CN112949643B - Method for improving license plate recognition efficiency in complex scene - Google Patents
Method for improving license plate recognition efficiency in complex scene Download PDFInfo
- Publication number
- CN112949643B CN112949643B CN202110207896.0A CN202110207896A CN112949643B CN 112949643 B CN112949643 B CN 112949643B CN 202110207896 A CN202110207896 A CN 202110207896A CN 112949643 B CN112949643 B CN 112949643B
- Authority
- CN
- China
- Prior art keywords
- camera module
- result
- license plate
- main control
- module
- 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
Images
Classifications
-
- 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
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
Abstract
The invention discloses a method for improving license plate recognition efficiency in a complex scene, which comprises a main control module, a main camera module and an auxiliary camera module, wherein the main camera module comprises a ground sensing module, the auxiliary camera module is formed by combining a plurality of cameras and comprises a shooting camera and a video recording camera, the main control module is respectively connected with the main camera module and the auxiliary camera module, and the main control module is loaded with an image recognition algorithm. The invention adopts the contrast verification mode and the cross recognition effect, only needs to adopt the function of the auxiliary camera module, does not need to additionally add other verification systems, and can greatly reduce the complexity of the system and simultaneously increase the functionality of the auxiliary camera module.
Description
Technical Field
The invention relates to the field of image recognition, in particular to a method for improving license plate recognition efficiency in a complex scene.
Background
The license plate recognition system is an application of computer video image recognition technology in vehicle license plate recognition. License plate recognition is widely applied to highway vehicle management, and is also a main means for recognizing vehicle identities by combining a DSRC technology in an Electronic Toll Collection (ETC) system, the license plate recognition technology requires that a moving automobile license plate can be extracted and recognized from a complex background, information such as license plate numbers and colors of vehicles can be recognized through technologies such as license plate extraction, image preprocessing, feature extraction, license plate character recognition and the like, the latest technical level at present is that the recognition rate of letters and numbers can reach 99.7%, and the recognition rate of Chinese characters can reach 99%.
However, in the image recognition, complex scenes such as basements, indoor parking lots or lifting parking lots always occur, so that the photographed images are blurred and dim, the images processed by the main control module cannot be directly output, a driver needs to continuously drive a vehicle to repeatedly move back and forth in a detection area, the effect of repeated recognition can be achieved, and the situation is unchanged.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for improving the license plate recognition efficiency in a complex scene.
In order to solve the technical problems, the invention provides the following technical scheme:
the invention relates to a method for improving license plate recognition efficiency in a complex scene, which comprises a main control module, a main camera module and an auxiliary camera module, wherein the main camera module comprises a ground sensing module, the auxiliary camera module is formed by combining a plurality of cameras and comprises a shooting camera and a video camera, the main control module is respectively connected with the main camera module and the auxiliary camera module, the main control module is loaded with an image recognition algorithm, and the license plate recognition specifically comprises the following steps:
s1, dynamic triggering, namely after a ground sensing module senses that a vehicle enters a channel, a main camera module is started to recognize, and an auxiliary camera module is started to start to work after sensing that other hardware is excited;
s2, a main camera module identification process:
1) the main camera module shoots the license plate, sends the image to the main control module, identifies the license plate in the image and records the result as A;
2) setting the working state as Default, namely setting the main camera module as a Default state, soft-triggering all cameras in the auxiliary camera module, shooting the license plate, sending an image obtained by shooting the license plate to the main control module, and obtaining a result B;
3) the main control module compares the result A with the result B, obtains an optimal result according to the definition, the identification area and the preset weight, reports the optimal result to the main control module to be C, and processes and forms a final order according to the service of the main control module under the condition that the car is branded;
s3, after the auxiliary camera module is started, the current working state is judged:
a. when the current working state is Default, namely a Default state, outputting a result list identified by the auxiliary camera, outputting a result with the highest reliability according to definition and an identification area after inputting the result list to the main control module, and marking the result as B;
b. when the current working state is RE-REC, namely, the camera shooting is restarted for secondary recognition, firstly judging whether the image state shot by the camera shooting is overtime or not, and directly ending the shooting under the overtime condition; judging whether the vehicle is a licensed vehicle or not in a non-overtime state, reporting the result to a final result C, and directly outputting the final result C;
c. when the current working state is RE-OPEN, namely the camera restarts the secondary rod lifting, firstly judging whether the shooting state is overtime, and directly ending the shooting under the overtime condition; and judging whether the final result is consistent with the final result C or not in the non-overtime state, and directly outputting a rod lifting instruction when the final result is consistent with the final result C.
