CN112861797A - Method and device for identifying authenticity of license plate and related equipment - Google Patents
Method and device for identifying authenticity of license plate and related equipment Download PDFInfo
- Publication number
- CN112861797A CN112861797A CN202110270333.6A CN202110270333A CN112861797A CN 112861797 A CN112861797 A CN 112861797A CN 202110270333 A CN202110270333 A CN 202110270333A CN 112861797 A CN112861797 A CN 112861797A
- Authority
- CN
- China
- Prior art keywords
- license plate
- vehicle
- license
- real
- judging whether
- 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 59
- 230000001174 ascending effect Effects 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 30
- 230000008859 change Effects 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 11
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000013135 deep learning Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000004888 barrier function Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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 application discloses a method for identifying true and false license plates, which comprises the steps of obtaining a vehicle image sequence; detecting license plates of all vehicle images in the vehicle image sequence to obtain license plate coordinates and license plate sizes of target license plates; judging whether the license plate motion trail accords with the real license plate motion trail or not according to each license plate coordinate; if the real license plate motion trail is met, judging whether the size of each license plate is in an increasing sequence; if the number of the target license plate is in the ascending sequence, determining that the target license plate is a real license plate; the method for identifying the true and false license plate can more effectively improve the accuracy of the true and false license plate identification result. The application also discloses a device and a system for identifying the authenticity of the license plate and a computer readable storage medium, which have the beneficial effects.
Description
Technical Field
The application relates to the technical field of computer vision, in particular to a method for identifying true and false license plates, and further relates to a device and a system for identifying true and false license plates and a computer readable storage medium.
Background
With the continuous development of technologies such as big data and deep learning, the intelligent traffic system gradually replaces the traditional human labor and becomes the mainstream system of the current traffic supervision. The automatic charging is started in the occasions such as the entrance and the exit of a parking lot, the entrance and the exit of a community and the like, and one intelligent camera can complete the complicated operations such as timing, charging and the like, thereby greatly facilitating the life of people. However, some people try to confuse false license plates such as printed or even copied license plates shot by using mobile phones for personal privity, so that not only is the property of other people seriously lost, but also a lot of adverse effects are caused to vehicle management. In order to solve the problem, a displacement calculation method is adopted in the related technology to judge the authenticity of the license plate, but the implementation mode has the defects of poor robustness and low accuracy.
Therefore, how to more effectively improve the accuracy of the identification result of the genuine-fake license plate is a problem to be solved urgently by the technical staff in the field.
Disclosure of Invention
The method can effectively improve the accuracy of the identification result of the real and false license plate; another object of the present application is to provide an apparatus, a system and a computer readable storage medium for identifying authenticity of a license plate, which also have the above-mentioned advantages.
In a first aspect, the present application provides a method for identifying an authentic vehicle license plate, including:
acquiring a vehicle image sequence;
detecting license plates of all vehicle images in the vehicle image sequence to obtain license plate coordinates and license plate sizes of target license plates;
judging whether the license plate motion trail accords with the real license plate motion trail or not according to each license plate coordinate;
if the real license plate motion trail is met, judging whether the size of each license plate is in an increasing sequence;
and if the number of the target license plate is in the ascending sequence, determining that the target license plate is the real license plate.
Preferably, the acquiring the vehicle image sequence includes:
collecting a video stream, and judging whether a video image in the video stream has a vehicle characteristic or not;
when the vehicle feature is present in the video image, the sequence of vehicle images is extracted from the video stream.
Preferably, the determining whether the video image in the video stream has the vehicle feature includes:
collecting the current light intensity;
if the current light intensity exceeds a preset threshold value, judging whether a vehicle head feature exists in the video image, and if so, determining that the vehicle feature exists in the video image;
if the current light intensity does not exceed the preset threshold value, judging whether the video image has the car light characteristics, and if so, determining that the video image has the car characteristics.
Preferably, the extracting the vehicle image sequence from the video stream when the vehicle feature exists in the video image includes:
when the number of the vehicle images with the vehicle characteristics in the video stream exceeds a preset number, extracting the vehicle image sequence from the video stream.
Preferably, the determining whether the license plate motion trajectory conforms to the real license plate motion trajectory according to each license plate coordinate includes:
determining license plate coordinate change conditions according to the real license plate motion trail;
judging whether each license plate coordinate meets the license plate coordinate change condition;
if so, determining that the license plate motion track conforms to the real license plate motion track.
Preferably, the determining whether the sizes of the license plates are in an increasing order includes:
determining the license plate height and the license plate width of the target license plate according to the license plate size;
and judging whether the height of the license plate and the width of the license plate are in an increasing order.
Preferably, the method for identifying the authenticity of the license plate further comprises the following steps:
and when the license plate motion trail does not accord with the real license plate motion trail or the sizes of the license plates are not in an increasing sequence, determining that the target license plate is a false license plate, and outputting an alarm prompt.
