CN116740661B - Method for reversely tracking Mongolian vehicle based on face recognition - Google Patents
Method for reversely tracking Mongolian vehicle based on face recognition Download PDFInfo
- Publication number
- CN116740661B CN116740661B CN202311010249.6A CN202311010249A CN116740661B CN 116740661 B CN116740661 B CN 116740661B CN 202311010249 A CN202311010249 A CN 202311010249A CN 116740661 B CN116740661 B CN 116740661B
- Authority
- CN
- China
- Prior art keywords
- value
- license plate
- mongolian
- vector
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004364 calculation method Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims description 75
- 238000004590 computer program Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 11
- 238000010586 diagram Methods 0.000 claims description 8
- 238000002834 transmittance Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012797 qualification Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for reversely tracking a Mongolian vehicle based on face recognition, which relates to the field of data recognition, wherein a road image acquisition device is used for acquiring and storing face images of a truck, environmental data and the face images are imported into a constructed defogging model to carry out clear processing on the face images, a face recognition strategy is used for recognizing a head part image, a nine-grid cutting is carried out on the head part image, characteristic value calculation is carried out on images in nine Gong Gemei grids, a characteristic value array is stored, license plate images are imported into a Mongolian recognition strategy to judge whether the Mongolian is used for carrying out, the characteristic value array of the Mongolian vehicle and characteristic value data of other non-Mongolian vehicles which are driven are imported into a similarity calculation formula to carry out similarity calculation, and the calculated license plate numbers with similarity exceeding a similarity threshold are stored to obtain the license plate numbers of the Mongolian vehicles, so that the Mongolian vehicles are accurately and quickly found, and the method has the advantage of high recognition rate.
Description
Technical Field
The invention relates to the field of data identification, in particular to a method for reversely tracking a Mongolian vehicle based on face identification.
Background
With the increase of the intensity of governments on overdriving, a truck driver actively shields the license plate in order to avoid punishment, and has a great influence on the highway overdriving, and the phenomenon of actively shielding the license plate cannot quickly acquire information of the vehicle, so that the vehicle cannot be quickly captured, and therefore, the problem of how to strike similar things after the fact is solved cannot be solved in the prior art;
for example, in the chinese patent with the publication number CN105551046B, a face positioning method and apparatus are provided, and the method includes: acquiring an enhanced vehicle body image of a vehicle to be identified, and respectively carrying out gradient projection in the horizontal direction and the vertical direction on the enhanced vehicle body image according to the vertical gradient value and the horizontal gradient value of each pixel of the enhanced vehicle body image to obtain a horizontal projection image and a vertical projection image; judging whether the car in the car body image to be processed is a car or not according to the distribution characteristics of the horizontal projection image and the vertical projection image; if the car is a car, determining a left edge line and a right edge line of the car face according to the range with projection values in the vertical projection diagram, determining a lower edge line and an upper edge line of the car face according to the peak value in the horizontal projection diagram, and determining a car face area according to the left edge line, the right edge line, the lower edge line and the upper edge line of the car face, so that the car face area can be positioned without license plate position information, and the positioning accuracy of the car face is improved;
meanwhile, a real-time detection method for license plate shielding of a vehicle without a license plate is disclosed in China patent with the application publication number of CN 104951784A. The method comprises the following steps: (1) carrying out license plate recognition and vehicle detection on a single frame; (2) Correlating the license plate identified by each frame with the license plate obtained by the previous frame identification, and outputting a license plate track chain after comprehensive identification; (3) Associating the same vehicle with multiple frames, removing false detection targets, and outputting a vehicle track chain when the vehicle drives out of the picture; (4) Analyzing the comprehensive recognition result of the license plate track chain, judging whether the character is blocked or not, and giving out the blocked character position; (5) And matching the license plate track chain with the vehicle track chain, and judging that the vehicle is not licensed when the vehicle track chain which is not matched with the license plate is not licensed. The invention not only can effectively and automatically detect no license plate or license plate shielding, but also can judge the position of shielding characters in the license plate, can perform real-time processing, and can judge that the vehicle is no license plate if the license plate is seriously shielded and can not be identified;
the above patents all exist: the invention provides a method for reversely tracking a Mongolian vehicle based on face recognition, which aims to solve the problem that a truck driver actively shields a license plate for avoiding punishment, has huge influence on road treatment, cannot quickly acquire information of the vehicle due to the phenomenon of actively shielding the license plate, and cannot quickly capture the vehicle, so that the problem of how to strike similar things afterwards becomes a difficult point.
