CN111752938A - License plate information acquisition and repair method and system - Google Patents
License plate information acquisition and repair method and system Download PDFInfo
- Publication number
- CN111752938A CN111752938A CN202010745743.7A CN202010745743A CN111752938A CN 111752938 A CN111752938 A CN 111752938A CN 202010745743 A CN202010745743 A CN 202010745743A CN 111752938 A CN111752938 A CN 111752938A
- Authority
- CN
- China
- Prior art keywords
- license plate
- information
- vehicle
- rule
- plate information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- 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
- G06V20/63—Scene text, e.g. street names
-
- 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
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a license plate information acquisition and repair method and a license plate information acquisition and repair system, and belongs to the technical field of computers. By adopting the license plate information acquisition and restoration method and system, on the basis of recognizing the vehicle image and the license plate image in the vehicle photo, the initial license plate information is obtained first, then the initial license plate information is analyzed and restored based on the numbering rule, the rule is automatically generated to optimize the license plate information, so that the automatic, convenient and high-accuracy license plate information acquisition and restoration are realized, the whole process is free from manual operation, the automation degree is high, the license plate recognition accuracy of the vehicle photo shot by the road monitoring equipment can be greatly improved, and convenience is brought to subsequent data summarization and big data application.
Description
Technical Field
The invention relates to the technical field of computers, in particular to the technical field of image recognition, and specifically relates to a license plate information acquisition and restoration method and a license plate information acquisition and restoration system.
Background
By 28 days 12 and 2018, the total mileage of the Chinese expressway reaches 14 ten thousand kilometers, and is the first place around the world. Over the 14 kilo-kilometer aorta, there are over approximately 1 million multiple toll stations. The toll station continuously collects manual or ETC toll data to the provincial high-speed system through the data acquisition equipment, and the provincial high-speed system can synchronize the high-speed data passing toll details to a high-speed large database of a traffic department through a public network or a private network in real time. In the whole data generation process, the toll collector judges the types of the payment vehicles and the payment-free vehicles and inputs vehicle type operation to the computer through a toll keyboard, the toll computer simultaneously carries out voice quotation, the lane quotation machine sends out quotation prompt tones, and the digital tube of the quotation machine displays the amount of money to be paid and the vehicle type. The driver finishes payment, a toll collector operates the vehicle to pass through the toll collection keyboard, the bill printer prints a bill at the moment, the barrier of the barrier gate is automatically lifted, the lane captures a vehicle image on which the related information of the toll collection is superposed, and the toll collection data is uploaded to the server through the network. In addition, the accuracy of systems and identification equipment of all toll stations is inconsistent, so that the data cannot avoid various conditions such as license plate number and axle number identification errors, transmission errors, manual errors and the like.
The main problem is that the license plate information of the vehicle image is not accurately identified, so that the image cannot correspond to the toll data one by one, and the system has a lot of data which need to be corrected and repaired further, thereby reducing the overall accuracy and reliability of the system.
Therefore, how to provide an automatic, convenient and high-accuracy license plate information acquisition and repair method becomes an urgent problem to be solved in the field.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide the license plate information acquisition and restoration method and the license plate information acquisition and restoration system which are automatic, convenient, high in accuracy, free of manual intervention and very beneficial to data summarization and big data application.
In order to achieve the above object, the license plate information collection and repair method of the present invention includes:
(10) recognizing a vehicle image and a license plate image in the vehicle photo;
(20) recognizing the license plate image to obtain initial license plate information;
(30) and analyzing and repairing the initial license plate information based on the numbering rule to generate rule optimized license plate information.
In the license plate information acquisition and repair method, the step (20) specifically comprises the following steps:
(20-1) identifying the color of the license plate and determining the type information of the license plate;
(20-2) identifying the license plate characters, and determining special license plate information and license plate province information;
and (22-3) identifying the letters and the numbers of the license plate and determining the number information of the license plate.
