CN113158721A - Vehicle fake plate identification method, device, equipment and storage medium - Google Patents
Vehicle fake plate identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113158721A CN113158721A CN202011490055.7A CN202011490055A CN113158721A CN 113158721 A CN113158721 A CN 113158721A CN 202011490055 A CN202011490055 A CN 202011490055A CN 113158721 A CN113158721 A CN 113158721A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- license plate
- face
- fake
- plate number
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- 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
Abstract
The invention relates to a method, a device, equipment and a storage medium for identifying a vehicle fake plate. The method comprises the following steps: acquiring high-definition scene graphs of all vehicles passing through the passing equipment; carrying out face recognition on the high-definition scene image to obtain a character string representing the face characteristics; carrying out vehicle identification on the high-definition scene graph to obtain the license plate number of the vehicle in the high-definition scene graph; associating the character strings with the license plate numbers to obtain a face vehicle relation table; and filtering the spatiotemporal relationship of the face vehicle relationship table to obtain the associated data of a plurality of character strings corresponding to the same license plate number, and determining that the vehicles in the associated data have fake-licensed vehicles. According to the method, the main driving face and the vehicle are photographed for correlation, and the temporal-spatial relationship is filtered and analyzed to determine whether the fake-licensed vehicle exists, so that the identification accuracy and efficiency of the fake-licensed vehicle are greatly improved.
Description
Technical Field
The invention relates to the technical field of vehicle identification, in particular to a method, a device, equipment and a storage medium for identifying a vehicle fake plate.
Background
Along with the rapid growth of economy in China, the living standard of people is remarkably improved, motor vehicles are more and more popularized, and more illegal behaviors of vehicles bring a plurality of challenges to security management departments. Because the fake-licensed vehicles are difficult to find and high in detection difficulty, a plurality of cases causing trouble escape are fake-licensed vehicles, and difficulty is increased for detecting the cases. With the continuous development of artificial intelligence technology in recent years, the technologies of license plate recognition, face clustering and the like are more mature, and the accuracy of the technologies of license plate recognition, face clustering and the like is higher and higher.
The current mainstream fake-licensed vehicles are found mainly by analyzing and recognizing vehicle pictures at urban gates, recording the time difference of vehicles with the same license plate color and license plate number appearing at different gates, screening according to the positions of the gates, and screening out vehicle data exceeding the time difference to obtain fake-licensed vehicles. The current fake-licensed vehicle discovery model mainly depends on license plate recognition, but the license plate recognition is related to factors such as illumination, angle and the like, and the colors and recognition accuracy of the license plates are different under different illumination conditions, so that the result of the fake-licensed vehicle analyzed by the fake-licensed vehicle is easy to be inaccurate; meanwhile, the current fake-licensed vehicle discovery model is calculated by depending on big data, but the vehicle passing record of a second-line city is at least about 2000 ten thousand per day, the space-time relation filtering of 2000 ten thousand of passing data is needed, and a certain time is consumed. Moreover, the current fake-licensed vehicle discovery model needs to filter the space-time relationship of the total number of passing vehicles, and more computing resources are consumed.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a device and a storage medium for identifying a vehicle fake plate, which overcome the disadvantages of the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method of identifying a vehicle fake-license, comprising:
acquiring high-definition scene graphs of all vehicles passing through the passing equipment;
carrying out face recognition on the high-definition scene image to obtain a character string representing face characteristics;
carrying out vehicle identification on the high-definition scene graph to obtain the license plate number of the vehicle in the high-definition scene graph;
associating the character string with the license plate number to obtain a face vehicle relation table;
and filtering the spatiotemporal relationship of the face vehicle relationship table to obtain associated data of a plurality of character strings corresponding to the same license plate number, and determining whether the vehicles in the associated data are fake-licensed vehicles.