In a second aspect, the present application further discloses an apparatus for recognizing true and false license plates, including:
the image sequence acquisition module is used for acquiring a vehicle image sequence;
the target license plate detection module is used for detecting license plates of all vehicle images in the vehicle image sequence to obtain license plate coordinates and license plate sizes of target license plates;
the license plate track judging module is used for judging whether the license plate motion track conforms to the real license plate motion track or not according to the license plate coordinates;
the license plate size judging module is used for judging whether the sizes of the license plates are in an increasing sequence or not if the license plate motion trail accords with the real license plate motion trail;
and the real and false license plate judging module is used for determining that the target license plate is a real license plate if the sizes of the license plates are in an increasing sequence.
In a third aspect, the present application further discloses a system for identifying authenticity of a license plate, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of any of the above-mentioned methods for authenticating license plates.
In a fourth aspect, the present application further discloses a computer-readable storage medium, in which a computer program is stored, and the computer program is used to implement any of the steps of the method for identifying an authentic and counterfeit license plate when being executed by a processor.
The method for identifying the authenticity of the license plate comprises the steps of obtaining a vehicle image sequence; detecting license plates of all vehicle images in the vehicle image sequence to obtain license plate coordinates and license plate sizes of target license plates; judging whether the license plate motion trail accords with the real license plate motion trail or not according to each license plate coordinate; if the real license plate motion trail is met, judging whether the size of each license plate is in an increasing sequence; and if the number of the target license plate is in the ascending sequence, determining that the target license plate is the real license plate.
Therefore, the method for identifying the true and false license plates realizes true and false license plate identification according to the license plate motion trail and the license plate size change in the vehicle running process, when a vehicle image sequence is obtained, a target license plate in an image is firstly detected and determined, then the motion trail and the size change of the target license plate are judged, when the motion trail of the target license plate meets the motion trail of the real license plate and the size of the license plate is changed in an increasing mode, the target license plate can be determined to be the real license plate, the accuracy of the true and false license plate identification result is effectively improved, and great convenience is provided for vehicle management.
The authenticity vehicle license plate recognition device, the authenticity vehicle license plate recognition system and the computer readable storage medium have the beneficial effects and are not repeated herein.
Drawings
In order to more clearly illustrate the technical solutions in the prior art and the embodiments of the present application, the drawings that are needed to be used in the description of the prior art and the embodiments of the present application will be briefly described below. Of course, the following description of the drawings related to the embodiments of the present application is only a part of the embodiments of the present application, and it will be obvious to those skilled in the art that other drawings can be obtained from the provided drawings without any creative effort, and the obtained other drawings also belong to the protection scope of the present application.
Fig. 1 is a schematic flow chart of a method for identifying authenticity of a license plate provided by the present application;
fig. 2 is a schematic structural diagram of an authenticity license plate recognition system provided by the present application;
fig. 3 is a schematic flow chart of another method for identifying an authentic license plate provided in the present application;
fig. 4 is a schematic structural diagram of an apparatus for recognizing authenticity of a license plate provided in the present application;
fig. 5 is a schematic structural diagram of an authenticity license plate recognition system provided by the present application.
Detailed Description
The core of the application is to provide the method for identifying the true and false license plate, and the method for identifying the true and false license plate can be used for more effectively improving the accuracy of the true and false license plate identification result; another core of the present application is to provide an apparatus, a system and a computer readable storage medium for identifying authenticity of a license plate, which also have the above-mentioned advantages.
In order to more clearly and completely describe the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for identifying an authentic license plate provided in the present application, where the method includes:
s101: acquiring a vehicle image sequence;
this step is intended to enable the acquisition of a sequence of images of the vehicle, which is a sequence of images containing information of the vehicle, which can be extracted from the video stream acquired by the image acquisition device. Specifically, for the image capturing device, when the image capturing device is in a working state, image capturing should be in real time, but for a video stream without vehicle entering or exiting, license plate detection is not required, so that real-time video frame detection can be performed on the video stream captured by the image capturing device, and a video frame without vehicle information is ignored to obtain a vehicle image sequence with vehicle information.
It is understood that the vehicle image sequence may be a continuous video frame or a video frame separated by a preset number of frames, for example, when vehicle information is detected in the video stream, the vehicle image starts to be captured, and the vehicle images are extracted every preset number of frames to form the vehicle image sequence. Of course, the specific value of the preset frame number is not unique, and the specific value is set by a technician according to the actual situation, which is not limited in the present application. Likewise, the specific number of vehicle images in the vehicle image sequence is not unique.
As a preferred embodiment, the acquiring the vehicle image sequence may include: collecting video streams, and judging whether the video images in the video streams have vehicle characteristics or not; when the vehicle features are present in the video images, a sequence of vehicle images is extracted from the video stream.