Disclosure of Invention
Aiming at the defects of the prior art, the invention mainly aims to provide a method for reversely tracking a Mongolian vehicle based on face recognition, which can effectively solve the problems in the background art: the truck driver can actively shelter from the license plate in order to avoid punishment, huge influence is brought to the highway treatment, and information acquisition can not be carried out on the vehicle rapidly due to the phenomenon of actively shelter from the license plate, so that the vehicle can not be captured rapidly, and the problem of striking similar things after the fact is solved. The specific technical scheme of the invention is as follows:
a method for reversely tracking a Mongolian vehicle based on face recognition comprises the following specific steps:
s1, a road image acquisition device acquires and stores a face image of a road truck;
s2, acquiring environment data, importing the environment data and the face image into a constructed defogging model, and performing sharpening processing on the face image;
s3, recognizing license plate part images by using a face recognition strategy;
s4, performing nine-grid cutting on the defogged face image, performing characteristic value calculation on the image in nine Gong Gemei grids, and storing a characteristic value array;
s5, importing license plate images into a mask recognition strategy to judge whether the license plates are masked, if so, executing S6, and if not, directly ending the flow;
s6, importing the Mongolian vehicle characteristic value array and other non-Mongolian vehicle characteristic value data of running into a similarity calculation formula to calculate similarity;
and S7, storing the license plate numbers with the calculated similarity exceeding the similarity threshold value to obtain the license plate number of the Mongolian vehicle.
The invention further improves that the specific content of the S1 comprises the following steps:
s101, the road image acquisition equipment acquires the road face image at regular time, and performs graying treatment on the image to obtain a graying treatment image;
s102, dividing pixel points of the graying processing image, calculating the difference value between the gray value of each pixel point and the gray value of the adjacent pixel point above to obtain a vertical gradient value of the pixel point, and calculating the difference value between the gray value of each pixel point and the gray value of the adjacent pixel point on the left side to obtain a horizontal gradient value of the pixel point;
s103, connecting pixels with vertical gradient values larger than a set vertical gradient threshold to obtain upper and lower boundary lines of a face image, connecting pixels with horizontal gradient values larger than the set horizontal gradient threshold to obtain left and right boundary lines of the face image to obtain a contour line of the face image, dividing the lengths of the upper and lower boundary lines by the lengths of the left and right boundary lines to obtain a quotient, comparing the quotient with a set aspect ratio of the face of the truck, wherein the aspect ratio of the face of the truck is set to be 0.9-1.5, the set vertical gradient threshold is in direct proportion to the smoke concentration, and the set range is 2-4, so that the face image of the truck corresponding to the quotient in the set aspect ratio of the face of the truck is collected and stored.
The invention is further improved in that the specific steps of S2 are as follows:
s201, acquiring the light transmittance T of a shooting position in a field environment, simultaneously acquiring a dark channel diagram of an input image, and finding out the first 0.1% pixel point with the highest brightness to form a pixel point set;
s202, extracting a pixel point set, restoring to a pixel point with maximum brightness in an original input image, and setting the brightness value as an atmospheric light value A;
s203, importing the environment data and the acquired face image into a defogging model formula to obtain a clear face image, wherein the defogging model formula is as follows:where I (x) is an input face image, J (x) is a defogged restored face image, t is a set lower transmittance value, and max () is a maximum value in a calculation bracket.
The invention further improves that the specific content of the S3 comprises the following steps:
s301, extracting defogging and recovering a face image J (x), dividing pixel points of the recovered face image to obtain color chromaticity values of each pixel point, extracting color chromaticity, length and width of a license plate of a storage truck, and forming an aggregate vector B;
s302, calculating the difference value between the chromaticity value of each pixel point and the chromaticity value of the adjacent pixel point to obtain a vertical chromaticity gradient value of the pixel point, and calculating the difference value between the chromaticity value of each pixel point and the chromaticity value of the adjacent pixel point on the left side to obtain a horizontal chromaticity gradient value of the pixel point;
s303, connecting pixels with vertical chroma gradient values larger than a set vertical chroma gradient value threshold, and connecting pixels with horizontal chroma gradient values larger than the set horizontal chroma gradient threshold to obtain a plurality of color areas;
s304, extracting color chromaticity, length and width values of the color areas to form an aggregate vector A, importing the color chromaticity, length and width values of the color areas and the aggregate vector B into a license plate similarity calculation formula to identify license plate positions, and setting the color area with the largest license plate similarity between a plurality of color areas and a storage truck as the area of the license plate;
s305, calculating a license plate similarity formula:wherein m is license plate similarity, A i For the ith number value in aggregate vector A, B i Is the i-th value in the set vector B.