As a preferable embodiment of the present invention, in the step 3) of the step S2, when the output information of the final result C is insufficient and it is necessary to determine whether the vehicle is a unlicensed vehicle, the method specifically includes the following steps:
if the main control information confirms that the vehicle is a licensed vehicle, outputting the information to a central office, and then manually continuously judging whether the vehicle needs to pay, if not, directly controlling the rod lifting, finishing the operation of the whole process by the main camera module, and finishing the identification; when payment is needed, manually setting the state of the auxiliary camera module as RE-OPEN again, wherein the overtime time is 120s, returning to trigger all the auxiliary cameras again to realize polling trigger, entering the identification process again, and triggering the RE-OPEN working state for RE-shooting the license plate to recheck the output result of the main camera module;
and if the main control information confirms that the vehicle is a unlicensed vehicle, setting the working state to be RE-REC, setting the timeout time to be 30s, returning to trigger all the auxiliary cameras again to realize polling triggering, entering the identification process again, and triggering the RE-REC working state to be used for shooting the target vehicle again and RE-identifying the license plate information of the target vehicle again.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, a multi-process identification method is arranged, a target license plate is identified mainly according to a main camera module shooting mode of a main process, an auxiliary camera module is started to achieve an auxiliary identification effect in the identification process, once a final conclusion obtained in the main process is wrong, the auxiliary camera module can be circulated to the original identification process again, corresponding feedback is formed according to different wrong conclusions, the final identification strategies are different, the judgment assistance of the auxiliary camera module on the main process is enhanced, and the verification and feedback effects can be formed while the bidirectional cross identification is formed.
The contrast verification mode and the cross recognition effect only need to adopt the function of the auxiliary camera module, other verification systems do not need to be additionally arranged, and the functions of the auxiliary camera module can be increased while the complexity of the system is greatly reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow module information diagram of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1
As shown in fig. 1, the present invention provides a method for improving license plate recognition efficiency in a complex scene, including a main control module, a main camera module and an auxiliary camera module, where the main camera module includes a ground sensing module, the auxiliary camera module is formed by combining multiple cameras and includes a shooting camera and a video camera, the main control module is respectively connected with the main camera module and the auxiliary camera module, and the main control module carries an image recognition algorithm, and the license plate recognition specifically includes the following steps:
s1, dynamic triggering, namely after a ground sensing module senses that a vehicle enters a channel, a main camera module is started to recognize, and an auxiliary camera module is started to start to work after sensing that other hardware is excited;
s2, a main camera module identification process:
1) the main camera module shoots the license plate, sends the image to the main control module, identifies the license plate in the image and records the result as A;
2) setting the working state as Default, namely setting the main camera module as a Default state, soft-triggering all cameras in the auxiliary camera module, shooting the license plate, sending an image obtained by shooting the license plate to the main control module, and obtaining a result B;
3) the main control module compares the result A with the result B, obtains an optimal result according to the definition, the identification area and the preset weight, reports the optimal result to the main control module to be C, and processes and forms a final order according to the service of the main control module under the condition that the car is branded;
s3, after the auxiliary camera module is started, the current working state is judged:
a. when the current working state is Default, namely a Default state, outputting a result list identified by the auxiliary camera, outputting a result with the highest reliability according to definition and an identification area after inputting the result list to the main control module, and marking the result as B;
b. when the current working state is RE-REC, namely, the camera shooting is restarted for secondary recognition, firstly judging whether the image state shot by the camera shooting is overtime or not, and directly ending the shooting under the overtime condition; judging whether the vehicle is a licensed vehicle or not in a non-overtime state, reporting the result to a final result C, and directly outputting the final result C;
c. when the current working state is RE-OPEN, namely the camera restarts the secondary rod lifting, firstly judging whether the shooting state is overtime, and directly ending the shooting under the overtime condition; and if the time-out state is not reached, judging whether the time-out state is consistent with the final result C, and directly outputting a rod lifting instruction if the time-out state is consistent with the final result C.