The preferred embodiment provides a method for acquiring a vehicle image sequence, which is realized by vehicle feature recognition. Specifically, a video stream is acquired through an image acquisition device, feature recognition is performed on each video image in the video stream, and when vehicle features exist in the video images, vehicle images can be extracted from the video stream to obtain a vehicle image sequence. The specific type of the vehicle feature is not exclusive, and for example, the vehicle feature may be a vehicle head feature, a vehicle light feature, a reflector feature, a tire feature, and the like, which is not limited in the present application.
As a preferred embodiment, the above determining whether the video image in the video stream has the vehicle feature may include: collecting the current light intensity; if the current light intensity exceeds a preset threshold value, judging whether the vehicle head characteristics exist in the video image, and if so, determining that the vehicle characteristics exist in the video image; if the current light intensity does not exceed the preset threshold value, judging whether the vehicle lamp characteristics exist in the video image, and if so, determining that the vehicle characteristics exist in the video image.
The present preferred embodiment provides a method of extracting vehicle features. Specifically, the light rays in the daytime and at night and the light rays in the sunny day and the cloudy day have great difference, and the difference can bring great influence to the extraction of the vehicle characteristics, so that the accuracy of the vehicle identification result is influenced, therefore, different vehicle characteristics can be extracted according to different light scenes, and more accurate identification of the true and false license plate is realized.
In a specific implementation process, the current light intensity can be collected by arranging a light sensor, and when the light intensity is weak, the car light can be used as an extracted image feature; when the light intensity is stronger, the vehicle head can be used as the extracted image feature, namely, for a night scene, the vehicle lamp feature can be collected from the video image, and for a daytime scene, the vehicle head feature can be collected from the video image, so that the judgment on whether the vehicle feature exists in the video image is realized. The light intensity threshold value can be preset as a standard for judging the light intensity, namely, the preset threshold value is set, of course, the value of the preset threshold value is not unique, and the preset threshold value can be set by a technician according to actual conditions, so that the application does not limit the preset threshold value.
As a preferred embodiment, the extracting the vehicle image sequence from the video stream when the vehicle feature exists in the video image may include: when the number of vehicle images with the vehicle characteristics in the video stream exceeds a preset number, extracting a vehicle image sequence from the video stream.
The preferred embodiment provides an implementation method for extracting a vehicle image sequence from a video stream, when a vehicle image with vehicle characteristics is detected to appear in the video stream, the number of frames appearing in the vehicle image is counted first, further, when the number of the vehicle images appearing in the video stream exceeds a preset number, the current vehicle can be determined to be a vehicle needing to pass through, license plate authenticity identification needs to be carried out on the vehicle, and at the moment, the vehicle image sequence is extracted from the video stream. The specific value of the preset number is not unique, and the technical personnel can set the value according to the actual situation, which is not limited in the application.
S102: detecting license plates of all vehicle images in the vehicle image sequence to obtain license plate coordinates and license plate sizes of target license plates;
the method comprises the steps of identifying license plate parameter information, wherein the license plate parameter information comprises license plate coordinates and license plate sizes. Firstly, license plate detection is carried out on each vehicle image in the vehicle image sequence, the process can be realized based on a target detection algorithm of deep learning, the specific realization process refers to the prior art, and the description is not repeated again in the application. Further, when detecting that the license plate information exists in the vehicle image, that is, the target license plate exists, the coordinate information and the size information of the target license plate can be obtained, wherein the coordinate information can be the coordinate of a certain point set on the target license plate, such as a central point, a corner point and the like; the size information may be the width and height of the target license plate.
S103: judging whether the license plate motion trail accords with the real license plate motion trail or not according to the license plate coordinates; if yes, executing S104; if not, executing S106;
the step aims to realize the judgment of the license plate motion trail, and specifically, the license plate motion trail of the current vehicle can be fitted by utilizing each license plate coordinate obtained based on the vehicle image sequence so as to determine whether the license plate motion trail accords with the real license plate motion trail. Generally speaking, in a scene of vehicle entrance and exit, all vehicle targets that want to enter a barrier gate move from far to near to a camera, so that a motion track of a license plate in a shot image should be a curve from top to bottom, the width and height of a license plate detection area both tend to increase gradually, and the motion tendency in the whole process is unchanged. Therefore, the authenticity of the license plate can be recognized by judging whether the license plate motion track conforms to the real license plate motion track, namely the motion curve.
As a preferred embodiment, the determining whether the license plate motion trajectory matches the real license plate motion trajectory according to the license plate coordinates may include: determining license plate coordinate change conditions according to the real license plate motion track; judging whether the coordinates of each license plate meet the change condition of the coordinates of the license plate; if so, determining that the license plate motion track conforms to the real license plate motion track.
The preferred embodiment provides a method for judging license plate motion trail, and specifically, license plate coordinate change conditions are determined according to real license plate motion trail, for example, in the process that a vehicle enters a barrier, the longitudinal coordinate changes of license plate coordinates are all in a descending trend, so that license plate motion trail judgment can be realized by judging whether each license plate coordinate meets the license plate coordinate condition or not.