The invention is further improved in that the step S4 comprises the following specific steps: s401, performing nine-grid cutting on the defogged restored face image, and extracting features of the image in nine Gong Gemei grids, wherein the extracted features are as follows: the first k text data m on the certification k Length data h of hanging ornament c And rearview mirror angle data Q c Wherein m is k K in the (a) is the number of characters;
s402, the first k text data m on the qualification certificate k Vectorization, conversion to a k-dimensional vector, and subsequent addition of a mountDecoration length data h c And rearview mirror angle data Q c And two-dimensional vectors, forming characteristic vector values, and storing the characteristic vector values.
The invention is further improved in that the step S5 comprises the following specific steps:
s501, acquiring distance l of vehicle from photographing equipment during photographing cz Simultaneously collecting the angle of view theta of a shooting camera xj Resolution z xj And sensor dimension T xj Simultaneously extracting a color region with the maximum license plate similarity with the stored truck as a range value of a region of the license plate;
s502, substituting the area range of the color area with the maximum license plate similarity with the storage truck, which is extracted in the S501, into area calculation software to perform area calculation to obtain the area S of the area range;
s503, the area S of the area range and the distance l between the vehicle and the photographing device cz Angle of view θ of shooting camera xj Resolution z xj And sensor dimension T xj Substituting the original area S of the license plate into a license plate original area calculation formula to calculate the original area S of the license plate y The original license plate area calculation formula is as follows:comparing the obtained original license plate area with the stored license plate area, if the original license plate area is smaller than or equal to 90% of the stored license plate area, the license plate is considered to be covered, and if the original license plate area is larger than 90% of the stored license plate area, the license plate is considered to be not covered.
The invention is further improved in that the step S6 comprises the following specific steps:
s601, extracting feature vector values of the face images restored after defogging is obtained in the step S402, and extracting corresponding other non-mask vehicle feature vector value data;
s602, substituting the extracted feature vector value data of a plurality of groups of non-mask vehicles and the feature vector value of the defogging restored face image into a vector similarity calculation formula to calculate vector similarity;
s603, calculating the vector similarity formulaThe method comprises the following steps:wherein m () is the number of vector values in brackets, m k1 Is the non-Mongolian vehicle characteristic vector value data, m k To restore the eigenvector value data of the face image after defogging, C i Hanging length data h for recovering face image after defogging c And rearview mirror angle data Q c The ith vector value, D, in the constructed two-dimensional vector i An i-th vector value in a two-dimensional vector formed by the trim length data and the rearview mirror angle data of the non-Mongolian vehicle.
The invention is further improved in that the S7 comprises the following concrete contents: extracting vector similarity calculated by the feature value array of the Mongolian vehicle and the feature value data of each running non-Mongolian vehicle, sorting the calculated vector similarity in descending order, extracting license plates of the non-Mongolian vehicles with the vector similarity being more than 90%, and setting the license plates as suspected Mongolian vehicles, wherein the S7 further comprises the following specific contents: determining the position of the suspected mask vehicle, and removing the suspected mask vehicle which is not in the area, wherein the step S7 further comprises the following specific contents: and searching the suspected mask vehicles according to the descending order of the similarity.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of back tracking a Mongolian vehicle based on face recognition as described above when executing the computer program.
A computer readable storage medium having a computer program stored thereon, the computer program when executed by a processor implementing a method of back tracking a Mongolian vehicle based on face recognition as described above.
Compared with the prior art, the invention has the following beneficial effects:
the invention collects and stores the face image of the wagon through the road image collecting equipment, guides the environment data and the face image into the constructed defogging model to carry out the sharpening process on the face image, recognizes the license plate part image by using the face recognition strategy, carries out the nine-grid cutting on the defogged face image, carries out the characteristic value calculation on the image in the nine Gong Gemei grid, stores the characteristic value array, guides the license plate image into the mask recognition strategy to judge whether the mask is carried out, guides the characteristic value array of the mask vehicle and the characteristic value data of other non-mask vehicles which run into the similarity calculation formula to carry out the similarity calculation, stores the license plate number of the obtained similarity exceeding the similarity threshold value to obtain the license plate number of the mask vehicle, and accurately and rapidly searches the mask vehicle with high recognition rate.
