CN116153091B - Intelligent epidemic prevention-based vehicle rapid passing method - Google Patents
Intelligent epidemic prevention-based vehicle rapid passing method Download PDFInfo
- Publication number
- CN116153091B CN116153091B CN202310035504.6A CN202310035504A CN116153091B CN 116153091 B CN116153091 B CN 116153091B CN 202310035504 A CN202310035504 A CN 202310035504A CN 116153091 B CN116153091 B CN 116153091B
- Authority
- CN
- China
- Prior art keywords
- license plate
- photo
- color
- vehicle
- feature
- 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 31
- 230000002265 prevention Effects 0.000 title claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims abstract description 11
- 239000003086 colorant Substances 0.000 claims abstract description 9
- 238000007689 inspection Methods 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—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
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/18105—Extraction of features or characteristics of the image related to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
-
- 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
Abstract
The invention discloses a vehicle rapid passing method based on intelligent epidemic prevention, which comprises the following steps: s1: acquiring a real-time vehicle photo of a vehicle in a license plate recognition area, and recognizing the position of a license plate in the real-time vehicle photo to obtain a license plate photo; s2: obtaining license plate colors and license plate numbers of license plate photos; s3: and (5) matching the license plate number with the license plate color, if the license plate number is matched, releasing, otherwise, performing manual inspection. According to the vehicle rapid passing method, the license plate color is identified by constructing the model, and the license plate number is identified by constructing the feature matrix, so that the license plate is accurately identified, the false detection rate of license plate identification equipment is reduced, the situation that epidemic prevention entrances and exits are misplaced due to inaccurate physical license plate information acquired by a camera or manual is avoided, and the matching accuracy is improved.
Description
Technical Field
The invention belongs to the technical field of vehicle management, and particularly relates to a vehicle rapid passing method based on intelligent epidemic prevention.
Background
At present, the epidemic situation of vehicles at a high-speed gateway or a city core gateway is checked by a manual checking mode to check whether the vehicles are vehicles in the city, and the situations of the vehicles cannot be quickly checked, so that traffic jam is caused. And the special person is required to watch for 24 hours in a very long period, and the non-zero contact and the labor input cost are high.
Disclosure of Invention
The invention provides a vehicle rapid passing method based on intelligent epidemic prevention in order to solve the problems.
The technical scheme of the invention is as follows: a vehicle rapid passing method based on intelligent epidemic prevention comprises the following steps:
s1: acquiring a real-time vehicle photo of a vehicle in a license plate recognition area, and recognizing the position of a license plate in the real-time vehicle photo to obtain a license plate photo;
s2: obtaining license plate colors and license plate numbers of license plate photos;
s3: and (5) matching the license plate number with the license plate color, if the license plate number is matched, releasing, otherwise, performing manual inspection.
Further, step S1 comprises the sub-steps of:
s11: acquiring a real-time vehicle photograph of a vehicle in a license plate recognition area;
s12: carrying out gray scale treatment on the real-time vehicle photo to obtain a final vehicle photo;
s13: and identifying four license plate vertexes in the final vehicle photo, and determining the position of the license plate according to the four license plate vertexes to obtain the license plate photo.
Further, in step S12, the calculation formula for performing the gradation process is:
wherein G represents the gray value of each pixel point after gray processing, P represents the pixel mean value, and P min Representing the minimum value of each pixel, P max The maximum value of each pixel is represented, and beta represents a preset gray threshold.
Further, in step S13, the specific method for identifying the four license plate vertices in the final vehicle photograph is as follows: performing binarization processing on the final vehicle photo, and determining a first horizontal line, a second horizontal line, a first vertical line and a second vertical line of the final vehicle photo after the binarization processing by using a quick communication region marking method; the intersection point of the first horizontal line and the first vertical line is used as a first license plate vertex, the intersection point of the first horizontal line and the second vertical line is used as a second license plate vertex, the intersection point of the second horizontal line and the first vertical line is used as a third license plate vertex, and the intersection point of the second horizontal line and the second vertical line is used as a fourth license plate vertex.
Further, in step S2, the specific method for identifying the license plate color is as follows: and constructing a license plate color recognition model, taking a license plate photo as input of the license plate color recognition model, and recognizing the license plate color.
Further, in step S2, the license plate color recognition model includes a feature extraction layer, a feature connection layer, and a color recognition layer that are sequentially connected;
the feature extraction layer is used for extracting color features of license plate photos; the characteristic connecting layer is used for splicing color characteristics; the color recognition layer is used for recognizing license plate colors according to the spliced color features.