In the license plate information collection and repair method, the step (30) specifically comprises the following steps:
(30-1) respectively comparing the vehicle image with the license plate type information and the special license plate information, judging whether the vehicle image is consistent with the license plate type information or not, if yes, entering the next step, and if not, sending a prompt that the vehicle type of the license plate is not consistent;
(30-2) determining a corresponding numbering rule according to the license plate type information and the license plate province information;
(30-3) judging whether the license plate number information is correct or not according to the numbering rule, and if not, entering the step (30-4); if the license plate number information is correct, the license plate number information is used as the rule to optimize the license plate information;
(30-4) judging whether the incorrect license plate number information can be automatically repaired, if so, repairing, and generating the rule optimized license plate information; if not, entering the step (30-5);
and (30-5) sending out a prompt that the license plate does not accord with the numbering rule.
In the license plate information acquisition and repair method, the step (30-2) specifically comprises the following steps:
determining a vehicle type numbering rule according to the license plate type information;
and determining a province numbering rule according to the license plate province information.
In the license plate information acquisition and repair method, the step (30-3) specifically comprises the following steps:
judging whether the license plate number information is correct or not according to the vehicle type numbering rule, and if not, entering the step (30-4); if the number is correct, judging whether the license plate number information is correct according to the province number rule, and if the number is incorrect, entering the step (30-4); if the license plate number information is correct, the license plate number information is used as the rule to optimize the license plate information.
In the license plate information collecting and repairing method, the step (30-4) of judging whether the incorrect license plate number information can be automatically repaired specifically comprises the following steps:
and judging whether the incorrect license plate number information accords with an automatic repair condition, wherein the automatic repair condition comprises a corresponding relation between the incorrect license plate number information and the correct license plate number information.
In the license plate information collection and repair method, in the state that the automatic repair cannot be performed in the step (30-4), the method further comprises the following steps:
identifying corresponding historical data similar to the vehicle image and the license plate image in a database, and if the historical data can be identified, entering the historical data to automatically repair the incorrect license plate number information and generating the rule optimized license plate information; if the historical data cannot be identified, the method proceeds to step (30-5).
In the license plate information collection and repair method, the historical data comprises a plurality of vehicle pictures shot at different positions of the same vehicle at the same time and a plurality of vehicle pictures shot at the same time and in the similar places.
The invention also provides a license plate information acquisition and repair system which comprises a processor and a memory, wherein the memory stores an application program, and when the processor reads and runs the application program, the license plate information acquisition and repair method is realized.
By adopting the license plate information acquisition and restoration method and system, on the basis of recognizing the vehicle image and the license plate image in the vehicle photo, the initial license plate information is obtained first, then the initial license plate information is analyzed and restored based on the numbering rule, the rule is automatically generated to optimize the license plate information, so that the automatic, convenient and high-accuracy license plate information acquisition and restoration are realized, the whole process is free from manual operation, the automation degree is high, the license plate recognition accuracy of the vehicle photo shot by the road monitoring equipment can be greatly improved, and convenience is brought to subsequent data summarization and big data application.
Drawings
Fig. 1 is a flowchart of steps of a license plate information collection and repair method according to the present invention.
Detailed Description
In order to clearly understand the technical contents of the present invention, the following examples are given in detail.
Fig. 1 is a flowchart illustrating steps of a license plate information collection and repair method according to the present invention.
In one embodiment, the license plate information collection and repair method includes:
(10) recognizing a vehicle image and a license plate image in the vehicle photo;
(20) recognizing the license plate image to obtain initial license plate information;
(30) and analyzing and repairing the initial license plate information based on the numbering rule to generate rule optimized license plate information.
In a preferred embodiment, the step (20) specifically comprises the following steps:
(20-1) identifying the color of the license plate and determining the type information of the license plate;
(20-2) identifying the license plate characters, and determining special license plate information and license plate province information;
and (22-3) identifying the letters and the numbers of the license plate and determining the number information of the license plate.