Optionally, the performing face recognition on the high-definition scene graph to obtain a character string representing a face feature includes:
carrying out face structuralization processing on the high-definition scene image, and detecting a main driving face of the vehicle in the high-definition scene image;
extracting the characteristics of the main driving face to obtain a binary characteristic value;
and clustering and archiving the characteristic values through a clustering algorithm to obtain the character string representing the human face characteristics.
Optionally, the performing vehicle identification on the high-definition scene graph to obtain the license plate number of the vehicle in the high-definition scene graph includes:
carrying out vehicle structurization on the high-definition scene graph, and detecting a vehicle in the high-definition scene graph;
and identifying the vehicle by using a vehicle algorithm to obtain a license plate number.
Optionally, the face-vehicle relationship table includes: the method comprises the following steps of (1) character strings, license plate numbers, passing equipment, passing time and equipment longitude and latitude;
the filtering of the spatiotemporal relationship of the face vehicle relationship table to obtain the associated data of a plurality of character strings corresponding to the same license plate number and determine that the vehicles in the associated data have fake-licensed vehicles comprises the following steps:
calling the face-vehicle relation table, and judging whether the same license plate number corresponds to a plurality of character strings;
if the same license plate number corresponds to a plurality of character strings, screening out all face vehicle relation data of the same license plate number corresponding to the plurality of character strings as initial association data;
grouping the initial associated data according to the passage time and the character string;
reading data corresponding to two vehicle character strings of which the passing time is different by set time in each character string as associated data;
reading the passing equipment corresponding to the two pieces of associated data;
calculating the device distance between the communication devices according to the longitude and latitude of the devices;
reading the pass time in the two pieces of associated data to calculate a pass time difference;
judging whether the equipment distance and the communication time difference meet preset standards or not;
if not, reading and outputting the license plate number in the associated data; the license plate number corresponds to a vehicle and a fake-licensed vehicle exists.
Optionally, the character string includes:
the system comprises a video identity coding zone bit, a standard administrative region code, a target type identification code and a personnel identification code.
Optionally, the acquiring the high-definition scene graphs of all vehicles passing through the passing device includes:
receiving the high-definition scene graph extracted by the face snapshot camera at the vehicle buckle;
or, receiving the image shot by the camera with the set specification; cutting the image to obtain the high-definition scene graph; the camera with the set specification does not comprise the face snapshot camera.
A vehicle fake-license identifying device, comprising:
the scene graph acquisition module is used for acquiring high-definition scene graphs of all vehicles passing through the passing equipment;
the face recognition module is used for carrying out face recognition on the high-definition scene image to obtain a character string representing the face characteristics;
the vehicle identification module is used for carrying out vehicle identification on the high-definition scene graph to obtain the license plate number of the vehicle in the high-definition scene graph;
the vehicle face association module is used for associating the character string with the license plate number to obtain a face vehicle relation table;
and the fake-licensed vehicle determining module is used for filtering the spatiotemporal relationship of the face vehicle relationship table to obtain associated data of a plurality of character strings corresponding to the same license plate number, and determining that the fake-licensed vehicles exist in the vehicles in the associated data.
Optionally, the face-vehicle relationship table includes: the method comprises the following steps of (1) character strings, license plate numbers, passing equipment, passing time and equipment longitude and latitude;
the fake-licensed vehicle determination module comprising:
the first judgment unit is used for calling the face vehicle relation table and judging whether a plurality of character strings corresponding to the same license plate number exist or not;
the initial association data screening unit is used for screening all the face vehicle relationship data of which the same license plate number corresponds to a plurality of character strings as initial association data if the same license plate number corresponds to the plurality of character strings;
an initial associated data grouping unit, configured to group the initial associated data according to the passage time and the character string;
the associated data reading unit is used for reading data corresponding to two vehicle character strings of which the passing time is different by set time in each character string as associated data;
the passing device exclusive unit is used for reading the passing devices corresponding to the two pieces of associated data;
the device distance calculating unit is used for calculating the device distance between the communication devices according to the latitude and longitude of the devices;
a passing time difference reading unit for reading the passing time in the two pieces of associated data to calculate a passing time difference;
a second judging unit, configured to judge whether the device distance and the communication time difference satisfy preset criteria;
the fake-licensed vehicle determining unit is used for reading and outputting the license plate number in the associated data if the fake-licensed vehicle determining unit does not meet the license plate number; the license plate number corresponds to a vehicle and a fake-licensed vehicle exists.