S104: judging whether the sizes of the license plates are in an increasing order or not; if yes, executing S105; if not, executing S106;
the step aims to realize judgment of the change trend of the license plate size, and specifically judges whether the sizes of the license plates obtained based on the vehicle image sequence are in an increasing sequence. As described above, for a vehicle object that is about to enter the barrier gate, the width and height of the license plate detection area in the captured image should both have a gradually increasing trend, and the movement trend in the whole process is not changed, so that the license plate detection can be realized by judging whether the size of the license plate is in an increasing order.
As a preferred embodiment, the determining whether the sizes of the license plates are in an increasing order may include: determining the license plate height and the license plate width of a target license plate according to the license plate size; and judging whether the height and the width of the license plate are in an increasing order.
The preferred embodiment provides a method for judging the change trend of the size of a license plate, and particularly the size of the license plate can specifically comprise the height and the width of the license plate, so that the change trend of the size of the license plate can be judged by judging whether the change trends of the height and the width of the license plate are both increasing trends.
S105: determining that the target license plate is a real license plate;
s106: and determining the target license plate as a false license plate.
The steps aim at realizing the output of the identification result of the real and false license plate. Specifically, when the license plate motion trail of the current vehicle is determined to accord with the real license plate motion trail, and the size of the license plates in the vehicle image sequence is in the gradually increasing sequence, the target license plate can be determined to be the real license plate, otherwise, the target license plate can be determined to be the false license plate, and corresponding prompt information is output. In addition, for the condition that the target license plate is a false license plate, an alarm prompt can be further output to remind a vehicle manager to carry out supervision and investigation in time.
Therefore, the method for identifying the true and false license plates realizes true and false license plate identification according to the license plate motion trail and the license plate size change in the vehicle running process, when a vehicle image sequence is obtained, a target license plate in an image is firstly detected and determined, then the motion trail and the size change of the target license plate are judged, when the motion trail of the target license plate meets the motion trail of the real license plate and the size of the license plate is changed in an increasing mode, the target license plate can be determined to be the real license plate, the accuracy of the true and false license plate identification result is effectively improved, and great convenience is provided for vehicle management.
The embodiment of the application provides another authenticity vehicle license plate identification method.
Referring to fig. 2 and 3, fig. 2 is a schematic structural diagram of an authenticity license plate recognition system provided in the present application, where the authenticity license plate recognition system includes three modules: 1. a video image acquisition module; 2. a judging module for the true and false license plate; 3. a true and false license plate output module; fig. 3 is a schematic flow chart of another method for identifying an authentic license plate provided by the present application, which includes the following specific implementation flows:
1. the video image acquisition module:
a camera is installed in a vehicle entrance and exit scene, the camera faces the entrance direction, and the camera is used for acquiring each frame of data in the video scene in real time.
2. True and false license plate judging module:
in a scene of vehicle entrance and exit, all vehicle targets which want to enter a barrier gate move from far to near to a camera, the motion track of a license plate on an image is a curve from top to bottom, the width and the height of a detected region of the license plate are gradually increased, and the motion trend in the whole process is unchanged. However, when trying to enter an entrance and exit charging channel, common false license plates, such as license plates shot by a mobile phone, license plates printed by paper, imitated license plates and the like, on one hand, real vehicle running tracks cannot be simulated, on the other hand, the size of the false license plates is not obviously changed when the false license plates are shaken left and right, the false license plates are always suddenly changed when the false license plates move back and forth, and the size of the license plates cannot be changed in an incremental manner; second, even if someone intentionally mimics the motion of a real vehicle, there is no characteristic information of the vehicle itself. Therefore, based on these characteristics, this module uses three kinds of judgement strategies to distinguish the authenticity of license plate effectively, include: judging the motion track of the license plate, judging the size change trend of the license plate and judging the characteristics of the vehicle.
Firstly, when a vehicle enters a preset detection area, the license plate detection is started, specifically, a target detection algorithm based on deep learning can be adopted, and the detection rate and the positioning accuracy of the method are obviously superior to those of the traditional license plate detection method. Secondly, in the moving process of the vehicle, license plate detection is carried out at intervals of 5 frames, the position P (x, y, w, h) of the license plate detection is recorded, and a coordinate sequence with the length of 10 is set and maintained.
(1) Judging the motion trail of the license plate:
after the license plate sequence of the entrance and exit scene is obtained, the motion trail of the license plate is judged through the stored 10 frames of license plate position information, and quadratic curve fitting can be carried out on the motion trail of the license plate by adopting a curve fitting algorithm.
Specifically, a quadratic fitting function y ═ p (x) is given in advance, and the x coordinate x of the upper left corner of each license plate position in the license plate sequence is used1,x2,,,x10And its corresponding y coordinate y1,y2,,,y10Such that the formula is satisfied:
thereby obtaining the running track of the license plate.
