN115359665A - Multichannel violation vehicle recording method and device based on radio frequency video all-in-one machine - Google Patents
Multichannel violation vehicle recording method and device based on radio frequency video all-in-one machine Download PDFInfo
- Publication number
- CN115359665A CN115359665A CN202210994319.5A CN202210994319A CN115359665A CN 115359665 A CN115359665 A CN 115359665A CN 202210994319 A CN202210994319 A CN 202210994319A CN 115359665 A CN115359665 A CN 115359665A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- passing
- intersection
- vehicle information
- matching rate
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000004891 communication Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 239000003086 colorant Substances 0.000 abstract description 2
- 238000013461 design Methods 0.000 description 14
- 230000006399 behavior Effects 0.000 description 5
- 230000000903 blocking effect Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Computational Linguistics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a multichannel violation vehicle recording method and device based on a radio frequency video all-in-one machine, and relates to the technical field of intelligent traffic. The method comprises the steps of firstly obtaining video data and first vehicle information collected in the same unit period, then obtaining second vehicle information through identification based on the video data, then obtaining vehicle information matching rate of vehicles passing through each intersection through dimensionality calculation such as license plate numbers, passing lane numbers, vehicle types and vehicle colors, then determining vehicle matching number based on all the vehicle information matching rates, and finally recording the video data when judging that fake-plate vehicles, license plates shield vehicles or license-plate-free vehicles pass through a multi-lane intersection in the same unit period based on the comparison result of the vehicle matching number and the number of vehicles passing through the intersection, so that the purpose of automatic evidence obtaining and file reservation is achieved, illegal vehicles do not need to be searched artificially and the identification accuracy and efficiency of the illegal vehicles are greatly improved.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic, and particularly relates to a multichannel violation vehicle recording method and device based on a radio frequency video all-in-one machine.
Background
The electronic license plate radio frequency communication identification system becomes the only technical standard for the identification of automobiles and non-motor vehicles by the characteristics of accuracy, uniqueness, legality, big data storage and the like. In the current intelligent traffic technology field, the illegal violation snapshot of motor vehicles or non-motor vehicles is mainly judged by a camera AI (Artificial Intelligence) identification algorithm. Along with the development of a radio frequency technology and the development of an electronic license plate industry, the radio frequency and video all-in-one machine is applied, so that the data acquisition can be more comprehensively and perfectly carried out on the vehicle violation behaviors, and the technical bottleneck caused by the limitation factors such as environment, climate, illumination, image recognition rate and accuracy when the data can only be acquired by a single camera is solved on a large level.
In the current electronic license plate industry, in the aspect of identifying motor vehicle or non-motor vehicle violation behaviors, the radio frequency video all-in-one machine identifies the violation behaviors such as fake plate, license plate shielding and no license plate, although some related data can be collected, the data collection is incomplete and mainly supports the condition of a single vehicle on a single lane, and the condition of multiple vehicles on multiple lanes cannot be rapidly collected and judged, generally, traffic management personnel can accurately judge all the violation behaviors by combining video or multiple pictures with artificial comprehensive judgment, and the problem of obvious low efficiency exists.
Disclosure of Invention
The invention aims to provide a multichannel violation vehicle recording method and device based on a radio frequency video all-in-one machine, computer equipment and a computer readable storage medium, which are used for solving the problem of obvious low efficiency caused by the fact that traffic management personnel can accurately judge violation behaviors of vehicles such as fake plate, license plate shielding, no license plate and the like only by combining videos or a plurality of pictures with artificial comprehensive judgment aiming at the condition of multiple lanes and multiple vehicles.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, a multichannel violation vehicle recording method based on a radio frequency video all-in-one machine is provided, and comprises the following steps:
acquiring video data and first vehicle information acquired in the same unit period, wherein the video data is acquired by a camera module in a radio frequency video all-in-one machine, the radio frequency video all-in-one machine is arranged at a multi-lane intersection, the first vehicle information is acquired by data interaction between a radio frequency module in the radio frequency video all-in-one machine and an electronic license plate of a vehicle passing through the intersection, the vehicle passing through the intersection is a vehicle passing through the multi-lane intersection, and the first vehicle information comprises at least one license plate number of the vehicle passing through the intersection, the number of the passing lane, the type of the vehicle and the color of the vehicle;
importing the video data into a vehicle information recognition model which is based on a target detection algorithm and is trained in advance, and outputting to obtain second vehicle information, wherein the second vehicle information comprises at least one license plate number of a vehicle passing through the intersection, a number of a passing lane, a vehicle type and a vehicle color;
traversing each intersection passing vehicle in the first vehicle information and each intersection passing vehicle in the second vehicle information, and calculating to obtain a vehicle information matching rate:
wherein i and j are positive integers respectively, VM ij A vehicle information matching rate, η, representing a vehicle passing through an ith vehicle intersection in the first vehicle information and a vehicle passing through a jth vehicle intersection in the second vehicle information LP Representing a predetermined weight coefficient, LP, corresponding to the license plate number ij Representing the matching rate of the number plate of the vehicle passing through the ith intersection and the vehicle passing through the jth intersection, eta CL Indicating the lane traveledNumber corresponding to a predetermined weight coefficient, CL ij Represents the passing lane number matching rate of the vehicle passing through the ith intersection and the vehicle passing through the jth intersection, eta VT Representing a predetermined weight coefficient, VT, corresponding to the type of vehicle ij Representing a vehicle type matching rate, eta, of a vehicle passing through the ith intersection and a vehicle passing through the jth intersection VC Indicating a preset weight coefficient, VC, corresponding to the color of the vehicle ij Representing a vehicle color matching rate of a vehicle passing through the ith intersection with a vehicle passing through the jth intersection;
summarizing all the vehicle information matching rates to obtain a matching rate set;
determining the matching number of the vehicles according to the matching rate set;
and judging whether a vehicle violating the rules passes through the multi-lane intersection in the same unit period or not according to the comparison result of the vehicle matching number and the number of the vehicles passing through the intersection in the first vehicle information and the second vehicle information, if so, recording the video data, otherwise, not recording the video data, wherein the vehicle violating the rules is a fake plate vehicle, a license plate sheltered vehicle or a license plate-free vehicle.