An identification device for a vehicle fake-license plate, comprising:
a processor, and a memory coupled to the processor;
the memory is used for storing a computer program, and the computer program is at least used for executing the vehicle fake-license identification method;
the processor is used for calling and executing the computer program in the memory.
A storage medium storing a computer program which, when executed by a processor, carries out the steps of the method of identifying a vehicle fake-license plate as described above.
The technical scheme provided by the application can comprise the following beneficial effects:
the application discloses a vehicle fake plate identification method, which comprises the following steps: acquiring high-definition scene graphs of all vehicles passing through the passing equipment; carrying out face recognition on the high-definition scene image to obtain a character string representing face characteristics; carrying out vehicle identification on the high-definition scene graph to obtain the license plate number of the vehicle in the high-definition scene graph; associating the character string with the license plate number to obtain a face vehicle relation table; and filtering the spatiotemporal relationship of the face vehicle relationship table to obtain associated data of a plurality of character strings corresponding to the same license plate number, and determining whether the vehicles in the associated data are fake-licensed vehicles. In the method, the main driving face and the license plate number of the vehicle passing through the vehicle buckle are identified, the main driving face and the license plate are bound, and then the time-space relation of data in the face vehicle relation table is analyzed, so that whether the fake-licensed vehicle exists in the vehicle is determined. In the method, the fake-licensed vehicles can be obtained only by analyzing the bayonet data of the main driver and the auxiliary driver, and all vehicle passing data is not needed; the vehicle fake-license condition identification method has the advantages that the identification steps of the vehicle fake-license condition are simplified, the data scale in the identification process is greatly reduced, and the identification efficiency of the vehicle fake-license condition is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for identifying a vehicle fake-license plate according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for spatiotemporal relationship filtering of a relationship table of a human face and a vehicle according to an embodiment of the present invention;
FIG. 3 is a block diagram of an apparatus for identifying a vehicle fake-license plate according to an embodiment of the present invention;
FIG. 4 is a block diagram of a vehicle fake-license plate identification device according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a character string format representing human face features according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
Fig. 1 is a flowchart of a method for identifying a vehicle fake-license plate according to an embodiment of the present invention. Referring to fig. 1, a method for identifying a vehicle fake-license plate includes:
step 101: and acquiring high-definition scene graphs of all vehicles passing through the passing equipment. The acquired high-definition scene graph can be a high-definition scene graph of a vehicle extracted by a high-definition face snapshot machine at a vehicle bayonet or a high-definition scene graph of the vehicle obtained by cutting a shot picture of a common camera.
Step 102: and carrying out face recognition on the high-definition scene image to obtain a character string representing the face characteristics. After the high-definition scene image of the vehicle is obtained, recognizing the face in the high-definition scene image, firstly, carrying out face structurization on the high-definition scene image, and detecting the main driving face of the vehicle in the image; then, extracting the characteristics of the main driving face to obtain a binary characteristic value; and clustering and filing the characteristic values of the human faces through a clustering algorithm, filing the human face characteristics of the same person together, and obtaining a character string VID representing the human face characteristics.
The specific form of the character string in the above embodiment is shown in fig. 5. Fig. 5 is a schematic diagram of a character string format representing human face features according to an embodiment of the present invention. Wherein, the 1 st bit code represents: and the video identity coding zone bit is used for distinguishing other codes. "V" in the above-described coding.
Bits 2-11 encode: the method follows the definition of the standard administrative region code of China and is accurate to villages (communities). "5301030101" in the above-mentioned encoding.