In the entrance and exit scene, due to the particularity of the license plate motion track, the license plate moves from top to bottom on the image and moves to one direction, so that the license plate positions of three adjacent frames should meet the following conditions (the license plate coordinate change condition):
(xi+2-xi+1)*(xi+1-xi) > 0 and (p (x)i+2)＞p(xi+1)&&p(xi+1)＞p(xi))
Therefore, all coordinate information in the license plate sequence is substituted into the polynomial equation of the motion trail of the license plate, whether the positions of the adjacent three frames of license plates meet the preset conditions or not is sequentially judged, if not, the license plates are directly transferred to a false license plate output module, and otherwise, a license plate size change trend judgment part is entered.
(2) Judging the size change trend of the license plate:
in the entrance and exit scene, the real vehicle moves from far to near to the direction close to the camera, so the size of the license plate is gradually increased, while the size of the false license plate is always gradually decreased or not gradually increased. Therefore, the width and the height of the real license plate are gradually increased, namely the width w of the adjacent two frames of license plates in the license plate sequenceiAnd height hiThe following conditions should be satisfied:
wi+1＞wi&&hi+1＞hi
therefore, the width and the height of the license plates of two adjacent frames in the license plate sequence are sequentially compared, if the width and the height of the license plates of two adjacent frames in the license plate sequence do not meet the conditions, the license plates are switched to a false license plate output module, and if the width and the height of the license plates of two adjacent frames in the license plate sequence do not meet the.
(3) And (3) judging the characteristics of the vehicle:
the vehicle characteristic judgment means that the authenticity of the license plate is judged by judging whether the scene image contains the vehicle characteristics and whether the scene image meets the motion track similar to the license plate. And when the license plate is detected, feature extraction is carried out on the image, if a preset condition is met, a real vehicle exists in the scene, so that the current license plate is determined to be a real license plate, otherwise, the current license plate is determined to be a false license plate, and a judgment result is transmitted to a real and false license plate output module.
Because there is great difference in daytime and night scene, can carry out vehicle characteristic to two kinds of scenes respectively and detect:
A. day scene:
in a daytime scene, vehicle features are clearly visible, a vehicle head detection algorithm based on deep learning can be adopted to perform vehicle head detection on the image sequence, and if the times of detecting the vehicle head features are more than 8 times, and the change of the detected vehicle head central point H (x, y) meets the motion track of a similar license plate, namely meets the formula corresponding to the license plate coordinate change condition, the current scene is considered to have real vehicles.
B. Night scene:
because the false license plate is used more frequently at night, the identification of the true and false license plates at night is not negligible as an important component in the license plate anti-counterfeiting system. In the night scene of an entrance, the visual field of a camera imaging picture is generally small, external reflected light is not assisted usually, the picture is dark, the imaging quality in rainy days is poorer, the vehicle characteristics are very fuzzy, for more common black vehicles, only a license plate with a reflective film can be seen, and a vehicle body, a vehicle head and a vehicle window are very fuzzy. Therefore, a detection algorithm similar to template matching cannot detect a vehicle target, and a real license plate is easily filtered while a false license plate is filtered. However, the car lamp is the most obvious feature of the vehicle at night, so that the problems of unclear body feature, difficulty in detecting the car head and the like existing in a complex night environment are well solved, and therefore whether the current target is the vehicle with a real license plate or not can be determined by detecting the car lamp and performing track judgment by using the center position of the left (or right) car lamp.
In specific implementation, a car light detection algorithm based on deep learning can be adopted to perform car light detection on an image sequence of an entrance scene, and if the number of times of car light feature detection is more than 8, and the detected left (or right) car light center point L (x, y) meets the motion track of a similar license plate, namely meets the formula corresponding to the license plate coordinate change condition, it is considered that a real vehicle exists in the current scene.
And finally, after the judgment of the vehicle characteristics is finished, transmitting the judgment result into a true and false license plate output module.
3. True and false license plate output module:
the detection results of the license plate motion track, the license plate size change condition and the vehicle characteristics are analyzed and processed, and the two results coexist:
(1) false license plate output module: the license plate motion trail does not meet the motion trail of a real license plate in the entrance and exit scene, the size of the license plate is not expanded, or the relevant characteristics of the vehicle are not detected, and the license plate is output as a false license plate;
(2) real license plate output module: and if all judgment conditions in the modules are met, outputting the license plate as a real license plate.
Thus, the identification of the real and false license plates is completed.
It should be noted that the execution sequence of the three determination strategies in the above-mentioned real and false license plate determination module is only one implementation manner provided in the embodiment of the present application, that is, the execution sequence of the three determination strategies is not unique, and as for the implementation manner of advanced vehicle characteristic determination, subsequent vehicle motion trajectory determination and vehicle size change trend determination provided in the above-mentioned embodiment, accurate license plate real and false recognition can be achieved as well.