Based on the content of the invention, an intelligent scheme for searching illegal vehicles without man-made synthesis aiming at the conditions of multiple lanes and multiple vehicles is provided, namely video data and first vehicle information acquired in the same unit period are firstly acquired, then second vehicle information is obtained by recognition based on the video data, then the matching rate of the vehicle information of each crossing passing through the vehicle is obtained by calculation according to the dimensions such as license plate number, passing lane number, vehicle type and vehicle color, then the matching number of the vehicle is determined based on all the matching rates of the vehicle information, and finally the video data is recorded when the vehicles with the fake plate, the vehicles with the fake plate or the vehicles without the fake plate pass through the multiple lanes crossing in the same unit period are judged based on the comparison result of the matching number of the vehicle and the number of the vehicles passing through the crossing, so that the purpose of automatic evidence obtaining and retaining is realized, the illegal vehicles do not need to be searched by man-made synthesis, the accuracy and the efficiency of illegal vehicle recognition are greatly improved, and the problem that illegal vehicles such as the fake plate, the number plate and the illegal vehicles without the fake plate and the number plate under the condition of multiple lanes and the multiple vehicles can not be completely recognized under the condition of multiple lanes and the multiple vehicles can not be recognized.
In one possible design, the vehicle information identification model includes a YOLO object detection model in combination with Opencv technology.
In one possible design, the license plate number matching rate LP ij Is determined as follows:
judging whether the license plate number of the vehicle passing through the ith intersection is matched with the license plate number of the vehicle passing through the jth intersection according to a preset license plate number matching rule, if so, enabling the license plate number matching rate LP ij To 100%, otherwise make the license plate number match rate LP ij Is 0%.
In one possible design, the weighting factor η is preset LP 、η CL 、η VT Or η VC Different values are preset according to different time periods of the same unit period, different weather conditions appearing in the same unit period and/or different road conditions of the multi-lane intersection.
In one possible design, determining the vehicle matching number according to the matching rate set includes the following steps S50 to S54:
s50, initializing the vehicle matching number to be zero, and then executing a step S51;
s51, searching the maximum value of the matching rate of the vehicle information in the current matching rate set, and then executing the step S52;
s52, judging whether the maximum value of the matching rate of the vehicle information is larger than a preset matching rate threshold value, if so, executing a step S53, otherwise, ending;
s53, taking a pair of crossing passing vehicles corresponding to the maximum value of the vehicle information matching rate as a pair of matched vehicles, adding 1 to the vehicle matching number, and then executing the step S54;
and S54, eliminating all vehicle information matching rates corresponding to the matched vehicles from the current matching rate set to obtain a new matching rate set, then judging whether the new matching rate set has any vehicle information matching rate, if so, returning to execute the step S51, and if not, finishing.
In one possible design, after regarding a pair of intersection-passing vehicles corresponding to the maximum value of the vehicle information matching rate as a pair of matching vehicles, the method further includes:
taking the license plate number, the number of the passing lane, the vehicle type and the vehicle color which correspond to the pair of matched vehicles and are in the first vehicle information as verification data corresponding to the video data;
and importing the video data and the verification data into the vehicle information identification model for training to obtain a new vehicle information identification model.
In one possible design, recording the video data includes:
marking vehicles passing through the road junction which are not successfully matched in the video images of the video data to obtain new video images;
storing the new video image in a database.
In a second aspect, a multichannel violation vehicle recording device based on a radio frequency video all-in-one machine is provided, and comprises a data information acquisition unit, a vehicle information identification unit, a matching rate calculation unit, a matching rate summarizing unit, a matching number determination unit and a violation vehicle judgment unit;
the data information acquisition unit is used for acquiring video data and first vehicle information which are acquired in the same unit period, wherein the video data are acquired by a camera module in a radio frequency video all-in-one machine, the radio frequency video all-in-one machine is arranged at a multi-lane intersection, the first vehicle information is acquired by data interaction between a radio frequency module in the radio frequency video all-in-one machine and an electronic license plate of a vehicle passing through the intersection, the vehicle passing through the intersection is a vehicle passing through the multi-lane intersection, and the first vehicle information comprises at least one license plate number of the vehicle passing through the intersection, the number of the passing lane, the type of the vehicle and the color of the vehicle;
the vehicle information identification unit is in communication connection with the data information acquisition unit and is used for importing the video data into a vehicle information identification model which is based on a target detection algorithm and completes training in advance and outputting to obtain second vehicle information, wherein the second vehicle information comprises at least one license plate number of a vehicle passing through the intersection, a passing lane number, a vehicle type and a vehicle color;
the matching rate calculation unit is respectively in communication connection with the data information acquisition unit and the vehicle information identification unit, and is used for traversing vehicles passing through the intersection in the first vehicle information and vehicles passing through the intersection in the second vehicle information, and calculating to obtain a vehicle information matching rate:
wherein i and j are positive integers respectively, VM ij A vehicle information matching rate, η, representing a vehicle passing through an ith intersection in the first vehicle information and a vehicle passing through a jth intersection in the second vehicle information LP Representing a predetermined weight coefficient, LP, corresponding to the license plate number ij Representing the matching rate of the number plate of the vehicle passing through the ith intersection and the vehicle passing through the jth intersection, eta CL Representing a predetermined weight coefficient, CL, corresponding to the number of the passing lane ij Represents the passing lane number matching rate of the vehicle passing through the ith intersection and the vehicle passing through the jth intersection, eta VT Indicating a preset weight coefficient, VT, corresponding to the type of vehicle ij Represents a vehicle type matching rate, η, of a vehicle passing through the ith intersection and a vehicle passing through the jth intersection VC Indicating a preset weight coefficient, VC, corresponding to the color of the vehicle ij Representing a vehicle color matching rate of a vehicle passing through the ith intersection with a vehicle passing through the jth intersection;
the matching rate summarizing unit is in communication connection with the matching rate calculating unit and is used for summarizing all the vehicle information matching rates to obtain a matching rate set;
the matching number determining unit is in communication connection with the matching rate summarizing unit and is used for determining the matching number of the vehicles according to the matching rate set;
the violation vehicle judging unit is in communication connection with the matching number determining unit and is used for judging whether a violation vehicle passes through the multi-lane intersection in the same unit period or not according to the comparison result of the vehicle matching number and the number of the vehicles passing through the intersection in the first vehicle information and the second vehicle information, if so, the video data is recorded, otherwise, the video data is not recorded, wherein the violation vehicle is a fake-plate vehicle, a license plate sheltered vehicle or a license plate-free vehicle.