Further, the specific method for extracting the color features of the license plate photo by the feature extraction layer comprises the following steps: constructing a feature matrix of the license plate photo, carrying out feature value decomposition on the feature matrix to obtain a feature vector corresponding to the maximum feature value, and taking the feature vector as a color feature; wherein, the p-th row and the q-th column element A in the feature matrix of the license plate photo pq The expression of (2) is:
wherein p, q=1, 2, …, L, α 1 ,α 2 ,,…,α L The wavelet characteristics of the pixel points of the L license plate photos are represented, and sigma represents the overshoot parameters.
Further, the expression of the Loss function Loss of the color recognition layer is:
wherein m is i Represents the ith color feature, m i-1 Indicating the i-1 th color feature,mu representing the s-th pixel point of license plate photo s And the s-1 th pixel point mu s-1 Is a distance of (3).
Further, in step S2, the specific method for obtaining the license plate number of the license plate photo includes: and (3) setting a region with gray level larger than a set threshold value in the license plate photo to be 1, and carrying out digital identification according to a region with pixel proportion exceeding 30% of total pixels in the region where the gray level is set to be 1, so as to obtain the license plate number.
Further, in step S3, if the license plate number and the license plate color are both consistent with the white list database, the matching is passed and released, otherwise, the manual inspection is performed.
The beneficial effects of the invention are as follows:
(1) According to the vehicle rapid passing method, the license plate color is identified by constructing the model, and the license plate number is identified by constructing the feature matrix, so that the license plate is accurately identified, the false detection rate of license plate identification equipment is reduced, the situation that epidemic prevention entrances and exits are misplaced due to inaccurate physical license plate information acquired by a camera or manual is avoided, and the matching accuracy is improved;
(2) According to the rapid vehicle passing method, the license plate photos are collected through the camera to identify the license plate, so that traffic jam caused by epidemic situation inspection of vehicles is avoided for the situation that vehicles at a high-speed entrance or an urban core entrance are more, and the vehicles meeting the requirements pass through the entrance rapidly.
Drawings
FIG. 1 is a flow chart of a fast vehicle passing method based on intelligent epidemic prevention.
Detailed Description
Embodiments of the present invention are further described below with reference to the accompanying drawings.
As shown in fig. 1, the invention provides a vehicle rapid passing method based on intelligent epidemic prevention, which comprises the following steps:
s1: acquiring a real-time vehicle photo of a vehicle in a license plate recognition area, and recognizing the position of a license plate in the real-time vehicle photo to obtain a license plate photo;
s2: obtaining license plate colors and license plate numbers of license plate photos;
s3: and (5) matching the license plate number with the license plate color, if the license plate number is matched, releasing, otherwise, performing manual inspection.
In an embodiment of the present invention, step S1 comprises the following sub-steps:
s11: acquiring a real-time vehicle photograph of a vehicle in a license plate recognition area;
s12: carrying out gray scale treatment on the real-time vehicle photo to obtain a final vehicle photo;
s13: and identifying four license plate vertexes in the final vehicle photo, and determining the position of the license plate according to the four license plate vertexes to obtain the license plate photo.
In the embodiment of the present invention, in step S12, the calculation formula for performing the gray scale processing is:
wherein G represents the gray value of each pixel point after gray processing, P represents the pixel mean value, and P min Representing the minimum value of each pixel, P max The maximum value of each pixel is represented, and beta represents a preset gray threshold.
In the embodiment of the present invention, in step S13, the specific method for identifying the vertices of four license plates in the final vehicle photograph is as follows: performing binarization processing on the final vehicle photo, and determining a first horizontal line, a second horizontal line, a first vertical line and a second vertical line of the final vehicle photo after the binarization processing by using a quick communication region marking method; the intersection point of the first horizontal line and the first vertical line is used as a first license plate vertex, the intersection point of the first horizontal line and the second vertical line is used as a second license plate vertex, the intersection point of the second horizontal line and the first vertical line is used as a third license plate vertex, and the intersection point of the second horizontal line and the second vertical line is used as a fourth license plate vertex.
In the embodiment of the present invention, in step S2, the specific method for identifying the license plate color is as follows: and constructing a license plate color recognition model, taking a license plate photo as input of the license plate color recognition model, and recognizing the license plate color.
License plate colors can be broadly divided into 5 categories: white, including local police vehicles, liberation army vehicles, armed police vehicles, etc.; black, including a collarband, foreign vehicle, etc.; blue, including small vehicles; yellow, including large-scale cars, trailers, motorcycles, driving school instructional cars, concrete cars, container trucks, and the like; the green comprises white-green mixing of small new energy vehicles, yellow-green mixing of large new energy vehicles, green cards of agricultural vehicles and the like. The method has high accuracy and quick license plate color recognition, and plays an important role in license plate number recognition, auxiliary vehicle model judgment and the like.
In the embodiment of the invention, in step S2, a license plate color recognition model comprises a feature extraction layer, a feature connection layer and a color recognition layer which are sequentially connected;
the feature extraction layer is used for extracting color features of license plate photos; the characteristic connecting layer is used for splicing color characteristics; the color recognition layer is used for recognizing license plate colors according to the spliced color features.