Therefore, the intelligent false license plate detection method provided by the embodiment of the application starts from the aspect of the whole system, and comprehensively considers factors of all aspects, so that the detection rate of the false license plate can reach more than 99.5%. Firstly, the realization method judges the authenticity of the license plate according to the change trend of the motion track and the size of the license plate, does not need to set a large number of parameters from the whole situation, is suitable for various vehicle types and has stronger adaptability; secondly, a processing mode of false license plate detection by using a traditional image processing algorithm is abandoned, and license plate detection and vehicle feature detection are realized by using a deep learning algorithm, so that the method is less influenced by external environment factors, has good robustness and can be popularized to various scenes; and finally, detecting the vehicle lamp target which is abnormally prominent at night by using a deep learning-based vehicle characteristic detection algorithm at night when the false license plate has higher occurrence probability, and judging the authenticity of the license plate, thereby effectively solving the problem of filtering the false license plate at night.
In order to solve the above technical problem, the present application further provides an apparatus for identifying an authentic or counterfeit license plate, please refer to fig. 4, where fig. 4 is a schematic structural diagram of the apparatus for identifying an authentic or counterfeit license plate provided by the present application, and the apparatus for identifying an authentic or counterfeit license plate may include:
the image sequence acquisition module 1 is used for acquiring a vehicle image sequence;
the target license plate detection module 2 is used for detecting license plates of all vehicle images in the vehicle image sequence to obtain license plate coordinates and license plate sizes of target license plates;
the license plate track judging module 3 is used for judging whether the license plate motion track conforms to the real license plate motion track or not according to each license plate coordinate;
the license plate size judging module 4 is used for judging whether the sizes of the license plates are in an increasing sequence or not if the license plate motion trail accords with the real license plate motion trail;
and the real and false license plate judging module 5 is used for determining that the target license plate is a real license plate if the sizes of the license plates are in an increasing sequence.
Therefore, the authenticity license plate recognition device provided by the embodiment of the application realizes authenticity of license plates according to license plate motion tracks and license plate size changes in the vehicle running process, when a vehicle image sequence is obtained, a target license plate in an image is firstly detected and determined, then the motion tracks and the size changes of the target license plate are judged, when the motion tracks of the target license plate meet the motion tracks of the real license plate and the size of the license plate is changed in an increasing mode, the target license plate can be determined to be the real license plate, the accuracy of authenticity license plate recognition results is effectively improved, and great convenience is provided for vehicle management.
As a preferred embodiment, the image sequence acquiring module 1 may include:
the characteristic judging unit is used for acquiring the video stream and judging whether the video image in the video stream has the vehicle characteristic or not;
and the image extraction unit is used for extracting the vehicle image sequence from the video stream when the vehicle features exist in the video images.
As a preferred embodiment, the characteristic determining unit may be specifically configured to collect current light intensity; if the current light intensity exceeds a preset threshold value, judging whether the vehicle head characteristics exist in the video image, and if so, determining that the vehicle characteristics exist in the video image; if the current light intensity does not exceed the preset threshold value, judging whether the vehicle lamp characteristics exist in the video image, and if so, determining that the vehicle characteristics exist in the video image.
As a preferred embodiment, the image extraction unit may be specifically configured to extract the vehicle image sequence from the video stream when the number of vehicle images having the vehicle feature in the video stream exceeds a preset number.
As a preferred embodiment, the license plate trajectory determination module 3 may be specifically configured to determine a license plate coordinate change condition according to a real license plate motion trajectory; judging whether the coordinates of each license plate meet the change condition of the coordinates of the license plate; if so, determining that the license plate motion track conforms to the real license plate motion track.
As a preferred embodiment, the license plate size determination module 4 may be specifically configured to determine a license plate height and a license plate width of a target license plate according to a license plate size; and judging whether the height and the width of the license plate are in an increasing order.
As a preferred embodiment, the authenticity license plate recognition device may further include a false license plate warning module, configured to determine that the target license plate is a false license plate and output a warning prompt when the license plate motion trajectory does not conform to the real license plate motion trajectory or the sizes of the license plates are not in an increasing order.
For the introduction of the apparatus provided in the present application, please refer to the above method embodiments, which are not described herein again.
In order to solve the above technical problem, the present application further provides an authenticity license plate recognition system, please refer to fig. 5, where fig. 5 is a schematic structural diagram of the authenticity license plate recognition system provided in the present application, and the authenticity license plate recognition system may include:
a memory 10 for storing a computer program;
the processor 20, when executing the computer program, may implement any of the steps of the above-mentioned method for identifying an authentic and counterfeit license plate.
For the introduction of the system provided by the present application, please refer to the above method embodiment, which is not described herein again.
In order to solve the above problem, the present application further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of any one of the above methods for identifying an authentic or counterfeit license plate can be implemented.
The computer-readable storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
For the introduction of the computer-readable storage medium provided in the present application, please refer to the above method embodiments, which are not described herein again.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The technical solutions provided by the present application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall into the protection scope of the present application.