In a third aspect, there is provided a computer device comprising a memory, a processor and a transceiver in communication with each other, wherein the memory is used for storing a computer program, the transceiver is used for sending and receiving messages, and the processor is used for reading the computer program and executing the multi-channel violation vehicle recording method as described in the first aspect or any possible design of the first aspect.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon instructions which, when run on a computer, perform a multi-channel violation vehicle recording method as set forth in the first aspect or any of the possible designs of the first aspect.
In a fifth aspect, there is provided a computer program product containing instructions which, when run on a computer, cause the computer to carry out a multi-channel violation vehicle recording method as set out in the first aspect or any possible design thereof.
The beneficial effect of above-mentioned scheme:
(1) The invention provides an intelligent scheme for aiming at the conditions of multiple lanes and multiple vehicles without manually and comprehensively searching for violation vehicles, namely, video data and first vehicle information acquired in the same unit period are firstly acquired, second vehicle information is acquired based on the video data, then the vehicle information matching rate of each pair of crossing passing vehicles is calculated from dimensions such as license plate number, passing lane number, vehicle type and vehicle color, the vehicle information matching rate is determined based on all the vehicle information matching rates, finally the video data is recorded when the number of fake plate vehicles, license plate blocking vehicles or no-number plate vehicles pass through the multiple lane crossing in the same unit period is judged based on the comparison result of the vehicle information matching rate and the crossing passing vehicle number, so that the purpose of automatically obtaining evidence and keeping the file is realized, the violation vehicles do not need to be manually and comprehensively searched, the accuracy and the efficiency of violation vehicle identification are greatly improved, and the problem that the violation vehicles such as fake plate, license plate blocking vehicles and no-number plate vehicles under the conditions of multiple lanes and multiple vehicles cannot be completely identified in the industry is solved;
(2) The matching calculation time and the CPU occupancy rate can be greatly shortened, and the conditions of different places, different time periods, different weather and/or different intersections can be better met through personalized weight coefficient configuration, so that the condition that the violation rate of the same equipment is greatly different under different scenes is avoided, and the practical application and popularization are facilitated;
(3) The vehicle information identification model can continuously learn by self, so that a complete vehicle information model database can be gradually established, and the problem that a plurality of vehicle passing data cannot be completely identified at the same time by video identification is further solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of a multichannel violation vehicle recording method based on a radio frequency video all-in-one machine provided in the embodiment of the application.
Fig. 2 is a schematic structural diagram of a multichannel violation vehicle recording device based on a radio frequency video all-in-one machine provided by the embodiment of the application.
Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly described below with reference to the accompanying drawings and the embodiments or the description in the prior art, it is obvious that the following description of the structure of the drawings is only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. It should be noted that the description of the embodiments is provided to help understanding of the present invention, and the present invention is not limited thereto.
It will be understood that, although the terms first, second, etc. may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, a first object may be referred to as a second object, and similarly, a second object may be referred to as a first object, without departing from the scope of example embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, B exists alone or A and B exist at the same time; also for example, a, B, and/or C, may indicate the presence of any one or any combination of a, B, and C; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists singly or A and B exist simultaneously; in addition, for the character "/" that may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
As shown in fig. 1, the multichannel violation vehicle recording method based on the radio frequency video all-in-one machine provided in the first aspect of the embodiment may be, but is not limited to be, executed by a Computer device having certain computing resources and being communicatively connected to the radio frequency video all-in-one machine, for example, by an electronic device such as a platform server, a Personal Computer (PC, which refers to a multipurpose Computer with a size, price and performance suitable for Personal use; a desktop Computer, a notebook Computer, a small notebook Computer, a tablet Computer, an ultrabook, and the like all belong to the Personal Computer), a smart phone, a Personal Digital Assistant (PDA), or a wearable device. As shown in fig. 1, the multi-channel violation vehicle recording method may include, but is not limited to, the following steps S1 to S6.
The method includes the steps that video data and first vehicle information collected in the same unit period are obtained, wherein the video data are collected through a camera module in a radio frequency video all-in-one machine, the radio frequency video all-in-one machine is arranged at a multi-lane intersection, the first vehicle information is obtained through data interaction between a radio frequency module in the radio frequency video all-in-one machine and an electronic license plate of a vehicle passing through the intersection, the vehicle passing through the intersection is the vehicle passing through the multi-lane intersection, and the first vehicle information includes but is not limited to at least one license plate number, the number of the passing lane, the type of the vehicle, the color of the vehicle and the like of the vehicle passing through the intersection.