Bit 12 encoding represents: default 1, representing face cluster analysis. Such as "1" in the above coding.
Bits 13-20 encode: the system reserves 8-bit codes, maximally supports 1 hundred million data volume, and indicates that the newly-appeared people in each region can maximally reach 1 hundred million, so as to meet the needs of face clustering under various domestic gathering scenes. "00000001" in the above coding.
Step 103: and carrying out vehicle identification on the high-definition scene graph to obtain the license plate number of the vehicle in the high-definition scene graph. Firstly, vehicle structuring is carried out on a high-definition scene graph, vehicles in the graph are detected, and then the license plate number and the license plate color of the vehicle are identified through a vehicle algorithm.
Step 104: and associating the character string with the license plate number to obtain a face vehicle relation table. And (3) associating the character string VID obtained in the step (102) with the license plate number and the license plate color obtained in the step (103) to obtain a relation table, wherein the relation table comprises VID, the license plate number, the license plate color, passing equipment, passing time, equipment longitude and latitude and the like.
Step 105: and filtering the spatiotemporal relationship of the face vehicle relationship table to obtain associated data of a plurality of character strings corresponding to the same license plate number, and determining whether the vehicles in the associated data are fake-licensed vehicles. Filtering the face-vehicle relationship table through a spatiotemporal relationship, grouping according to the license plate numbers, and screening data of a plurality of VID numbers corresponding to the same license plate number in a very short time (such as 1 hour) in the grouping; and screening out the license plate numbers meeting the conditions, wherein if one license plate number corresponds to a plurality of VID numbers, the license plate numbers contain fake-licensed vehicles.
In the method, the fake-licensed vehicles can be obtained only by analyzing the data of the bayonets of the main driver and the auxiliary driver, and all vehicle passing data is not needed; the analysis is carried out through the face clustering and the face and license plate association mode, and compared with the traditional fake-licensed car analysis which is carried out only according to the license plate, the analysis is more accurate.
For more detailed description of the implementation process of filtering the face-vehicle relationship table by using the spatiotemporal relationship to recognize the fake-licensed vehicle in the present application, the recognition process will now be discussed in detail, specifically referring to the following embodiments:
FIG. 2 is a flowchart of a spatiotemporal relationship filtering method for a relationship table of a human face and a vehicle according to an embodiment of the present invention. Referring to fig. 2, performing spatiotemporal relationship filtering on the face vehicle relationship table to obtain associated data of a plurality of character strings corresponding to the same license plate number, and determining that a fake-licensed vehicle exists in the vehicles in the associated data, includes:
step 201: and calling the face-vehicle relation table. The method and the device can acquire high-definition scene graphs of a plurality of vehicles passing through the passing equipment, and analyze the high-definition scene graphs to obtain a face vehicle relation table, wherein the high-definition scene graphs of the vehicles can be stored in the face vehicle relation table.
Step 202: and judging whether the same license plate number corresponds to a plurality of character strings. And identifying all data in the face-vehicle relation table, and determining whether a plurality of character strings corresponding to one license plate number exist. Specifically, the method comprises the following steps: the method comprises the steps of firstly selecting a license plate number, then traversing a face-to-face vehicle relation table by taking the license plate number as a basis, obtaining all character strings corresponding to the license plate number, then judging whether the obtained character strings are consistent, if so, representing that the condition that one license plate number corresponds to a plurality of character strings does not exist, otherwise, representing that one license plate number corresponds to a plurality of character strings.
Step 203: and if the same license plate number corresponds to a plurality of character strings, screening out the face and vehicle relation data of the plurality of character strings corresponding to the same license plate number as initial association data. And screening the relational data of a plurality of character strings corresponding to one license plate number to perform the following processing.
Step 204: and grouping the initial associated data according to the passage time and the character string. And grouping the screened face and vehicle data as initial associated data, and dividing the initial associated data into corresponding groups by taking the character strings as units according to the sequence of the passing time.