In a further preferred embodiment, the step (30) specifically comprises the following steps:
(30-1) respectively comparing the vehicle image with the license plate type information and the special license plate information, judging whether the vehicle image is consistent with the license plate type information or not, if yes, entering the next step, and if not, sending a prompt that the vehicle type of the license plate is not consistent;
(30-2) determining a corresponding numbering rule according to the license plate type information and the license plate province information;
(30-3) judging whether the license plate number information is correct or not according to the numbering rule, and if not, entering the step (30-4); if the license plate number information is correct, the license plate number information is used as the rule to optimize the license plate information;
(30-4) judging whether the incorrect license plate number information can be automatically repaired, if so, repairing, and generating the rule optimized license plate information; if not, entering the step (30-5);
and (30-5) sending out a prompt that the license plate does not accord with the numbering rule.
In a further preferred embodiment, the step (30-2) comprises the following steps:
determining a vehicle type numbering rule according to the license plate type information;
and determining a province numbering rule according to the license plate province information.
The step (30-3) specifically comprises the following steps:
judging whether the license plate number information is correct or not according to the vehicle type numbering rule, and if not, entering the step (30-4); if the number is correct, judging whether the license plate number information is correct according to the province number rule, and if the number is incorrect, entering the step (30-4); if the license plate number information is correct, the license plate number information is used as the rule to optimize the license plate information.
In another preferred embodiment, the judging whether the incorrect license plate number information can be automatically repaired in the step (30-4) specifically includes:
and judging whether the incorrect license plate number information accords with an automatic repair condition, wherein the automatic repair condition comprises a corresponding relation between the incorrect license plate number information and the correct license plate number information.
In a further preferred embodiment, in the state where it is determined in the step (30-4) that the automatic repair is not possible, the method further includes the steps of:
identifying corresponding historical data similar to the vehicle image and the license plate image in a database, and if the historical data can be identified, entering the historical data to automatically repair the incorrect license plate number information and generating the rule optimized license plate information; if the historical data cannot be identified, the method proceeds to step (30-5).
In a more preferred embodiment, the historical data includes a plurality of vehicle photographs taken of the same vehicle at different locations at the same time and a plurality of vehicle photographs taken of the same vehicle at similar times and locations.
The invention also discloses a license plate information acquisition and repair system which comprises a processor and a memory, wherein the memory stores an application program, and when the processor reads and runs the application program, the license plate information acquisition and repair method is realized.
In practical application, the license plate information acquisition and restoration method and the license plate information acquisition and restoration system can realize restoration and cleaning of original license plate data and provide a basis for forming a vehicle driving data big data system associated with a license plate and subsequent big data application.
Firstly, the license plate information is subjected to basic logic rule cleaning, including the length, color, number and letter combination rules and the like of the license plate, and finally, logically invalid license plate information data is marked.
The logic rule cleaning comprises the following steps:
regular cleaning of vehicle type license plate
The method comprises the steps of respectively processing new energy vehicles, trucks, buses, coaches, trailers and the like according to corresponding cleaning rules. If the third position is D/F (small) or the last position is D/F (large), and one new position is added to the license plate number, the new energy vehicle is used; the mark of the last place of the license plate number as the police is the police car; the last place of the license plate number is marked as a trailer; the last label of the license plate number "port" is a port car, and so on.
(II) regular cleaning of license plate in region
The rule of the Beijing license plate is as follows: [ Jing A Jing B Jing C Jing D Jing E Jing F Jing G Jing H Jing J Jing K Jing L Jing M Jing N Jing P Jing Q Jing Y ] + [ 5-digit English ], and the license plate containing no English letters "I" and "O" is valid, and other Beijing license plates can be marked as invalid data. Under the condition of marking invalid data, the 'I' can be automatically repaired to be '1', whether the business logic of the Beijing license plate is met or not is judged by combining with the rule code 001002, if yes, the repair is finished, and if not, the repair is not carried out, and the marking as the invalid data is kept. Other provinces and special vehicles, foreign vehicles and the like can be cleaned in sequence by adopting similar rules.