In the step S1, the same unit period may be, but is not limited to, the same minute or the same second, etc. The radio frequency video all-in-one machine is an existing device, and can be but not limited to pull the video data of the camera module through an h.265 protocol (i.e. a new video coding standard formulated after an h.264 protocol), and since a special chip is arranged inside the electronic license plate to store detailed information of vehicles, such as information of license plate number, vehicle type, vehicle color and filing date, accurate detailed data (i.e. the first vehicle information) of vehicles passing through the intersection can be acquired through interaction between the radio frequency module and conventional data of the electronic license plate. In addition, the number of the passing lane is the unique number of a certain lane which is specifically passed by the vehicle passing through the multi-lane intersection at the intersection, and can be determined by the conventional radio frequency direction finding technology.
And S2, importing the video data into a vehicle information recognition model which is based on a target detection algorithm and is trained in advance, and outputting to obtain second vehicle information, wherein the second vehicle information comprises but is not limited to the license plate number, the number of the passing lane, the type of the vehicle, the color of the vehicle and the like of at least one vehicle passing through the intersection.
In step S2, the target detection algorithm is an existing artificial intelligence recognition algorithm for recognizing and marking the position of objects in the picture, and specifically, but not limited to, the target detection algorithm is proposed in 2015 by using Faster R-CNN (Faster Regions with associated Neural Networks features), which obtains a plurality of first target detection algorithms in the ILSVRV and COCO contests in 2015, SSD (Single Shot multiple box Detector, single Shot Liu target detection algorithm, one of the currently popular main detection frames, which is proposed on ECCV by Wei Liu, or YOLO (young only box Detector, which has been recently developed to V4 version), the application in the industry is also extensive, and the basic principle is to firstly divide the input image into 7 × 7 grids, then predict 2 grids for each grid, remove 2 frames for each grid, and then remove frames according to a threshold comparison method, and remove frames of the target detection algorithm, and finally remove frames, and obtain a target detection window. Therefore, in particular, the vehicle information identification model includes, but is not limited to, a YOLO target detection model that combines Opencv (which is a cross-platform computer vision and machine learning software library issued based on apache2.0 licensing/open source and can be run on Linux, windows, android, and Mac OS operating systems) technology, so that in the process of multiple vehicles passing through multiple lanes simultaneously, the vehicle identification and the vehicle number counting can be simultaneously and completely realized, and the problem that the vehicle data passing through multiple vehicles cannot be simultaneously and completely identified by video identification can be solved.
S3, traversing each intersection passing vehicle in the first vehicle information and each intersection passing vehicle in the second vehicle information, and calculating to obtain a vehicle information matching rate:
wherein i and j are each a positive integer,VM ij a vehicle information matching rate, η, representing a vehicle passing through an ith vehicle intersection in the first vehicle information and a vehicle passing through a jth vehicle intersection in the second vehicle information LP Representing a preset weight coefficient, LP, corresponding to the license plate number ij Representing the matching rate, eta, of the number plate of the vehicle passing through the ith intersection and the vehicle passing through the jth intersection CL Representing a preset weight coefficient, CL, corresponding to the number of the passing lane ij Represents the matching rate of the passing lane number of the vehicle passing through the ith intersection and the passing vehicle passing through the jth intersection, eta VT Representing a predetermined weight coefficient, VT, corresponding to the type of vehicle ij Representing a vehicle type matching rate, eta, of a vehicle passing through the ith intersection and a vehicle passing through the jth intersection VC Indicating a preset weight coefficient, VC, corresponding to the color of the vehicle ij Indicating the vehicle color matching rate of the vehicle passing through the ith intersection and the vehicle passing through the jth intersection.
In the step S3, specifically, the license plate number matching rate LP ij May be determined, but is not limited to, as follows: judging whether the license plate number of the vehicle passing through the ith intersection is matched with the license plate number of the vehicle passing through the jth intersection according to a preset license plate number matching rule (such as only matching the last four characters of the license plate number or only matching the first five characters of the license plate number, and the like), and if so, enabling a license plate number matching rate LP ij To 100%, otherwise make the license plate number match rate LP ij Is 0%. Matching rate CL of passing lane numbers at the same time ij Vehicle type matching rate VT ij And vehicle color matching rate VC ij And may be obtained in a similar manner by conventional modification. In addition, in order to ensure that the vehicle information matching rate can be adapted to the spatial and temporal situation, it is preferable that a weight coefficient η is preset LP 、η CL 、η VT Or η VC Different values are preset according to different time periods of the same unit period, different weather conditions appearing in the same unit period and/or different road conditions of the multi-lane intersection; for example, in the morning, the noon and the evening, different preset weighting coefficients eta are respectively set LP 、η CL 、η VT And η VC 。
And S4, summarizing all the vehicle information matching rates to obtain a matching rate set.
In the step S4, assuming that the first vehicle information includes M license plates of vehicles passing through the intersection, a number of passing lanes, a vehicle type, and a vehicle color, and the second vehicle information includes N license plates of vehicles passing through the intersection, a number of passing lanes, a vehicle type, and a vehicle color, through the step S3, M × N matching rates of the vehicle information are obtained, so that the matching rate set includes M × N elements.
And S5, determining the matching number of the vehicles according to the matching rate set.
In the step S5, the vehicle matching number may be determined based on a comparison result of a vehicle information matching rate with a preset matching rate threshold. Preferably, in order to accurately determine the vehicle matching number, the vehicle matching number is determined according to the matching rate set, including but not limited to the following steps S50 to S54.
And S50, initializing the vehicle matching number to be zero, and then executing the step S51.
And S51, finding the maximum value of the matching rate of the vehicle information in the current matching rate set, and then executing the step S52.
S52, judging whether the maximum value of the matching rate of the vehicle information is larger than a preset matching rate threshold value, if so, executing a step S53, and if not, finishing.