Drawings
FIG. 1 is a schematic diagram of a method for back tracking a Mongolian vehicle based on face recognition according to the present invention;
FIG. 2 is a schematic diagram of a specific flow frame of step S2 of a method for backward tracking a Mongolian vehicle based on face recognition according to the present invention;
fig. 3 is a schematic diagram of a specific flow frame of step S4 of a method for backward tracking a mask vehicle based on face recognition according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
Aiming at the problem that the intensity of governments on treatment is increased, a truck driver actively shields a license plate in order to avoid punishment, huge influence is brought to highway treatment, and the phenomenon of actively shielding the license plate cannot quickly acquire information of a vehicle, so that the vehicle cannot be quickly captured, and the problem that how to strike similar things later becomes a difficulty is solved, the method for reversely tracking a Mongolian vehicle based on face recognition is adopted, as shown in fig. 1-3, and comprises the following specific steps:
s1, a road image acquisition device acquires and stores a face image of a road truck;
the specific content of S1 comprises the following steps:
s101, the road image acquisition equipment acquires the road face image at regular time, and performs graying treatment on the image to obtain a graying treatment image;
s102, dividing the gray processing image into pixels, calculating the difference value between the gray value of each pixel and the gray value of the adjacent pixel above to obtain a vertical gradient value of the pixel, and calculating the difference value between the gray value of each pixel and the gray value of the adjacent pixel on the left to obtain a horizontal gradient value of the pixel;
s103, connecting pixels with vertical gradient values larger than a set vertical gradient threshold to obtain upper and lower boundary lines of a face image, connecting pixels with horizontal gradient values larger than the set horizontal gradient threshold to obtain left and right boundary lines of the face image, obtaining a contour line of the face image, dividing the lengths of the upper and lower boundary lines by the lengths of the left and right boundary lines to obtain quotient, comparing the quotient with a set aspect ratio of the face of the truck, wherein the aspect ratio of the face of the truck is set to be 0.9-1.5, the set horizontal gradient threshold and the vertical gradient threshold are in direct proportion to smoke concentration, and the set range is set to be 2-4, so that the face image of the truck corresponding to the quotient in the set aspect ratio of the face of the truck is collected and stored, and the vertical gradient threshold and the horizontal gradient threshold can be flexibly set according to the requirement of the truck, and the set value is set to be 2-4;
s2, acquiring environment data, importing the environment data and the face image into a constructed defogging model, and performing sharpening processing on the face image;
the specific steps of S2 are as follows:
s201, acquiring the light transmittance T of a shooting position in a field environment, simultaneously acquiring a dark channel diagram of an input image, and finding out the first 0.1% pixel point with the highest brightness to form a pixel point set;
s202, extracting a pixel point set, restoring to a pixel point with maximum brightness in an original input image, and setting the brightness value as an atmospheric light value A;
s203, importing the environment data and the acquired face image into a defogging model formula to obtain a clear face image, wherein the defogging model formula is as follows:wherein I (x) is an input face image, J (x) is a defogged restored face image, t is a set lower limit value of transmissivity, max () is a maximum value in a calculation bracket, and t is 0.1;
s3, recognizing license plate part images by using a face recognition strategy;
the specific content of S3 comprises the following steps:
s301, extracting defogging and recovering a face image J (x), dividing pixel points of the recovered face image to obtain color chromaticity values of each pixel point, extracting color chromaticity, length and width of a license plate of a storage truck, and forming an aggregate vector B;
s302, calculating the difference value between the chromaticity value of each pixel point and the chromaticity value of the adjacent pixel point to obtain a vertical chromaticity gradient value of the pixel point, and calculating the difference value between the chromaticity value of each pixel point and the chromaticity value of the adjacent pixel point on the left side to obtain a horizontal chromaticity gradient value of the pixel point;
s303, connecting pixels with vertical chroma gradient values larger than a set vertical chroma gradient value threshold, and connecting pixels with horizontal chroma gradient values larger than a set horizontal chroma gradient threshold to obtain a plurality of color areas, wherein the vertical chroma gradient value threshold and the horizontal chroma gradient threshold can be flexibly set according to the requirement of a vehicle, and the set values are 2-4;
s304, extracting color chromaticity, length and width values of the color areas to form an aggregate vector A, importing the color chromaticity, length and width values of the color areas and the aggregate vector B into a license plate similarity calculation formula to identify license plate positions, and setting the color area with the largest license plate similarity between a plurality of color areas and a storage truck as the area of the license plate;
s305, calculating a license plate similarity formula:wherein m is license plate similarity, A i For the ith number value in aggregate vector A, B i Is the i-th value in the aggregate vector B;