(III) Association verification and repair
The license plate information can be repaired by using the information of the same vehicle stored in the system. For example, two pictures of the head and the tail of one vehicle are taken at the same high-speed toll road junction, and the other license plate information which is identified as a logic error can be repaired according to the license plate information which is correctly identified. On the other hand, the driving route can be simulated and generated according to the vehicle passing record, the logically accurate but actually wrong license plate number can be corrected through the data of the entrance and the exit, for example, the data of the vehicle when the vehicle enters the high speed is used for repairing the data when the vehicle exits the high speed, and the like.
By adopting the license plate information acquisition and restoration method and system, on the basis of recognizing the vehicle image and the license plate image in the vehicle photo, the initial license plate information is obtained first, then the initial license plate information is analyzed and restored based on the numbering rule, the rule is automatically generated to optimize the license plate information, so that the automatic, convenient and high-accuracy license plate information acquisition and restoration are realized, the whole process is free from manual operation, the automation degree is high, the license plate recognition accuracy of the vehicle photo shot by the road monitoring equipment can be greatly improved, and convenience is brought to subsequent data summarization and big data application.
In this specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Claims (9)
1. A license plate information acquisition and repair method is characterized by comprising the following steps:
(10) recognizing a vehicle image and a license plate image in the vehicle photo;
(20) recognizing the license plate image to obtain initial license plate information;
(30) and analyzing and repairing the initial license plate information based on the numbering rule to generate rule optimized license plate information.
2. The license plate information collection and repair method according to claim 1, wherein the step (20) specifically comprises the steps of:
(20-1) identifying the color of the license plate and determining the type information of the license plate;
(20-2) identifying the license plate characters, and determining special license plate information and license plate province information;
and (22-3) identifying the letters and the numbers of the license plate and determining the number information of the license plate.
3. The license plate information collection and repair method according to claim 2, wherein the step (30) specifically comprises the steps of:
(30-1) respectively comparing the vehicle image with the license plate type information and the special license plate information, judging whether the vehicle image is consistent with the license plate type information or not, if yes, entering the next step, and if not, sending a prompt that the vehicle type of the license plate is not consistent;
(30-2) determining a corresponding numbering rule according to the license plate type information and the license plate province information;
(30-3) judging whether the license plate number information is correct or not according to the numbering rule, and if not, entering the step (30-4); if the license plate number information is correct, the license plate number information is used as the rule to optimize the license plate information;
(30-4) judging whether the incorrect license plate number information can be automatically repaired, if so, repairing, and generating the rule optimized license plate information; if not, entering the step (30-5);
and (30-5) sending out a prompt that the license plate does not accord with the numbering rule.
4. The license plate information collection and repair method according to claim 3, wherein the step (30-2) specifically comprises the steps of:
determining a vehicle type numbering rule according to the license plate type information;
and determining a province numbering rule according to the license plate province information.
5. The license plate information collection and repair method according to claim 4, wherein the step (30-3) specifically comprises the steps of:
judging whether the license plate number information is correct or not according to the vehicle type numbering rule, and if not, entering the step (30-4); if the number is correct, judging whether the license plate number information is correct according to the province number rule, and if the number is incorrect, entering the step (30-4); if the license plate number information is correct, the license plate number information is used as the rule to optimize the license plate information.
6. The license plate information collection and repair method according to claim 3, wherein the step (30-4) of determining whether the incorrect license plate number information can be automatically repaired specifically comprises:
and judging whether the incorrect license plate number information accords with an automatic repair condition, wherein the automatic repair condition comprises a corresponding relation between the incorrect license plate number information and the correct license plate number information.
7. The license plate information collection and repair method according to claim 3, wherein in the state where it is determined in the step (30-4) that automatic repair cannot be performed, further comprising the steps of:
identifying corresponding historical data similar to the vehicle image and the license plate image in a database, and if the historical data can be identified, entering the historical data to automatically repair the incorrect license plate number information and generating the rule optimized license plate information; if the historical data cannot be identified, the method proceeds to step (30-5).
8. The license plate information collection and repair method of claim 3, wherein the historical data comprises a plurality of vehicle photos taken of the same vehicle at different locations at the same time and a plurality of vehicle photos taken of the same vehicle at similar times and locations.