In step S52, the matching rate threshold is, for example, 61.8%.
And S53, taking a pair of crossing passing vehicles corresponding to the maximum value of the vehicle information matching rate as a pair of matched vehicles, adding 1 to the vehicle matching number, and then executing the step S54.
S54, eliminating all vehicle information matching rates corresponding to the matched vehicles from the current matching rate set to obtain a new matching rate set, then judging whether vehicle information matching rates exist in the new matching rate set, if so, returning to execute the step S51, and otherwise, ending.
In the step S54, for example, if the pair of matching vehicles is the vehicle a and the vehicle B, all vehicle information matching rates corresponding to the vehicle a and all vehicle information matching rates corresponding to the vehicle B need to be eliminated from the current matching rate set.
S6, judging whether vehicles violating the rules pass through the multi-lane intersection in the same unit period or not according to the comparison result of the vehicle matching number and the number of the vehicles passing through the intersection in the first vehicle information and the second vehicle information, if so, recording the video data, and otherwise, not recording the video data, wherein the vehicles violating the rules are fake-licensed vehicles, license plate sheltered vehicles or license plate-free vehicles.
In the step S6, specifically, if the vehicle matching number is equal to the number of vehicles passing through the intersection in the first vehicle information and the second vehicle information, it indicates that at least one vehicle passing through the intersection in the first vehicle information corresponds to at least one vehicle passing through the intersection in the second vehicle information one to one, and there is no fake plate vehicle, license plate blocking vehicle or license plate-free vehicle, otherwise, it indicates that there may be fake plate vehicle, license plate blocking vehicle or license plate-free vehicle, and it is necessary to record the video data for obtaining evidence and retaining the file. Preferentially, in order to facilitate the staff to intuitively and quickly perceive the violation vehicle, the video data is recorded, including but not limited to: marking vehicles passing through the road junction (namely the violation vehicles) which are not successfully matched in the video images of the video data to obtain new video images; the new video image is then stored in a database.
The multichannel violation vehicle recording method based on the radio frequency video all-in-one machine and described in the steps S1-S6 provides an intelligent scheme for searching violation vehicles without manual synthesis under the condition of multiple lanes and multiple vehicles, namely video data and first vehicle information collected in the same unit period are firstly obtained, second vehicle information is obtained through recognition based on the video data, then vehicle information matching rates of vehicles passing through each crossing are obtained through calculation according to dimensions such as license plate numbers, passing lane numbers, vehicle types and vehicle colors, then vehicle matching numbers are determined based on all the vehicle information matching rates, and finally the purpose of automatic evidence obtaining and retaining is achieved when the fact that fake plate vehicles, license plates block the vehicles or no license plates pass through the multiple lanes crossing in the same unit period is judged based on the comparison result of the vehicle matching numbers and the crossing passing vehicle numbers, so that the violation vehicle recognition accuracy and efficiency are greatly improved, and the problems that the fake plate vehicles cannot be completely recognized under the condition of multiple lanes, license plates and the number of vehicles in the industry cannot be completely recognized are solved. In addition, the matching calculation time and the CPU occupancy rate can be greatly shortened; and through the configuration of the personalized weight coefficient, the condition of different places, different time periods, different weather and/or different intersections can be better met, the condition that the violation rate of the same equipment is greatly different under different scenes is avoided, and the practical application and popularization are facilitated.
In this embodiment, on the basis of the technical solution of the first aspect, a possible design of how to enable the vehicle information recognition model to continuously learn by itself is further provided, that is, after a pair of intersection passing vehicles corresponding to the maximum value of the vehicle information matching rate is used as a pair of matching vehicles, the method further includes, but is not limited to: taking the license plate number, the number of the passing lane, the type of the vehicle and the color of the vehicle which correspond to the pair of matched vehicles and are in the first vehicle information as verification data corresponding to the video data; and importing the video data and the verification data into the vehicle information identification model for training to obtain a new vehicle information identification model.
Therefore, based on the first possible design, the vehicle information identification model can continuously learn by itself, so that a complete vehicle information model database can be gradually established, and the problem that a plurality of vehicle passing data cannot be completely identified simultaneously by video identification at present is further solved.