Claims (10)
1. A method for identifying authenticity of a license plate is characterized by comprising the following steps:
acquiring a vehicle image sequence;
detecting license plates of all vehicle images in the vehicle image sequence to obtain license plate coordinates and license plate sizes of target license plates;
judging whether the license plate motion trail accords with the real license plate motion trail or not according to each license plate coordinate;
if the real license plate motion trail is met, judging whether the size of each license plate is in an increasing sequence;
and if the number of the target license plate is in the ascending sequence, determining that the target license plate is the real license plate.
2. The method for identifying the authenticity of a license plate according to claim 1, wherein the step of obtaining the vehicle image sequence comprises:
collecting a video stream, and judging whether a video image in the video stream has a vehicle characteristic or not;
when the vehicle feature is present in the video image, the sequence of vehicle images is extracted from the video stream.
3. The method for identifying the authenticity of a license plate according to claim 2, wherein the judging whether the video images in the video stream have the vehicle characteristics comprises:
collecting the current light intensity;
if the current light intensity exceeds a preset threshold value, judging whether a vehicle head feature exists in the video image, and if so, determining that the vehicle feature exists in the video image;
if the current light intensity does not exceed the preset threshold value, judging whether the video image has the car light characteristics, and if so, determining that the video image has the car characteristics.
4. The method according to claim 2, wherein the extracting the vehicle image sequence from the video stream when the vehicle feature exists in the video image comprises:
when the number of the vehicle images with the vehicle characteristics in the video stream exceeds a preset number, extracting the vehicle image sequence from the video stream.
5. The method for identifying whether a license plate is true or false according to claim 1, wherein the step of judging whether the license plate motion trail conforms to the real license plate motion trail according to each license plate coordinate comprises the following steps:
determining license plate coordinate change conditions according to the real license plate motion trail;
judging whether each license plate coordinate meets the license plate coordinate change condition;
if so, determining that the license plate motion track conforms to the real license plate motion track.
6. The method of claim 1, wherein the determining whether the license plate sizes are in an increasing order comprises:
determining the license plate height and the license plate width of the target license plate according to the license plate size;
and judging whether the height of the license plate and the width of the license plate are in an increasing order.
7. The method of claim 1, further comprising:
and when the license plate motion trail does not accord with the real license plate motion trail or the sizes of the license plates are not in an increasing sequence, determining that the target license plate is a false license plate, and outputting an alarm prompt.
8. An authenticity vehicle license plate recognition apparatus, comprising:
the image sequence acquisition module is used for acquiring a vehicle image sequence;
the target license plate detection module is used for detecting license plates of all vehicle images in the vehicle image sequence to obtain license plate coordinates and license plate sizes of target license plates;
the license plate track judging module is used for judging whether the license plate motion track conforms to the real license plate motion track or not according to the license plate coordinates;
the license plate size judging module is used for judging whether the sizes of the license plates are in an increasing sequence or not if the license plate motion trail accords with the real license plate motion trail;
and the real and false license plate judging module is used for determining that the target license plate is a real license plate if the sizes of the license plates are in an increasing sequence.
9. A genuine and counterfeit license plate recognition system, comprising:
a memory for storing a computer program;
a processor for executing said computer program to implement the steps of the method of authenticating a license plate according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, is configured to carry out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110270333.6A CN112861797A (en) | 2021-03-12 | 2021-03-12 | Method and device for identifying authenticity of license plate and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110270333.6A CN112861797A (en) | 2021-03-12 | 2021-03-12 | Method and device for identifying authenticity of license plate and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112861797A true CN112861797A (en) | 2021-05-28 |
Family
ID=75994307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110270333.6A Pending CN112861797A (en) | 2021-03-12 | 2021-03-12 | Method and device for identifying authenticity of license plate and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112861797A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723316A (en) * | 2021-09-01 | 2021-11-30 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN114842462A (en) * | 2022-04-07 | 2022-08-02 | 深圳市捷顺科技实业股份有限公司 | Anti-counterfeiting method for license plate |