9. A license plate information collection and repair system, comprising a processor and a memory, wherein the memory stores an application program, and when the processor reads and runs the application program, the license plate information collection and repair method according to any one of claims 1 to 8 is implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010745743.7A CN111752938A (en) | 2020-07-29 | 2020-07-29 | License plate information acquisition and repair method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010745743.7A CN111752938A (en) | 2020-07-29 | 2020-07-29 | License plate information acquisition and repair method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111752938A true CN111752938A (en) | 2020-10-09 |
Family
ID=72712413
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010745743.7A Pending CN111752938A (en) | 2020-07-29 | 2020-07-29 | License plate information acquisition and repair method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111752938A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860412A (en) * | 2020-07-29 | 2020-10-30 | 贵州数据宝网络科技有限公司 | License plate information repairing method and system based on historical data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732205A (en) * | 2015-03-09 | 2015-06-24 | 江苏省邮电规划设计院有限责任公司 | System for checking expressway toll evasion |
| CN108416878A (en) * | 2018-03-16 | 2018-08-17 | 西安艾润物联网技术服务有限责任公司 | Car plate method of calibration, device and computer readable storage medium |
| CN109523790A (en) * | 2018-10-26 | 2019-03-26 | 安徽四创电子股份有限公司 | A kind of license plate error correction method based on license plate similarity |
-
2020
- 2020-07-29 CN CN202010745743.7A patent/CN111752938A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732205A (en) * | 2015-03-09 | 2015-06-24 | 江苏省邮电规划设计院有限责任公司 | System for checking expressway toll evasion |
| CN108416878A (en) * | 2018-03-16 | 2018-08-17 | 西安艾润物联网技术服务有限责任公司 | Car plate method of calibration, device and computer readable storage medium |
| CN109523790A (en) * | 2018-10-26 | 2019-03-26 | 安徽四创电子股份有限公司 | A kind of license plate error correction method based on license plate similarity |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860412A (en) * | 2020-07-29 | 2020-10-30 | 贵州数据宝网络科技有限公司 | License plate information repairing method and system based on historical data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2858919C (en) | License plate recognition | |
| CN109191605B (en) | Highway charging rate accuracy evaluation method considering charging path | |
| US20130132166A1 (en) | Smart toll network for improving performance of vehicle identification systems | |
| US8738525B2 (en) | Method and system for processing vehicular violations | |
| CN108777021B (en) | Bill identification method and system based on scanner mixed scanning | |
| CN110969160A (en) | License plate image correction and recognition method and system based on deep learning | |
| BRPI0613569A2 (en) | electronic vehicle identification | |
| CN111369801B (en) | Vehicle identification method, device, equipment and storage medium | |
| Ravirathinam et al. | Automatic license plate recognition for indian roads using faster-rcnn | |
| CN115810134B (en) | Image acquisition quality inspection method, system and device for vehicle insurance anti-fraud | |
| CN110414632A (en) | A kind of information identification storage method for hand-written logistics document | |
| CN111752938A (en) | License plate information acquisition and repair method and system | |
| CN111860412A (en) | License plate information repairing method and system based on historical data | |
| CN110991442A (en) | High-accuracy highway license plate cloud identification method | |
| CN111179452A (en) | ETC channel-based bus fee deduction system and method | |
| KR20110028925A (en) | System and method for collecting toll road fee | |
| CN115131564A (en) | Vehicle component damage detection method based on artificial intelligence and related equipment | |
| CN114882393A (en) | Road reverse running and traffic accident event detection method based on target detection | |
| CN113239881A (en) | Invoice reimbursement method | |
| Welekar et al. | Analysis of Rules Violation & Efficient E-Challan Generation Using OCR In Real Time Traffic | |
| CN111768545A (en) | Traffic safety monitoring method and system | |
| CN111179044A (en) | Bill reimbursement method and device | |
| CN110598922A (en) | Vehicle oil charge reimbursement method and device, server and electronic equipment | |
| JPS5843081A (en) | Fee collecting system | |
| CN115905349A (en) | Automatic matching method for bus card swiping data of handheld POS machine |
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 |