As shown in fig. 2, a second aspect of the present embodiment provides a virtual device for implementing the multichannel violation vehicle recording method according to any one of the first aspect or the first aspect, where the virtual device includes a data information obtaining unit, a vehicle information identifying unit, a matching rate calculating unit, a matching rate summarizing unit, a matching number determining unit, and a violation vehicle determining unit;
the data information acquisition unit is used for acquiring video data and first vehicle information which are acquired in the same unit period, wherein the video data are acquired by a camera module in a radio frequency video all-in-one machine, the radio frequency video all-in-one machine is arranged at a multi-lane intersection, the first vehicle information is acquired by data interaction between a radio frequency module in the radio frequency video all-in-one machine and an electronic license plate of a vehicle passing through the intersection, the vehicle passing through the intersection is a vehicle passing through the multi-lane intersection, and the first vehicle information comprises at least one license plate number of the vehicle passing through the intersection, the number of the passing lane, the type of the vehicle and the color of the vehicle;
the vehicle information identification unit is in communication connection with the data information acquisition unit and is used for importing the video data into a vehicle information identification model which is based on a target detection algorithm and completes training in advance and outputting to obtain second vehicle information, wherein the second vehicle information comprises at least one license plate number of a vehicle passing through the intersection, a passing lane number, a vehicle type and a vehicle color;
the matching rate calculation unit is respectively in communication connection with the data information acquisition unit and the vehicle information identification unit, and is used for traversing each intersection passing vehicle in the first vehicle information and each intersection passing vehicle in the second vehicle information, and calculating to obtain a vehicle information matching rate:
wherein i and j are positive integers respectively, VM ij A vehicle information matching rate, η, representing a vehicle passing through an ith vehicle intersection in the first vehicle information and a vehicle passing through a jth vehicle intersection in the second vehicle information LP Representing a preset weight coefficient, LP, corresponding to the license plate number ij Indicating the ith vehicleThe matching rate, eta, of the number plate of the vehicles passing through the intersection and the vehicles passing through the jth intersection CL Representing a preset weight coefficient, CL, corresponding to the number of the passing lane ij Represents the matching rate of the passing lane number of the vehicle passing through the ith intersection and the passing vehicle passing through the jth intersection, eta VT Representing a predetermined weight coefficient, VT, corresponding to the type of vehicle ij Representing a vehicle type matching rate, eta, of a vehicle passing through the ith intersection and a vehicle passing through the jth intersection VC Indicating a preset weight coefficient, VC, corresponding to the color of the vehicle ij Representing a vehicle color matching rate of a vehicle passing through the ith intersection with a vehicle passing through the jth intersection;
the matching rate summarizing unit is in communication connection with the matching rate calculating unit and is used for summarizing all the vehicle information matching rates to obtain a matching rate set;
the matching number determining unit is in communication connection with the matching rate summarizing unit and is used for determining the matching number of the vehicles according to the matching rate set;
the violation vehicle judging unit is in communication connection with the matching number determining unit and is used for judging whether violation vehicles pass through the multi-lane intersection in the same unit period or not according to the comparison result of the vehicle matching number and the number of vehicles passing through the intersection in the first vehicle information and the second vehicle information, if yes, the video data are recorded, and if not, the video data are not recorded, wherein the violation vehicles are fake-licensed vehicles, license plate sheltered vehicles or license plate-free vehicles.
The working process, working details and technical effects of the device provided in the second aspect of this embodiment may refer to the first aspect or any one of the first aspect that may be designed as the multichannel violation vehicle recording method, and are not described herein again.
As shown in fig. 3, a third aspect of the present embodiment provides a computer device for executing the multi-channel violation vehicle recording method according to any one of the first aspect or the first aspect, including a memory, a processor and a transceiver, which are sequentially connected in communication, wherein the memory is used for storing a computer program, the transceiver is used for transceiving messages, and the processor is used for reading the computer program to execute the multi-channel violation vehicle recording method according to any one of the first aspect or the first aspect. For example, the Memory may include, but is not limited to, a Random-Access Memory (RAM), a Read-Only Memory (ROM), a Flash Memory (Flash Memory), a First-in First-out (FIFO), and/or a First-in Last-out (FILO), and the like; the processor may be, but is not limited to, a microprocessor of the model number STM32F105 family. In addition, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.
For the working process, working details and technical effects of the foregoing computer device provided in the third aspect of this embodiment, reference may be made to the first aspect or any one of the possible designs of the multichannel violation vehicle recording method in the first aspect, which is not described herein again.
A fourth aspect of the present embodiment provides a computer readable storage medium storing instructions comprising the multi-channel violation vehicle recording method as may be devised by the first aspect or any of the first aspects, i.e., the computer readable storage medium having stored thereon instructions which, when executed on a computer, perform the multi-channel violation vehicle recording method as may be devised by any of the first aspects or the first aspects. The computer-readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a computer-readable storage medium such as a floppy disk, an optical disk, a hard disk, a flash Memory, a flash disk and/or a Memory Stick (Memory Stick), and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
For the working process, working details and technical effects of the foregoing computer-readable storage medium provided in the fourth aspect of this embodiment, reference may be made to the first aspect or any one of the possible designs of the multichannel violation vehicle recording method in the first aspect, which is not described herein again.
A fifth aspect of the present embodiments provides a computer program product containing instructions which, when run on a computer, cause the computer to perform a multi-channel violation vehicle recording method as described in the first aspect or any of the possible designs of the first aspect. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices.
Finally, it should be noted that: the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A multichannel violation vehicle recording method based on a radio frequency video all-in-one machine is characterized by comprising the following steps:
acquiring video data and first vehicle information acquired in the same unit period, wherein the video data is acquired by a camera module in a radio frequency video all-in-one machine, the radio frequency video all-in-one machine is arranged at a multi-lane intersection, the first vehicle information is acquired by data interaction between a radio frequency module in the radio frequency video all-in-one machine and an electronic license plate of a vehicle passing through the intersection, the vehicle passing through the intersection is a vehicle passing through the multi-lane intersection, and the first vehicle information comprises at least one license plate number of the vehicle passing through the intersection, the number of the passing lane, the type of the vehicle and the color of the vehicle;
importing the video data into a vehicle information recognition model which is based on a target detection algorithm and is trained in advance, and outputting to obtain second vehicle information, wherein the second vehicle information comprises at least one license plate number of a vehicle passing through the intersection, a number of a passing lane, a vehicle type and a vehicle color;
traversing each intersection passing vehicle in the first vehicle information and each intersection passing vehicle in the second vehicle information, and calculating to obtain a vehicle information matching rate:
wherein i and j are positive integers respectively, VM ij A vehicle information matching rate, η, representing a vehicle passing through an ith vehicle intersection in the first vehicle information and a vehicle passing through a jth vehicle intersection in the second vehicle information LP Representing a predetermined weight coefficient, LP, corresponding to the license plate number ij Representing the matching rate, eta, of the number plate of the vehicle passing through the ith intersection and the vehicle passing through the jth intersection CL Representing a preset weight coefficient, CL, corresponding to the number of the passing lane ij Represents the matching rate of the passing lane number of the vehicle passing through the ith intersection and the passing vehicle passing through the jth intersection, eta VT Indicating a preset weight coefficient, VT, corresponding to the type of vehicle ij Representing a vehicle type matching rate, eta, of a vehicle passing through the ith intersection and a vehicle passing through the jth intersection VC Indicating a predetermined weight coefficient, VC, corresponding to the color of the vehicle ij Representing a vehicle color matching rate of a vehicle passing through the ith intersection with a vehicle passing through the jth intersection;
summarizing all the vehicle information matching rates to obtain a matching rate set;
determining the matching number of the vehicles according to the matching rate set;
and judging whether a violation vehicle passes through the multi-lane intersection in the same unit period or not according to a comparison result of the vehicle matching number and the number of vehicles passing through the intersection in the first vehicle information and the second vehicle information, if so, recording the video data, otherwise, not recording the video data, wherein the violation vehicle is a fake plate vehicle, a license plate sheltered vehicle or a license plate-free vehicle.