s4, performing nine-grid cutting on the defogged face image, performing characteristic value calculation on the image in nine Gong Gemei grids, and storing a characteristic value array;
s4 comprises the following specific steps: s401, performing nine-grid cutting on the defogged restored face image, and extracting features of the image in nine Gong Gemei grids, wherein the extracted features are as follows: the first k text data m on the certification k Length data h of hanging ornament c And rearview mirror angle data Q c Wherein m is k K in the (a) is the number of characters;
s402, the first k text data m on the qualification certificate k Vectorization, conversion into a k-dimensional vector, and subsequent addition of the pendant length data h c And rearview mirror angle data Q c Two-dimensional vectors, forming characteristic vector values, and storing the characteristic vector values;
s5, importing license plate images into a mask recognition strategy to judge whether the license plates are masked, if so, executing S6, and if not, directly ending the flow;
s5, the method comprises the following specific steps:
s501, acquiring distance l of vehicle from photographing equipment during photographing cz Simultaneously collecting the angle of view of a shooting cameraθ xj Resolution z xj And sensor dimension T xj Simultaneously extracting a color region with the maximum license plate similarity with the stored truck as a range value of a region of the license plate;
s502, substituting the area range of the color area with the maximum license plate similarity with the storage truck, which is extracted in the S501, into area calculation software to perform area calculation to obtain the area S of the area range;
s503, the area S of the area range and the distance l between the vehicle and the photographing device cz Angle of view θ of shooting camera xj Resolution z xj And sensor dimension T xj Substituting the original area S of the license plate into a license plate original area calculation formula to calculate the original area S of the license plate y The original area calculation formula of the license plate is as follows:comparing the obtained original license plate area with the stored license plate area, if the original license plate area is smaller than or equal to 90% of the stored license plate area, considering that the license plate is covered, and if the original license plate area is larger than 90% of the stored license plate area, considering that the license plate is not covered;
s6, importing the Mongolian vehicle characteristic value array and other non-Mongolian vehicle characteristic value data of running into a similarity calculation formula to calculate similarity;
s6, the method comprises the following specific steps:
s601, extracting feature vector values of the face images restored after defogging is obtained in the step S402, and extracting corresponding other non-mask vehicle feature vector value data;
s602, substituting the extracted feature vector value data of a plurality of groups of non-mask vehicles and the feature vector value of the defogging restored face image into a vector similarity calculation formula to calculate vector similarity;
s603, a vector similarity calculation formula is as follows:wherein m () is the number of vector values in brackets, m k1 Is the non-Mongolian vehicle characteristic vector value data, m k To restore the eigenvector value data of the face image after defogging, C i Hanging length data h for recovering face image after defogging c And rearview mirror angle data Q c The ith vector value, D, in the constructed two-dimensional vector i An i-th vector value in a two-dimensional vector formed by the trim length data and the rearview mirror angle data of the non-Mongolian vehicle;
s7, storing the license plate numbers with the calculated similarity exceeding the similarity threshold value to obtain license plate numbers of the Mongolian vehicle;
s7 comprises the following specific contents: extracting vector similarity calculated by the feature value array of the Mongolian vehicle and the feature value data of each running non-Mongolian vehicle, sorting the calculated vector similarity in descending order, extracting license plates of the non-Mongolian vehicles with the vector similarity being more than 90%, and setting the license plates as suspected Mongolian vehicles, wherein S7 further comprises the following concrete contents: determining the position of the suspected mask vehicle, and removing the suspected mask vehicle which is not in the area, wherein the step S7 further comprises the following specific contents: and searching the suspected mask vehicles according to the descending order of the similarity.
Example 2
The present embodiment provides an electronic device including: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes a method of back tracking a Mongolian vehicle based on face recognition as described above by invoking a computer program stored in the memory.
The electronic device may be configured or configured differently to generate a larger difference, and may include one or more processors (Central Processing Units, CPU) and one or more memories, where at least one computer program is stored in the memories, and the computer program is loaded and executed by the processors to implement a method for backward tracking a Mongolian vehicle based on face recognition provided by the above method embodiments. The electronic device can also include other components for implementing the functions of the device, for example, the electronic device can also have wired or wireless network interfaces, input-output interfaces, and the like, for inputting and outputting data. The present embodiment is not described herein.