Step 205: and reading data corresponding to the two vehicle character strings with the difference of the passing time in each character string as associated data. And screening two groups with the closest transit time in each group divided into the thick character strings, and carrying out the next analysis.
Step 206: and reading the passing equipment corresponding to the two pieces of associated data.
Step 207: and calculating the equipment distance between the communication equipment according to the longitude and latitude of the equipment.
Step 208: and reading the transit time in the two pieces of associated data to calculate a transit time difference.
Step 209: and judging whether the equipment distance and the communication time difference meet preset standards. The specific setting of the preset standard is not fixed, and the setting is specifically carried out according to the road condition and the speed limit of the area. But the setting principle is that the setting of the preset standard is changed to meet the real situation and the traffic law. For example, the distance between two transit devices in 1 hour cannot exceed 120km, to ensure that a vehicle may pass through the two transit devices in 1 hour.
Step 210: if not, reading and outputting the license plate number in the associated data; the license plate number corresponds to a vehicle and a fake-licensed vehicle exists.
In the above embodiment, the implementation process of filtering the spatiotemporal relationship is described in detail, in the process, whether the vehicle is reasonable to run or not is determined according to the distance between the passing devices through which the vehicle passes and the time difference between the passing devices, and if the distance is not reasonable, the vehicle is determined to have a fake-licensed vehicle. In the method, the face of the main driver and the license plate of the vehicle are subjected to associated recognition, so that whether the same license plate is driven by multiple persons is determined, and if the same license plate is driven by multiple persons, whether the fake-licensed condition exists is further judged, so that the recognition efficiency and accuracy of the fake-licensed vehicle are greatly improved.
Corresponding to the identification method of the vehicle fake-licensed provided by the embodiment of the invention, the embodiment of the invention also provides an identification device of the vehicle fake-licensed. Please see the examples below.
Fig. 3 is a block diagram of an apparatus for identifying a vehicle fake-license plate according to an embodiment of the present invention. Referring to fig. 3, an apparatus for recognizing a vehicle fake-license plate includes:
the scene graph acquiring module 301 is configured to acquire high-definition scene graphs of all vehicles passing through the passing device.
And the face recognition module 302 is configured to perform face recognition on the high-definition scene graph to obtain a character string representing a face feature.
And the vehicle identification module 303 is configured to perform vehicle identification on the high-definition scene graph to obtain a license plate number of a vehicle in the high-definition scene graph.
And the vehicle face association module 304 is configured to associate the character string with the license plate number to obtain a face-vehicle relationship table. The face-vehicle relationship table includes: character string, license plate number, passing equipment, passing time and equipment longitude and latitude
The fake-licensed vehicle determining module 305 is configured to perform spatiotemporal relationship filtering on the face vehicle relationship table to obtain associated data of a plurality of character strings corresponding to the same license plate number, and determine that a fake-licensed vehicle exists in the vehicles in the associated data.
The fake-licensed vehicle determination module 305 specifically includes: the first judgment unit is used for calling the face vehicle relation table and judging whether a plurality of character strings corresponding to the same license plate number exist or not; the initial association data screening unit is used for screening all the face vehicle relationship data of which the same license plate number corresponds to a plurality of character strings as initial association data if the same license plate number corresponds to the plurality of character strings; an initial associated data grouping unit, configured to group the initial associated data according to the passage time and the character string; the associated data reading unit is used for reading data corresponding to two vehicle character strings of which the passing time is different by set time in each character string as associated data; the passing device exclusive unit is used for reading the passing devices corresponding to the two pieces of associated data; the device distance calculating unit is used for calculating the device distance between the communication devices according to the latitude and longitude of the devices; a passing time difference reading unit for reading the passing time in the two pieces of associated data to calculate a passing time difference; a second judging unit, configured to judge whether the device distance and the communication time difference satisfy preset criteria; the fake-licensed vehicle determining unit is used for reading and outputting the license plate number in the associated data if the fake-licensed vehicle determining unit does not meet the license plate number; the license plate number corresponds to a vehicle and a fake-licensed vehicle exists.