2. The multi-channel violation vehicle recording method as recited in claim 1 wherein the vehicle information identification model comprises a YOLO target detection model in conjunction with Opencv technology.
3. The multi-channel violation vehicle recording method of claim 1,license plate number matching rate LP ij Is determined as follows:
judging whether the license plate number of the vehicle passing through the ith intersection is matched with the license plate number of the vehicle passing through the jth intersection according to a preset license plate number matching rule, if so, enabling a license plate number matching rate LP ij Is 100%, otherwise the license plate number matching rate LP is realized ij Is 0%.
4. The multi-channel violation vehicle recording method of claim 1 wherein the predetermined weight coefficient η LP 、η CL 、η VT Or η VC Different values are preset according to different time periods of the same unit period, different weather conditions appearing in the same unit period and/or different road conditions of the multi-lane intersection.
5. The multi-channel violation vehicle recording method as recited in claim 1 wherein determining the number of vehicle matches based on the set of match rates comprises steps S50-S54 of:
s50, initializing the vehicle matching number to be zero, and then executing a step S51;
s51, searching the maximum value of the matching rate of the vehicle information in the current matching rate set, and then executing the step S52;
s52, judging whether the maximum value of the matching rate of the vehicle information is larger than a preset matching rate threshold value, if so, executing a step S53, otherwise, ending;
s53, taking a pair of crossing passing vehicles corresponding to the maximum value of the vehicle information matching rate as a pair of matched vehicles, adding 1 to the vehicle matching number, and then executing the step S54;
s54, eliminating all vehicle information matching rates corresponding to the matched vehicles from the current matching rate set to obtain a new matching rate set, then judging whether vehicle information matching rates exist in the new matching rate set, if so, returning to execute the step S51, and otherwise, ending.
6. The multi-channel violation vehicle recording method of claim 5 wherein after passing the pair of intersection passing vehicles corresponding to the maximum value of vehicle information matching rate as a pair of matching vehicles, the method further comprises:
taking the license plate number, the number of the passing lane, the vehicle type and the vehicle color which correspond to the pair of matched vehicles and are in the first vehicle information as verification data corresponding to the video data;
and importing the video data and the verification data into the vehicle information identification model for training to obtain a new vehicle information identification model.
7. The multi-channel violation vehicle recording method as recited in claim 1 wherein recording said video data comprises:
marking vehicles passing through the road junction which are not successfully matched in the video images of the video data to obtain new video images;
storing the new video image in a database.
8. A multi-channel violation vehicle recording device based on a radio frequency video all-in-one machine is characterized by comprising a data information acquisition unit, a vehicle information identification unit, a matching rate calculation unit, a matching rate summarizing unit, a matching number determination unit and a violation vehicle judgment unit;
the data information acquisition unit is used for acquiring video data and first vehicle information which are acquired in the same unit period, wherein the video data are acquired by a camera module in a radio frequency video all-in-one machine, the radio frequency video all-in-one machine is arranged at a multi-lane intersection, the first vehicle information is acquired by data interaction between a radio frequency module in the radio frequency video all-in-one machine and an electronic license plate of a vehicle passing through the intersection, the vehicle passing through the intersection is a vehicle passing through the multi-lane intersection, and the first vehicle information comprises at least one license plate number of the vehicle passing through the intersection, the number of the passing lane, the type of the vehicle and the color of the vehicle;
the vehicle information identification unit is in communication connection with the data information acquisition unit and is used for importing the video data into a vehicle information identification model which is based on a target detection algorithm and is trained in advance and outputting to obtain second vehicle information, wherein the second vehicle information comprises at least one license plate number of a vehicle passing through the intersection, a number of a lane passing through the intersection, a vehicle type and a vehicle color;
the matching rate calculation unit is respectively in communication connection with the data information acquisition unit and the vehicle information identification unit, and is used for traversing vehicles passing through the intersection in the first vehicle information and vehicles passing through the intersection in the second vehicle information, and calculating to obtain a vehicle information matching rate:
wherein i and j are positive integers respectively, VM ij A vehicle information matching rate, η, representing a vehicle passing through an ith intersection in the first vehicle information and a vehicle passing through a jth intersection in the second vehicle information LP Representing a predetermined weight coefficient, LP, corresponding to the license plate number ij Representing the matching rate, eta, of the number plate of the vehicle passing through the ith intersection and the vehicle passing through the jth intersection CL Representing a preset weight coefficient, CL, corresponding to the number of the passing lane ij Represents the matching rate of the passing lane number of the vehicle passing through the ith intersection and the passing vehicle passing through the jth intersection, eta VT Indicating a preset weight coefficient, VT, corresponding to the type of vehicle ij Representing a vehicle type matching rate, eta, of a vehicle passing through the ith intersection and a vehicle passing through the jth intersection VC Indicating a preset weight coefficient, VC, corresponding to the color of the vehicle ij Representing a vehicle color matching rate of a vehicle passing through the ith intersection with a vehicle passing through the jth intersection;
the matching rate summarizing unit is in communication connection with the matching rate calculating unit and is used for summarizing all the vehicle information matching rates to obtain a matching rate set;
the matching number determining unit is in communication connection with the matching rate summarizing unit and is used for determining the matching number of the vehicles according to the matching rate set;
the violation vehicle judging unit is in communication connection with the matching number determining unit and is used for judging whether a violation vehicle passes through the multi-lane intersection in the same unit period or not according to the comparison result of the vehicle matching number and the number of the vehicles passing through the intersection in the first vehicle information and the second vehicle information, if so, the video data is recorded, otherwise, the video data is not recorded, wherein the violation vehicle is a fake-plate vehicle, a license plate sheltered vehicle or a license plate-free vehicle.