Example 3
The present embodiment proposes a computer-readable storage medium having stored thereon an erasable computer program;
the computer program, when executed on the computer device, causes the computer device to perform a method of tracking a Mongolian vehicle in a reverse direction based on face recognition as described above.
For example, the computer readable storage medium can be Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), compact disk Read-Only Memory (CD-ROM), magnetic tape, floppy disk, optical data storage device, etc.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It should be understood that determining B from a does not mean determining B from a alone, but can also determine B from a and/or other information.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by way of wired or/and wireless networks from one website site, computer, server, or data center to another. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. 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 invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely one, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, 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 present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A method for reversely tracking a Mongolian vehicle based on face recognition is characterized by comprising the following steps: the method comprises the following specific steps:
s1, a road image acquisition device acquires and stores a face image of a road truck;
s2, acquiring environment data, importing the environment data and the face image into a constructed defogging model, and performing sharpening processing on the face image;
s3, recognizing license plate part images by using a face recognition strategy;
s4, performing nine-grid cutting on the defogged face image, performing characteristic value calculation on the image in nine Gong Gemei grids, and storing a characteristic value array;
s5, importing license plate images into a mask recognition strategy to judge whether the license plates are masked, if so, executing S6, and if not, directly ending the flow;
s6, importing the Mongolian vehicle characteristic value array and other non-Mongolian vehicle characteristic value data of running into a similarity calculation formula to calculate similarity;
s7, storing the license plate numbers with the calculated similarity exceeding the similarity threshold value to obtain license plate numbers of the Mongolian vehicle; the specific content of the S1 comprises the following steps:
s101, the road image acquisition equipment acquires the road face image at regular time, and performs graying treatment on the image to obtain a graying treatment image;
s102, dividing pixel points of the graying processing image, calculating the difference value between the gray value of each pixel point and the gray value of the adjacent pixel point above to obtain a vertical gradient value of the pixel point, and calculating the difference value between the gray value of each pixel point and the gray value of the adjacent pixel point on the left side to obtain a horizontal gradient value of the pixel point; s103, connecting pixels with vertical gradient values larger than a set vertical gradient threshold to obtain upper and lower boundary lines of a face image, connecting pixels with horizontal gradient values larger than the set horizontal gradient threshold to obtain left and right boundary lines of the face image to obtain a contour line of the face image, dividing the lengths of the upper and lower boundary lines by the lengths of the left and right boundary lines to obtain a quotient, comparing the quotient with a set aspect ratio range of the face of the wagon, and acquiring and storing the face image of the wagon corresponding to the quotient in the set aspect ratio range of the face of the wagon; the specific steps of the S2 are as follows:
s201, acquiring the light transmittance T of a shooting position in a field environment, simultaneously acquiring a dark channel diagram of an input image, and finding out the first 0.1% pixel point with the highest brightness to form a pixel point set;
s202, extracting a pixel point set, restoring to a pixel point with maximum brightness in an original input image, and setting the brightness value as an atmospheric light value A;
s203, importing the environment data and the acquired face image into a defogging model formula to obtain a clear face image, wherein the defogging model formula is as follows:wherein I (x) is an input face image, J (x) is a defogged restored face image, t is a set lower limit value of transmissivity, and max () is a maximum value in a calculation bracket; the specific content of the S3 comprises the following steps:
s301, extracting defogging and recovering a face image J (x), dividing pixel points of the recovered face image to obtain color chromaticity values of each pixel point, extracting color chromaticity, length and width of a license plate of a storage truck, and forming an aggregate vector B;
s302, calculating the difference value between the chromaticity value of each pixel point and the chromaticity value of the adjacent pixel point to obtain a vertical chromaticity gradient value of the pixel point, and calculating the difference value between the chromaticity value of each pixel point and the chromaticity value of the adjacent pixel point on the left side to obtain a horizontal chromaticity gradient value of the pixel point;