The face recognition module 302 is specifically configured to: carrying out face structuralization processing on the high-definition scene image, and detecting a main driving face of the vehicle in the high-definition scene image; extracting the characteristics of the main driving face to obtain a binary characteristic value; and clustering and archiving the characteristic values through a clustering algorithm to obtain the character string representing the human face characteristics.
The vehicle identification module 303 is specifically configured to: carrying out vehicle structurization on the high-definition scene graph, and detecting a vehicle in the high-definition scene graph; and identifying the vehicle by using a vehicle algorithm to obtain a license plate number.
In the device, the fake-licensed vehicles can be obtained only by analyzing the data of the bayonets of the main driver and the auxiliary driver, and all vehicle passing data is not needed; the method analyzes the vehicle through the face clustering and the face and license plate association, and is more accurate compared with the analysis of the traditional fake-licensed vehicle which only analyzes the vehicle according to the license plate; the current mainstream fake plate analysis model adopts a big data analysis mode, a high-performance CPU is needed, and a large number of servers are needed for city-level fake plate analysis.
In order to more clearly introduce a hardware system for implementing the embodiment of the invention, the embodiment of the invention also provides a vehicle fake plate identification device corresponding to the vehicle fake plate identification method provided by the embodiment of the invention. Please see the examples below.
Fig. 4 is a block diagram of an apparatus for identifying a vehicle fake-license plate according to an embodiment of the present invention. Referring to fig. 4, an apparatus for recognizing a vehicle fake-license plate includes:
a processor 401 and a memory 402 connected to the processor 401;
the memory 402 is used for storing a computer program at least for executing the vehicle fake-license plate identification method;
the processor 401 is used to call and execute the computer program in the memory 402.
Meanwhile, the application also discloses a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the vehicle fake plate identification method are realized.
The fake-licensed vehicles can be obtained only by analyzing the card data of the main driver and the auxiliary driver, and all vehicle passing data is not needed; the method analyzes the vehicle by means of face clustering and association of the faces and the license plates, and improves the identification precision of the vehicle fake-licensed compared with the traditional fake-licensed vehicle analysis which only analyzes the vehicle license plates.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A method of identifying a vehicle fake plate, comprising:
acquiring high-definition scene graphs of all vehicles passing through the passing equipment;
carrying out face recognition on the high-definition scene image to obtain a character string representing face characteristics;
carrying out vehicle identification on the high-definition scene graph to obtain the license plate number of the vehicle in the high-definition scene graph;
associating the character string with the license plate number to obtain a face vehicle relation table;
and filtering the spatiotemporal relationship of the face vehicle relationship table to obtain associated data of a plurality of character strings corresponding to the same license plate number, and determining whether the vehicles in the associated data are fake-licensed vehicles.
2. The method according to claim 1, wherein the performing face recognition on the high-definition scene graph to obtain a character string representing a face feature comprises:
carrying out face structuralization processing on the high-definition scene image, and detecting a main driving face of the vehicle in the high-definition scene image;
extracting the characteristics of the main driving face to obtain a binary characteristic value;
and clustering and archiving the characteristic values through a clustering algorithm to obtain the character string representing the human face characteristics.
3. The method of claim 1, wherein the performing vehicle identification on the high-definition scene graph to obtain a license plate number of a vehicle in the high-definition scene graph comprises:
carrying out vehicle structurization on the high-definition scene graph, and detecting a vehicle in the high-definition scene graph;
and identifying the vehicle by using a vehicle algorithm to obtain a license plate number.