Further, in step 3) of step S2, when the output information of the final result C is insufficient and it is necessary to determine whether the vehicle is a unlicensed vehicle, the method specifically includes the following steps:
if the main control information confirms that the vehicle is a licensed vehicle, outputting the information to a central office, and then manually continuously judging whether the vehicle needs to pay, if not, directly controlling the rod lifting, finishing the operation of the whole process by the main camera module, and finishing the identification; when payment is needed, manually setting the state of the auxiliary camera module as RE-OPEN again, wherein the overtime time is 120s, returning to trigger all the auxiliary cameras again to realize polling trigger, entering the identification process again, and triggering the RE-OPEN working state for RE-shooting the license plate to recheck the output result of the main camera module;
and if the main control information confirms that the vehicle is a unlicensed vehicle, setting the working state to be RE-REC, setting the timeout time to be 30s, returning to trigger all the auxiliary cameras again to realize polling triggering, entering the identification process again, and triggering the RE-REC working state to be used for shooting the target vehicle again and RE-identifying the license plate information of the target vehicle again.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. The utility model provides a method for promoting license plate recognition efficiency under complicated scene, includes main control module, main camera module and supplementary camera module, its characterized in that, main camera module includes the ground sense module, supplementary camera module is formed by a plurality of camera combinations, includes and shoots camera and video recording camera, main control module is connected with main camera module and supplementary camera module respectively, and main control module carries out the image recognition algorithm, and its license plate discernment specifically contains following step:
s1, dynamic triggering, namely after a ground sensing module senses that a vehicle enters a channel, a main camera module is started to recognize, and an auxiliary camera module is started to start to work after sensing that other hardware is excited;
s2, a main camera module identification process:
1) the main camera module shoots the license plate, sends the image to the main control module, identifies the license plate in the image and records the result as A;
2) setting the working state as Default, namely setting the main camera module as a Default state, soft-triggering all cameras in the auxiliary camera module, shooting the license plate, sending an image obtained by shooting the license plate to the main control module, and obtaining a result B;
3) the main control module compares the result A with the result B, obtains an optimal result according to the definition, the identification area and the preset weight, reports the optimal result to C finally, and processes and forms a final order according to the service of the main control module under the condition that the license plate exists;
once the identification information of the final result C is insufficient, whether the vehicle is a unlicensed vehicle needs to be judged, and the method specifically comprises the following steps:
if the main control information confirms that the vehicle is a licensed vehicle, outputting the information to a central office, and then manually continuously judging whether the vehicle needs to pay, if not, directly controlling the rod lifting, finishing the operation of the whole process by the main camera module, and finishing the identification; when payment is needed, manually setting the state of the auxiliary camera module as RE-OPEN again, wherein the overtime time is 120s, returning to trigger all the auxiliary cameras again to realize polling trigger, entering the identification process again, and triggering the RE-OPEN working state for RE-shooting the license plate to recheck the output result of the main camera module;
if the main control information confirms that the vehicle is a unlicensed vehicle, setting the working state to be RE-REC, setting the timeout time to be 30s, returning to trigger all auxiliary cameras again to realize polling triggering, entering the identification process again, triggering the RE-REC working state, and shooting the target vehicle again to RE-identify the license plate information of the target vehicle again
S3, after the auxiliary camera module is started, the current working state is judged:
a. when the current working state is Default, namely a Default state, outputting a result list identified by the auxiliary camera, outputting a result with the highest reliability according to definition and an identification area after inputting the result list to the main control module, and marking the result as B;
b. when the current working state is RE-REC, namely, the camera shooting is restarted for secondary recognition, firstly judging whether the image state shot by the camera shooting is overtime or not, and directly ending the shooting under the overtime condition; judging whether the vehicle is a licensed vehicle or not in a non-overtime state, reporting the result to a final result C, and directly outputting the final result C;