In the embodiment of the invention, the specific method for extracting the color features of the license plate photo by the feature extraction layer comprises the following steps: constructing a feature matrix of the license plate photo, carrying out feature value decomposition on the feature matrix to obtain a feature vector corresponding to the maximum feature value, and taking the feature vector as a color feature; wherein, the p-th row and the q-th column element A in the feature matrix of the license plate photo pq The expression of (2) is:
wherein p, q=1, 2, …, L, α 1 ,α 2 ,,…,α L The wavelet characteristics of the pixel points of the L license plate photos are represented, and sigma represents the overshoot parameters.
In the embodiment of the present invention, the expression of the Loss function Loss of the color recognition layer is:
wherein m is i Represents the ith color feature, m i-1 Indicating the i-1 th color feature,mu representing the s-th pixel point of license plate photo s And the s-1 th pixel point mu s-1 Is a distance of (3).
In the embodiment of the invention, in step S2, the specific method for obtaining the license plate number of the license plate photo is as follows: and (3) setting a region with gray level larger than a set threshold value in the license plate photo to be 1, and carrying out digital identification according to a region with pixel proportion exceeding 30% of total pixels in the region where the gray level is set to be 1, so as to obtain the license plate number.
In the embodiment of the invention, in step S3, if the license plate number and the license plate color are consistent with the white list database, the matching is passed and released, otherwise, the manual inspection is carried out. The identified license plate number and license plate color information are transmitted to an epidemic prevention big data platform through a network, the epidemic prevention big data platform carries out white list matching, if a white list vehicle is returned to meet the requirements, the barrier gate is notified to open, the display screen notifies the vehicle to pass, if the vehicle does not return to the requirements, the vehicle does not pass, and the display screen notifies the vehicle to lean on the right lane to check.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (3)
1. A vehicle rapid passing method based on intelligent epidemic prevention is characterized by comprising the following steps:
s1: acquiring a real-time vehicle photo of a vehicle in a license plate recognition area, and recognizing the position of a license plate in the real-time vehicle photo to obtain a license plate photo;
s2: obtaining license plate colors and license plate numbers of license plate photos;
s3: matching license plate numbers with license plate colors, if the license plate numbers are matched, releasing, otherwise, performing manual inspection;
said step S1 comprises the sub-steps of:
s11: acquiring a real-time vehicle photograph of a vehicle in a license plate recognition area;
s12: carrying out gray scale treatment on the real-time vehicle photo to obtain a final vehicle photo;
s13: identifying four license plate vertexes in the final vehicle photo, and determining the position of the license plate according to the four license plate vertexes to obtain the license plate photo;
in the step S12, the calculation formula for performing the gray scale processing is as follows:
wherein G represents the gray value of each pixel point after gray processing, P represents the pixel mean value, and P min Representing the minimum value of each pixel, P max Representing the maximum value of each pixel point, and beta represents a preset gray threshold;
in the step S13, the specific method for identifying the four license plate vertices in the final vehicle photograph is as follows: performing binarization processing on the final vehicle photo, and determining a first horizontal line, a second horizontal line, a first vertical line and a second vertical line of the final vehicle photo after the binarization processing by using a quick communication region marking method; taking the intersection point of the first horizontal line and the first vertical line as a first license plate vertex, taking the intersection point of the first horizontal line and the second vertical line as a second license plate vertex, taking the intersection point of the second horizontal line and the first vertical line as a third license plate vertex, and taking the intersection point of the second horizontal line and the second vertical line as a fourth license plate vertex;
in the step S2, the specific method for identifying the license plate color is as follows: constructing a license plate color recognition model, taking a license plate photo as input of the license plate color recognition model, and recognizing the license plate color;
in the step S2, the license plate color recognition model includes a feature extraction layer, a feature connection layer and a color recognition layer which are sequentially connected;
the feature extraction layer is used for extracting color features of license plate photos; the characteristic connecting layer is used for splicing color characteristics; the color recognition layer is used for recognizing license plate colors according to the spliced color features;
the specific method for extracting the color features of the license plate photo by the feature extraction layer comprises the following steps: constructing a feature matrix of the license plate photo, carrying out feature value decomposition on the feature matrix to obtain a feature vector corresponding to the maximum feature value, and taking the feature vector as a color feature; wherein, the p-th row and the q-th column element A in the feature matrix of the license plate photo pq The expression of (2) is:
wherein p, q=1, 2, …, L, α 1 ,α 2 ,,…,α L The wavelet characteristics of pixel points of L license plate photos are represented, and sigma represents overshoot parameters;
the expression of the Loss function Loss of the color recognition layer is:
wherein m is i Represents the ith color feature, m i-1 Indicating the i-1 th color feature,mu representing the s-th pixel point of license plate photo s And the s-1 th pixel point mu s-1 Is a distance of (3).