9. A computer device comprising a memory, a processor and a transceiver communicatively connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to transmit and receive messages, and the processor is configured to read the computer program and perform the multi-channel violation vehicle recording method of any of claims 1-7.
10. A computer readable storage medium having stored thereon instructions which, when executed on a computer, perform the multi-channel violation vehicle recording method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210994319.5A CN115359665A (en) | 2022-08-17 | 2022-08-17 | Multichannel violation vehicle recording method and device based on radio frequency video all-in-one machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210994319.5A CN115359665A (en) | 2022-08-17 | 2022-08-17 | Multichannel violation vehicle recording method and device based on radio frequency video all-in-one machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115359665A true CN115359665A (en) | 2022-11-18 |
Family
ID=84002836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210994319.5A Pending CN115359665A (en) | 2022-08-17 | 2022-08-17 | Multichannel violation vehicle recording method and device based on radio frequency video all-in-one machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115359665A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116721552A (en) * | 2023-06-12 | 2023-09-08 | 北京博宏科元信息科技有限公司 | Non-motor vehicle overspeed identification recording method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798334A (en) * | 2017-08-25 | 2018-03-13 | 天津中兴智联科技有限公司 | A kind of matching process and device of vehicle electron identifying data and video identification data |
| CN108596119A (en) * | 2018-04-28 | 2018-09-28 | 江苏本能科技有限公司 | Radio frequency identification and video identification matching process and system, equipment, storage medium |
| CN111666853A (en) * | 2020-05-28 | 2020-09-15 | 平安科技（深圳）有限公司 | Real-time vehicle violation detection method, device, equipment and storage medium |
| CN112712706A (en) * | 2020-12-23 | 2021-04-27 | 高新兴智联科技有限公司 | License plate recognition method |
-
2022
- 2022-08-17 CN CN202210994319.5A patent/CN115359665A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798334A (en) * | 2017-08-25 | 2018-03-13 | 天津中兴智联科技有限公司 | A kind of matching process and device of vehicle electron identifying data and video identification data |
| CN108596119A (en) * | 2018-04-28 | 2018-09-28 | 江苏本能科技有限公司 | Radio frequency identification and video identification matching process and system, equipment, storage medium |
| CN111666853A (en) * | 2020-05-28 | 2020-09-15 | 平安科技（深圳）有限公司 | Real-time vehicle violation detection method, device, equipment and storage medium |
| CN112712706A (en) * | 2020-12-23 | 2021-04-27 | 高新兴智联科技有限公司 | License plate recognition method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116721552A (en) * | 2023-06-12 | 2023-09-08 | 北京博宏科元信息科技有限公司 | Non-motor vehicle overspeed identification recording method, device, equipment and storage medium |
| CN116721552B (en) * | 2023-06-12 | 2024-05-14 | 北京博宏科元信息科技有限公司 | Non-motor vehicle overspeed identification recording method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245579B (en) | People flow density prediction method and device, computer equipment and readable medium | |
| EP3806064A1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| WO2021139191A1 (en) | Method for data labeling and apparatus for data labeling | |
| CN109740479A (en) | A kind of vehicle recognition methods, device, equipment and readable storage medium storing program for executing again | |
| WO2023273344A1 (en) | Vehicle line crossing recognition method and apparatus, electronic device, and storage medium | |
| WO2021169174A1 (en) | Road congestion degree prediction method, apparatus, computer device, and readable storage medium | |
| CN115063589A (en) | Knowledge distillation-based vehicle component segmentation method and related equipment | |
| CN110889388A (en) | Violation identification method, device, equipment and storage medium | |
| CN115359665A (en) | Multichannel violation vehicle recording method and device based on radio frequency video all-in-one machine | |
| CN110363193B (en) | Vehicle weight recognition method, device, equipment and computer storage medium | |
| CN116721552B (en) | Non-motor vehicle overspeed identification recording method, device, equipment and storage medium | |
| CN112966687B (en) | Image segmentation model training method and device and communication equipment | |
| CN114005120A (en) | License plate character cutting method, license plate recognition method, device, equipment and storage medium | |
| CN112101302B (en) | Illegal poster detection method and system and electronic equipment | |
| CN110704650B (en) | OTA picture tag identification method, electronic equipment and medium | |
| CN115757987B (en) | Method, device, equipment and medium for determining companion object based on track analysis | |
| CN115131826B (en) | Article detection and identification method, and network model training method and device | |
| US20220309763A1 (en) | Method for identifying traffic light, device, cloud control platform and vehicle-road coordination system | |
| CN112989869B (en) | Optimization method, device, equipment and storage medium of face quality detection model | |
| CN111639640B (en) | License plate recognition method, device and equipment based on artificial intelligence | |
| Lin et al. | Realtime Vehicle Tracking Method Based on YOLOv5+ DeepSORT | |
| CN116052220B (en) | Pedestrian re-identification method, device, equipment and medium | |
| CN117574179B (en) | Method and device for constructing multi-task learning model | |
| CN113295181B (en) | Vehicle path planning method, device and system | |
| CN114943865B (en) | Target detection sample optimization method based on artificial intelligence and related equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221118 |