4. The method of claim 1, wherein the face-to-vehicle relationship table comprises: the method comprises the following steps of (1) character strings, license plate numbers, passing equipment, passing time and equipment longitude and latitude;
the filtering of the spatiotemporal relationship of the face vehicle relationship table to obtain the associated data of a plurality of character strings corresponding to the same license plate number and determine that the vehicles in the associated data have fake-licensed vehicles comprises the following steps:
calling the face-vehicle relation table, and judging whether the same license plate number corresponds to a plurality of character strings;
if the same license plate number corresponds to a plurality of character strings, screening out all face vehicle relation data of the same license plate number corresponding to the plurality of character strings as initial association data;
grouping the initial associated data according to the passage time and the character string;
reading data corresponding to two vehicle character strings of which the passing time is different by set time in each character string as associated data;
reading the passing equipment corresponding to the two pieces of associated data;
calculating the device distance between the communication devices according to the longitude and latitude of the devices;
reading the pass time in the two pieces of associated data to calculate a pass time difference;
judging whether the equipment distance and the communication time difference meet preset standards or not;
if not, reading and outputting the license plate number in the associated data; the license plate number corresponds to a vehicle and a fake-licensed vehicle exists.
5. The method of claim 1, wherein the string comprises:
the system comprises a video identity coding zone bit, a standard administrative region code, a target type identification code and a personnel identification code.
6. The method of claim 1, wherein the obtaining a high-definition scene graph of all vehicles passing by a transit device comprises:
receiving the high-definition scene graph extracted by the face snapshot camera at the vehicle buckle;
or, receiving the image shot by the camera with the set specification; cutting the image to obtain the high-definition scene graph; the camera with the set specification does not comprise the face snapshot camera.
7. An apparatus for identifying a vehicle fake plate, comprising:
the scene graph acquisition module is used for acquiring high-definition scene graphs of all vehicles passing through the passing equipment;
the face recognition module is used for carrying out face recognition on the high-definition scene image to obtain a character string representing the face characteristics;
the vehicle identification module is used for carrying out vehicle identification on the high-definition scene graph to obtain the license plate number of the vehicle in the high-definition scene graph;
the vehicle face association module is used for associating the character string with the license plate number to obtain a face vehicle relation table;
and the fake-licensed vehicle determining module is used for filtering the spatiotemporal relationship of the face vehicle relationship table to obtain associated data of a plurality of character strings corresponding to the same license plate number, and determining that the fake-licensed vehicles exist in the vehicles in the associated data.
8. The apparatus of claim 7, wherein the face-to-vehicle relationship table comprises: the method comprises the following steps of (1) character strings, license plate numbers, passing equipment, passing time and equipment longitude and latitude;
the fake-licensed vehicle determination module comprising:
the first judgment unit is used for calling the face vehicle relation table and judging whether a plurality of character strings corresponding to the same license plate number exist or not;
the initial association data screening unit is used for screening all the face vehicle relationship data of which the same license plate number corresponds to a plurality of character strings as initial association data if the same license plate number corresponds to the plurality of character strings;
an initial associated data grouping unit, configured to group the initial associated data according to the passage time and the character string;
the associated data reading unit is used for reading data corresponding to two vehicle character strings of which the passing time is different by set time in each character string as associated data;
the passing device exclusive unit is used for reading the passing devices corresponding to the two pieces of associated data;
the device distance calculating unit is used for calculating the device distance between the communication devices according to the latitude and longitude of the devices;
a passing time difference reading unit for reading the passing time in the two pieces of associated data to calculate a passing time difference;
a second judging unit, configured to judge whether the device distance and the communication time difference satisfy preset criteria;
the fake-licensed vehicle determining unit is used for reading and outputting the license plate number in the associated data if the fake-licensed vehicle determining unit does not meet the license plate number; the license plate number corresponds to a vehicle and a fake-licensed vehicle exists.
9. An apparatus for identifying a vehicle fake plate, comprising:
a processor, and a memory coupled to the processor;
the memory is configured to store a computer program for performing at least the method of identifying a vehicle deck according to any one of claims 1 to 6;
the processor is used for calling and executing the computer program in the memory.
10. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the steps of the method of identifying a vehicle deck according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011490055.7A CN113158721A (en) | 2020-12-16 | 2020-12-16 | Vehicle fake plate identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011490055.7A CN113158721A (en) | 2020-12-16 | 2020-12-16 | Vehicle fake plate identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113158721A true CN113158721A (en) | 2021-07-23 |
Family
ID=76882598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011490055.7A Pending CN113158721A (en) | 2020-12-16 | 2020-12-16 | Vehicle fake plate identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158721A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103578277A (en) * | 2012-08-07 | 2014-02-12 | 上海弘视通信技术有限公司 | Method and device for searching fake plate suspicion vehicle |
| CN107967806A (en) * | 2017-12-01 | 2018-04-27 | 深圳云天励飞技术有限公司 | Vehicle fake-license detection method, device, readable storage medium storing program for executing and electronic equipment |
| CN108230684A (en) * | 2016-12-21 | 2018-06-29 | 杭州海康威视数字技术股份有限公司 | Detection method of license plate and device |
| CN110765134A (en) * | 2019-10-25 | 2020-02-07 | 四川东方网力科技有限公司 | File establishing method, equipment and storage medium |
-
2020
- 2020-12-16 CN CN202011490055.7A patent/CN113158721A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103578277A (en) * | 2012-08-07 | 2014-02-12 | 上海弘视通信技术有限公司 | Method and device for searching fake plate suspicion vehicle |
| CN108230684A (en) * | 2016-12-21 | 2018-06-29 | 杭州海康威视数字技术股份有限公司 | Detection method of license plate and device |
| CN107967806A (en) * | 2017-12-01 | 2018-04-27 | 深圳云天励飞技术有限公司 | Vehicle fake-license detection method, device, readable storage medium storing program for executing and electronic equipment |
| CN110765134A (en) * | 2019-10-25 | 2020-02-07 | 四川东方网力科技有限公司 | File establishing method, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3493101B1 (en) | Image recognition method, terminal, and nonvolatile storage medium | |
| WO2020173022A1 (en) | Vehicle violation identifying method, server and storage medium | |
| CN105320923B (en) | Model recognizing method and device | |
| CN108921083B (en) | Illegal mobile vendor identification method based on deep learning target detection | |
| CN108197544B (en) | Face analysis method, face filtering method, face analysis device, face filtering device, embedded equipment, medium and integrated circuit | |
| CN105426903A (en) | Cloud determination method and system for remote sensing satellite images | |
| CN109871780B (en) | Face quality judgment method and system and face identification method and system | |
| CN106022285A (en) | Vehicle type identification method and vehicle type identification device based on convolutional neural network | |
| CN104166841A (en) | Rapid detection identification method for specified pedestrian or vehicle in video monitoring network | |
| CN110163109B (en) | Lane line marking method and device | |
| CN104978567A (en) | Vehicle detection method based on scenario classification | |
| CN109948616A (en) | Image detecting method, device, electronic equipment and computer readable storage medium | |
| CN107590500A (en) | A kind of color recognizing for vehicle id method and device based on color projection classification | |
| CN111627215A (en) | Video image identification method based on artificial intelligence and related equipment | |
| CN106156777A (en) | Textual image detection method and device | |
| Azad et al. | New method for optimization of license plate recognition system with use of edge detection and connected component | |
| CN111753642B (en) | Method and device for determining key frame | |
| CN110674887A (en) | End-to-end road congestion detection algorithm based on video classification | |
| CN106778765B (en) | License plate recognition method and device | |
| Ciuntu et al. | Real-time traffic sign detection and classification using machine learning and optical character recognition | |
| CN114519689A (en) | Image tampering detection method, device, equipment and computer readable storage medium | |
| CN113158721A (en) | Vehicle fake plate identification method, device, equipment and storage medium | |
| CN112633163B (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm | |
| CN104077566B (en) | Bayonet socket picture method for detecting human face based on color difference | |
| CN114155576A (en) | Image processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210723 |
|
| WD01 | Invention patent application deemed withdrawn after publication |