2. The rapid transit method of vehicles based on intelligent epidemic prevention according to claim 1, wherein in the step S2, the specific method for obtaining license plate numbers of license plate photos is as follows: and (3) setting a region with gray level larger than a set threshold value in the license plate photo to be 1, and carrying out digital identification according to a region with pixel proportion exceeding 30% of total pixels in the region where the gray level is set to be 1, so as to obtain the license plate number.
3. The rapid transit method of vehicles based on intelligent epidemic prevention according to claim 1, wherein in the step S3, if the license plate number and the license plate color are both consistent with the white list database, the matching is passed and released, otherwise, the manual inspection is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310035504.6A CN116153091B (en) | 2023-01-10 | 2023-01-10 | Intelligent epidemic prevention-based vehicle rapid passing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310035504.6A CN116153091B (en) | 2023-01-10 | 2023-01-10 | Intelligent epidemic prevention-based vehicle rapid passing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116153091A CN116153091A (en) | 2023-05-23 |
| CN116153091B true CN116153091B (en) | 2024-02-06 |
Family
ID=86355613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310035504.6A Active CN116153091B (en) | 2023-01-10 | 2023-01-10 | Intelligent epidemic prevention-based vehicle rapid passing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116153091B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934963A (en) * | 2017-12-16 | 2019-06-25 | 郑州灵珑信息科技有限公司 | Based on Car license recognition around city high speed Toll Free method |
| CN113157774A (en) * | 2021-04-30 | 2021-07-23 | 贵州数据宝网络科技有限公司 | Vehicle cargo carrying and bearing monitoring method and system |
| WO2022111355A1 (en) * | 2020-11-30 | 2022-06-02 | 展讯通信（上海）有限公司 | License plate recognition method and apparatus, storage medium and terminal |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9466000B2 (en) * | 2011-05-19 | 2016-10-11 | The Regents Of The University Of California | Dynamic Bayesian Networks for vehicle classification in video |
-
2023
- 2023-01-10 CN CN202310035504.6A patent/CN116153091B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934963A (en) * | 2017-12-16 | 2019-06-25 | 郑州灵珑信息科技有限公司 | Based on Car license recognition around city high speed Toll Free method |
| WO2022111355A1 (en) * | 2020-11-30 | 2022-06-02 | 展讯通信（上海）有限公司 | License plate recognition method and apparatus, storage medium and terminal |
| CN113157774A (en) * | 2021-04-30 | 2021-07-23 | 贵州数据宝网络科技有限公司 | Vehicle cargo carrying and bearing monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116153091A (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rasheed et al. | Automated number plate recognition using hough lines and template matching | |
| WO2019223586A1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| CN109858389B (en) | Vertical ladder people counting method and system based on deep learning | |
| CN110969160A (en) | License plate image correction and recognition method and system based on deep learning | |
| CN110414320B (en) | Method and system for safety production supervision | |
| CN111079640B (en) | Vehicle type identification method and system based on automatic amplification sample | |
| CN110689724B (en) | Automatic motor vehicle zebra crossing present pedestrian auditing method based on deep learning | |
| CN101692313A (en) | Portable vehicle recognition device base on embedded platform | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| Kumar et al. | Automatic vehicle number plate recognition system using machine learning | |
| CN111553355B (en) | Monitoring video-based method for detecting and notifying store outgoing business and managing store owner | |
| CN101567041A (en) | Method for recognizing characters of number plate images of motor vehicles based on trimetric projection | |
| CN111783589A (en) | Complex scene crowd counting method based on scene classification and multi-scale feature fusion | |
| CN107818321A (en) | A kind of watermark date recognition method for vehicle annual test | |
| CN110245583A (en) | A kind of intelligent identification Method of Vehicular exhaust survey report | |
| CN109034024B (en) | Logistics vehicle type classification and identification method based on image target detection | |
| CN111488854A (en) | Automatic identification and classification method for road traffic signs | |
| CN107798879A (en) | A kind of method of Intelligent Recognition fake-licensed car | |
| CN109993058A (en) | The recognition methods of road signs based on multi-tag classification | |
| CN115171013A (en) | Vehicle scheduling system and method based on intelligent traffic accident rescue | |
| CN116153091B (en) | Intelligent epidemic prevention-based vehicle rapid passing method | |
| CN113989874A (en) | Highway construction safety accident early warning system and method | |
| CN116229396B (en) | High-speed pavement disease identification and warning method | |
| CN111046822A (en) | Large vehicle anti-theft method based on artificial intelligence video identification | |
| CN115995056A (en) | Automatic bridge disease identification method based on deep learning |
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 |