| TWI789830B (en) * | 2021-07-15 | 2023-01-11 | 台灣車輛充電股份有限公司 | License plate recognition device and method for parking lot system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344988A (en) * | 2008-06-16 | 2009-01-14 | 上海高德威智能交通系统有限公司 | Image acquisition and processing equipment and method, vehicle monitoring and recording system |
| CN102142194A (en) * | 2010-12-30 | 2011-08-03 | 杭州海康威视数字技术股份有限公司 | Video detection method and system |
| CN105740841A (en) * | 2016-02-29 | 2016-07-06 | 浙江宇视科技有限公司 | Method and device for determining vehicle detection mode |
| CN108921151A (en) * | 2018-05-31 | 2018-11-30 | 四川物联亿达科技有限公司 | A kind of full Vehicle License Plate Recognition System of common camera based on deep learning |
| CN110533039A (en) * | 2019-09-04 | 2019-12-03 | 深圳市捷顺科技实业股份有限公司 | A kind of true-false detection method of license plate, device and equipment |
| CN111079751A (en) * | 2019-12-16 | 2020-04-28 | 深圳市芊熠智能硬件有限公司 | Method and device for identifying authenticity of license plate, computer equipment and storage medium |
| CN111382735A (en) * | 2018-12-29 | 2020-07-07 | 浙江宇视科技有限公司 | Night vehicle detection method, device, equipment and storage medium |
| CN111626225A (en) * | 2020-05-28 | 2020-09-04 | 济南博观智能科技有限公司 | License plate recognition method, device and equipment for station vehicle and storage medium |
-
2021
- 2021-03-12 CN CN202110270333.6A patent/CN112861797A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344988A (en) * | 2008-06-16 | 2009-01-14 | 上海高德威智能交通系统有限公司 | Image acquisition and processing equipment and method, vehicle monitoring and recording system |
| CN102142194A (en) * | 2010-12-30 | 2011-08-03 | 杭州海康威视数字技术股份有限公司 | Video detection method and system |
| CN105740841A (en) * | 2016-02-29 | 2016-07-06 | 浙江宇视科技有限公司 | Method and device for determining vehicle detection mode |
| CN108921151A (en) * | 2018-05-31 | 2018-11-30 | 四川物联亿达科技有限公司 | A kind of full Vehicle License Plate Recognition System of common camera based on deep learning |
| CN111382735A (en) * | 2018-12-29 | 2020-07-07 | 浙江宇视科技有限公司 | Night vehicle detection method, device, equipment and storage medium |
| CN110533039A (en) * | 2019-09-04 | 2019-12-03 | 深圳市捷顺科技实业股份有限公司 | A kind of true-false detection method of license plate, device and equipment |
| CN111079751A (en) * | 2019-12-16 | 2020-04-28 | 深圳市芊熠智能硬件有限公司 | Method and device for identifying authenticity of license plate, computer equipment and storage medium |
| CN111626225A (en) * | 2020-05-28 | 2020-09-04 | 济南博观智能科技有限公司 | License plate recognition method, device and equipment for station vehicle and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI789830B (en) * | 2021-07-15 | 2023-01-11 | 台灣車輛充電股份有限公司 | License plate recognition device and method for parking lot system |
| CN113723316A (en) * | 2021-09-01 | 2021-11-30 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN113723316B (en) * | 2021-09-01 | 2024-04-16 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN114842462A (en) * | 2022-04-07 | 2022-08-02 | 深圳市捷顺科技实业股份有限公司 | Anti-counterfeiting method for license plate |
| CN114842462B (en) * | 2022-04-07 | 2024-04-09 | 深圳市捷顺科技实业股份有限公司 | License plate anti-fake method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112861797A (en) | Method and device for identifying authenticity of license plate and related equipment | |
| CN107563347B (en) | Passenger flow counting method and device based on TOF camera | |
| TWI497422B (en) | A system and method for recognizing license plate image | |
| CN103824452B (en) | A kind of peccancy parking detector based on panoramic vision of lightweight | |
| CN102722704B (en) | Method and system for recognizing vehicle license plate by integrating video dynamic tracking | |
| CN104966071B (en) | It is a kind of based on the night car plate detection of infrared light filling and recognition methods and device | |
| CN111382704B (en) | Vehicle line pressing violation judging method and device based on deep learning and storage medium | |
| CN107330373A (en) | A kind of parking offense monitoring system based on video | |
| CN101030256B (en) | Method and apparatus for cutting vehicle image | |
| CN110826508A (en) | Pedestrian and non-motor vehicle violation detection and tracking method based on video stream | |
| CN103679704A (en) | Video motion shadow detecting method based on lighting compensation | |
| CN105046948A (en) | System and method of monitoring illegal traffic parking in yellow grid line area | |
| CN115035564A (en) | Face recognition method, system and related components based on intelligent patrol car camera | |
| Santos et al. | Car recognition based on back lights and rear view features | |
| CN115690441A (en) | Traffic signal lamp area detection method, device and equipment | |
| CN113657250A (en) | Flame detection method and system based on monitoring video | |
| KR100942409B1 (en) | Method for detecting a moving vehicle at a high speed | |
| JP2004086417A (en) | Method and device for detecting pedestrian on zebra crossing | |
| CN116682268A (en) | Portable urban road vehicle violation inspection system and method based on machine vision | |
| Deb et al. | Vehicle license plate detection algorithm based on color space and geometrical properties | |
| CN107993446A (en) | A kind of traffic prohibition parking area domain parking offense monitoring device | |
| CN114373147A (en) | Detection method for low-texture video license plate | |
| Deb et al. | An efficient method of vehicle license plate detection based on HSI color model and histogram | |
| CN113822149A (en) | Emergency lane visual detection method and system based on view angle of unmanned aerial vehicle | |
| JPH1166490A (en) | Vehicle detecting method |
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 |
Application publication date: 20210528 |
|
| RJ01 | Rejection of invention patent application after publication |