c. when the current working state is RE-OPEN, namely the camera restarts the secondary rod lifting, firstly judging whether the shooting state is overtime, and directly ending the shooting under the overtime condition; and judging whether the final result is consistent with the final result C or not in the non-overtime state, and directly outputting a rod lifting instruction when the final result is consistent with the final result C.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110207896.0A CN112949643B (en) | 2021-02-24 | 2021-02-24 | Method for improving license plate recognition efficiency in complex scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110207896.0A CN112949643B (en) | 2021-02-24 | 2021-02-24 | Method for improving license plate recognition efficiency in complex scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112949643A CN112949643A (en) | 2021-06-11 |
| CN112949643B true CN112949643B (en) | 2022-06-07 |
Family
ID=76246030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110207896.0A Active CN112949643B (en) | 2021-02-24 | 2021-02-24 | Method for improving license plate recognition efficiency in complex scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949643B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113569689A (en) * | 2021-07-21 | 2021-10-29 | 河北顺思科技有限公司 | Data matching method and device for vehicle dynamic weighing system and terminal |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103035125A (en) * | 2012-12-12 | 2013-04-10 | 北京蓝卡软件技术有限公司 | Vehicle license plate recognition method and system thereof |
| CN106205139A (en) * | 2016-07-14 | 2016-12-07 | 浙江宇视科技有限公司 | Vehicle room entry/exit management method and device |
| CN106204767A (en) * | 2015-04-30 | 2016-12-07 | 上海临界点机电设备有限公司 | No-stop charging system based on HIEP payment standards |
| CN106408950A (en) * | 2016-11-18 | 2017-02-15 | 北京停简单信息技术有限公司 | Parking lot entrance and exit license plate recognition system and method |
| CN109035847A (en) * | 2018-07-25 | 2018-12-18 | 厦门路桥信息股份有限公司 | Go out admission abnormality eliminating method, medium and system based on cloud landing |
| US10633003B1 (en) * | 2018-12-05 | 2020-04-28 | Here Global B.V. | Method, apparatus, and computer readable medium for verifying a safe vehicle operation via a portable device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160127693A1 (en) * | 2014-10-29 | 2016-05-05 | Dae Kwon Chung | WiFi Wireless Rear View Parking System |
-
2021
- 2021-02-24 CN CN202110207896.0A patent/CN112949643B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103035125A (en) * | 2012-12-12 | 2013-04-10 | 北京蓝卡软件技术有限公司 | Vehicle license plate recognition method and system thereof |
| CN106204767A (en) * | 2015-04-30 | 2016-12-07 | 上海临界点机电设备有限公司 | No-stop charging system based on HIEP payment standards |
| CN106205139A (en) * | 2016-07-14 | 2016-12-07 | 浙江宇视科技有限公司 | Vehicle room entry/exit management method and device |
| CN106408950A (en) * | 2016-11-18 | 2017-02-15 | 北京停简单信息技术有限公司 | Parking lot entrance and exit license plate recognition system and method |
| CN109035847A (en) * | 2018-07-25 | 2018-12-18 | 厦门路桥信息股份有限公司 | Go out admission abnormality eliminating method, medium and system based on cloud landing |
| US10633003B1 (en) * | 2018-12-05 | 2020-04-28 | Here Global B.V. | Method, apparatus, and computer readable medium for verifying a safe vehicle operation via a portable device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112949643A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103985230B (en) | A kind of Notification Method based on image, device and notice system | |
| KR101988540B1 (en) | System and method for managing parking | |
| CN105654734A (en) | Data processing method and device for vehicle violations | |
| CN105825184A (en) | Vehicle data processing method and device | |
| CN112949643B (en) | Method for improving license plate recognition efficiency in complex scene | |
| KR101974105B1 (en) | Photographing system and method for increasing recognition rate of vehicle number | |
| CN107729867A (en) | Identify the method and system illegally driven | |
| KR101038650B1 (en) | Adaptive modeling method for background image, detecting method and system for illegal-stopping and parking vehicle using it | |
| KR101660254B1 (en) | recognizing system of vehicle number for parking crossing gate | |
| KR102506971B1 (en) | Method and system for recognizing license plates of two-wheeled vehicles through deep-learning-based rear shooting | |
| CN114202957A (en) | Parking management method, management device, and storage medium | |
| CN104765859A (en) | Illegal parking vehicle information inputting method and system | |
| CN114373323A (en) | Processing method and processing system for parking space occupation | |
| KR101610295B1 (en) | Intelligent enforcement system for illegal parking enforcement and providing method thereof | |
| KR100770157B1 (en) | Movement license number of an automobil system | |
| KR101547239B1 (en) | System and method for adjusting camera brightness based extraction of background image | |
| CN112712626A (en) | Vehicle verification method and device based on license plate information, computer equipment and storage medium | |
| CN113206994B (en) | Camera automatic engineering survey method and device, electronic equipment, chip and storage medium | |
| CN111882917B (en) | Vehicle queue-jumping problem processing method and processing device | |
| KR200415231Y1 (en) | In-car type illegal vehicles detection system while driving | |
| TW201824864A (en) | Dynamic image feature enhancement method and system capable of directly and instantly adjusting imaging parameters of the camera and improving parameters of the captured image | |
| KR20170066934A (en) | Intelligent parking enforcement system and providing method thereof | |
| CN113501003B (en) | Driving assistance prompting method, device, equipment, storage medium and program product | |
| KR101451070B1 (en) | Method to recognize license plates by removing recognition error by shadow and license plate recognition system | |
| CN117975431A (en) | License plate recognition control method, device, equipment and storage medium |
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 |