s303, connecting pixels with vertical chroma gradient values larger than a set vertical chroma gradient value threshold, and connecting pixels with horizontal chroma gradient values larger than the set horizontal chroma gradient threshold to obtain a plurality of color areas;
s304, extracting color chromaticity, length and width values of the color areas to form an aggregate vector A, importing the color chromaticity, length and width values of the color areas and the aggregate vector B into a license plate similarity calculation formula to identify license plate positions, and setting the color area with the largest license plate similarity between a plurality of color areas and a storage truck as the area of the license plate;
s305, calculating a license plate similarity formula:wherein m is license plate similarity, A i For the ith number value in aggregate vector A, B i Is the i-th value in the aggregate vector B; the step S4 comprises the following specific steps: s401, performing nine-grid cutting on the defogged restored face image, and extracting features of the image in nine Gong Gemei grids, wherein the extracted features are as follows: the first k text data m on the certification k Length data h of hanging ornament c And rearview mirror angle data Q c Wherein m is k K in the (a) is the number of characters;
s402, the first k text data m on the qualification certificate k Vectorization, conversion into a k-dimensional vector, and subsequent addition of the pendant length data h c And rearview mirror angle data Q c Two-dimensional vectors, forming characteristic vector values, and storing the characteristic vector values; the step S5 comprises the following specific steps:
s501, acquiring distance l of vehicle from photographing equipment during photographing cz Simultaneously collecting the angle of view theta of a shooting camera xj Resolution z xj And sensor dimension T xj Simultaneously extracting a color region with the maximum license plate similarity with the stored truck as a range value of a region of the license plate;
s502, substituting the area range of the color area with the maximum license plate similarity with the storage truck, which is extracted in the S501, into area calculation software to perform area calculation to obtain the area S of the area range;
s503, the area S of the area range and the distance l between the vehicle and the photographing device cz Angle of view θ of shooting camera xj Resolution z xj And sensor dimension T xj Substituting the original area S of the license plate into a license plate original area calculation formula to calculate the original area S of the license plate y The original license plate area calculation formula is as follows:comparing the obtained original license plate area with the stored license plate area, if the original license plate area is smaller than or equal to 90% of the stored license plate area, the license plate is considered to be covered, and if the original license plate area is larger than 90% of the stored license plate area, the license plate is considered to be not covered.
2. A method for back tracking a monument vehicle based on face recognition as in claim 1, wherein: the step S6 comprises the following specific steps:
s601, extracting feature vector values of the face images restored after defogging is obtained in the step S402, and extracting corresponding other non-mask vehicle feature vector value data;
s602, substituting the extracted feature vector value data of a plurality of groups of non-mask vehicles and the feature vector value of the defogging restored face image into a vector similarity calculation formula to calculate vector similarity;
s603, the vector similarity calculation formula is as follows:wherein m () is the number of vector values in brackets, m k1 Is the non-Mongolian vehicle characteristic vector value data, m k To restore the eigenvector value data of the face image after defogging, C i Hanging length data h for recovering face image after defogging c And rearview mirror angle data Q c The ith vector value, D, in the constructed two-dimensional vector i An i-th vector value in a two-dimensional vector formed by the trim length data and the rearview mirror angle data of the non-Mongolian vehicle.
3. A method for back tracking a monument vehicle based on face recognition as defined in claim 2, wherein: the S7 comprises the following specific contents: extracting vector similarity calculated by the feature value array of the Mongolian vehicles and the feature value data of each non-Mongolian vehicle, sorting the calculated vector similarity in descending order, extracting license plates of the non-Mongolian vehicles with the vector similarity being more than 90%, and setting the license plates as suspected Mongolian vehicles.
4. A method for back tracking a monument vehicle based on face recognition as in claim 3, wherein: the S7 further comprises the following concrete contents: the positions of the suspected mask vehicles are determined, and the suspected mask vehicles which are not in the area are removed from consideration.
5. The method for back tracking a Mongolian vehicle based on face recognition of claim 4, wherein: the S7 further comprises the following concrete contents: and searching the suspected mask vehicles according to the descending order of the similarity.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a method of back tracking a mask vehicle based on face recognition as claimed in any one of claims 1 to 5 when the computer program is executed by the processor.
7. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, which when executed by a processor, implements a method of back tracking a Mongolian vehicle based on face recognition according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311010249.6A CN116740661B (en) | 2023-08-11 | 2023-08-11 | Method for reversely tracking Mongolian vehicle based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311010249.6A CN116740661B (en) | 2023-08-11 | 2023-08-11 | Method for reversely tracking Mongolian vehicle based on face recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116740661A CN116740661A (en) | 2023-09-12 |
| CN116740661B true CN116740661B (en) | 2023-12-22 |
Family
ID=87901577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311010249.6A Active CN116740661B (en) | 2023-08-11 | 2023-08-11 | Method for reversely tracking Mongolian vehicle based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116740661B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951784A (en) * | 2015-06-03 | 2015-09-30 | 杨英仓 | Method of detecting absence and coverage of license plate in real time |
| CN105551046A (en) * | 2015-12-17 | 2016-05-04 | 浙江宇视科技有限公司 | Vehicle face location method and device |
| CN111985471A (en) * | 2020-07-14 | 2020-11-24 | 浙江大华技术股份有限公司 | License plate positioning method and device and storage medium |
| CN113343880A (en) * | 2021-06-21 | 2021-09-03 | 广州大学 | Method, device, equipment and medium for identifying vehicle shielding number plate |
| CN115424217A (en) * | 2022-08-31 | 2022-12-02 | 东方世纪科技股份有限公司 | AI vision-based intelligent vehicle identification method and device and electronic equipment |
| CN115909314A (en) * | 2022-12-21 | 2023-04-04 | 浙江大华技术股份有限公司 | License plate shielding detection method, illegal parking detection method and equipment thereof |
| CN116052150A (en) * | 2023-01-18 | 2023-05-02 | 暨南大学 | Vehicle face recognition method for shielding license plate |
-
2023
- 2023-08-11 CN CN202311010249.6A patent/CN116740661B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951784A (en) * | 2015-06-03 | 2015-09-30 | 杨英仓 | Method of detecting absence and coverage of license plate in real time |
| CN105551046A (en) * | 2015-12-17 | 2016-05-04 | 浙江宇视科技有限公司 | Vehicle face location method and device |
| CN111985471A (en) * | 2020-07-14 | 2020-11-24 | 浙江大华技术股份有限公司 | License plate positioning method and device and storage medium |
| CN113343880A (en) * | 2021-06-21 | 2021-09-03 | 广州大学 | Method, device, equipment and medium for identifying vehicle shielding number plate |
| CN115424217A (en) * | 2022-08-31 | 2022-12-02 | 东方世纪科技股份有限公司 | AI vision-based intelligent vehicle identification method and device and electronic equipment |
| CN115909314A (en) * | 2022-12-21 | 2023-04-04 | 浙江大华技术股份有限公司 | License plate shielding detection method, illegal parking detection method and equipment thereof |
| CN116052150A (en) * | 2023-01-18 | 2023-05-02 | 暨南大学 | Vehicle face recognition method for shielding license plate |
Non-Patent Citations (1)
| Title |
|---|
| Single Image Haze Removal Using Dark Channel Prior;Kaiming He 等;《IEEE》;第33卷(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116740661A (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021003824A1 (en) | Image recognition-based illegal building identification method and device | |
| CN109101924B (en) | Machine learning-based road traffic sign identification method | |
| Wang et al. | An effective method for plate number recognition | |
| US8351662B2 (en) | System and method for face verification using video sequence | |
| CN109740424A (en) | Traffic violations recognition methods and Related product | |
| CN103324930B (en) | A kind of registration number character dividing method based on grey level histogram binaryzation | |
| CN104200210B (en) | A kind of registration number character dividing method based on component | |
| CN108491498B (en) | Bayonet image target searching method based on multi-feature detection | |
| CN103927762B (en) | Target vehicle automatic tracking method and device | |
| CN105893510A (en) | Video structurization system and target search method thereof | |
| CN108319952B (en) | Vehicle feature extraction method and device | |
| CN108694399B (en) | License plate recognition method, device and system | |
| CN106600977A (en) | Parking violation detection method and system based on multi-feature identification | |
| CN107194393B (en) | Method and device for detecting temporary license plate | |
| CN107392139A (en) | A kind of method for detecting lane lines and terminal device based on Hough transformation | |
| US20170243067A1 (en) | Side window detection through use of spatial probability maps | |
| CN112257541A (en) | License plate recognition method, electronic device and computer-readable storage medium | |
| CN111915583A (en) | Vehicle and pedestrian detection method based on vehicle-mounted thermal infrared imager in complex scene | |
| CN103699880A (en) | Internet of things-based traffic violation vehicle license plate detection and identification method | |
| CN114708547A (en) | Vehicle weight recognition method and device, computer equipment and storage medium | |
| CN110766009A (en) | Tail plate identification method and device and computer readable storage medium | |
| CN116740661B (en) | Method for reversely tracking Mongolian vehicle based on face recognition | |
| Li et al. | A novel approach for vehicle detection using an AND–OR-graph-based multiscale model | |
| CN111476245A (en) | Vehicle left-turn violation detection method and device, computer equipment and storage medium | |
| CN108647679B (en) | Car logo identification method based on car window coarse positioning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |