CN115376117A - License plate recognition method in rainy and foggy weather - Google Patents
License plate recognition method in rainy and foggy weather Download PDFInfo
- Publication number
- CN115376117A CN115376117A CN202210805387.2A CN202210805387A CN115376117A CN 115376117 A CN115376117 A CN 115376117A CN 202210805387 A CN202210805387 A CN 202210805387A CN 115376117 A CN115376117 A CN 115376117A
- Authority
- CN
- China
- Prior art keywords
- rain
- image
- fog
- fog image
- license plate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 10
- 238000004891 communication Methods 0.000 claims abstract description 8
- 238000002834 transmittance Methods 0.000 claims abstract description 7
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a license plate recognition method in rainy and foggy weather, which comprises the steps of firstly collecting license plate images influenced by the rainy and foggy weather, and taking the license plate images as rain and foggy images; then establishing a rain and fog image model, carrying out minimum operation on the rain and fog image model, and calculating the transmittance; traversing all pixel values of the rain and fog image to obtain an optimal segmentation value for segmenting the foreground and the atmospheric part of the rain and fog image, segmenting the rain and fog image, selecting the maximum communication area of the atmospheric part as a target, converting the maximum communication area into a bright channel, and taking the average value of the pixel values of the bright channel as an atmospheric light value; and finally, repairing the defogged image according to the calculated transmissivity, the atmospheric light value and a preset threshold of the transmissivity. The invention improves the quality of the defogged image and improves the accuracy and reliability of license plate identification.
Description
Technical Field
The invention relates to the field of image processing, in particular to a license plate recognition method in rainy and foggy weather.
Background
Along with the continuous improvement of national infrastructure and the continuous improvement of national economic level, the number of motor vehicles owned by people in China is continuously increased. The rapid development of urban traffic facilitates the traveling of the national people and simultaneously brings about various problems such as traffic jam, frequent accidents and the like. Under the condition, the license plate is one of the most important identity marks of the motor vehicle, and the accurate recognition of the license plate so as to determine the vehicle information becomes an important assistance for helping traffic management departments to process traffic problems.
The existing license plate recognition mode has the defects that the existing license plate recognition mode has great limitation, and the problems of fuzziness and inaccurate recognition are easy to occur particularly in rainy and foggy weather.
Disclosure of Invention
The invention aims to solve the technical problem of providing a license plate identification method in rainy and foggy weather aiming at the defects related in the background technology.
The invention adopts the following technical scheme for solving the technical problems:
a method for identifying a license plate under rain and fog weather comprises the following steps:
step 1), collecting license plate images influenced by rain and fog weather, and taking the license plate images as rain and fog images;
step 2), establishing a rain and fog image model:
where x is the image coordinate, J c (x) Is a clear image after rain and fog are removed, I c (x) Is a rain-fog image, A c Is the atmospheric light value, t (x) is the transmittance;
step 3), performing minimum operation on the rain and fog image model to obtain:
according to dark channel prior theory, the dark channel of a sharp image is represented as:
wherein, J dark A dark channel representing a clear image, c represents one of three channels of an RGB color space, and omega (x) represents the neighborhood of a pixel point x;
the fog density C (x) of the rain fog image is positively correlated with the difference value of the brightness and the saturation of the rain fog image, some pixels of a dark channel of the rain fog image are not 0 when the brightness is higher, and the threshold value T =0.8 max [ C (x) ]]When C (x) is less than or equal to T, the brightness of the rain and fog image is not high, and the dark channel is formedWhen C (x) > T, the brightness of the rain and fog image is higher, and the dark channel I is dark (x)=I gray (x) S (x), wherein I gray (x) Representing the gray value of a pixel point at a coordinate x in the rain and fog image, and s (x) representing the saturation at the coordinate x in the rain and fog image;
Step 4), traversing all pixel values of the rain and fog image to obtain an optimal segmentation value for segmenting the foreground and the atmosphere part of the rain and fog image, and segmenting the rain and fog image; selecting the maximum communication area of the atmosphere part as a target, converting the maximum communication area into a bright channel, and taking the average value of pixel values of the bright channel as an atmosphere light value A;
step 5), the image brightness is too high when the transmissivity t is too small, so the preset threshold value t of the transmissivity is used for judging the brightness of the image m And repairing the defogged image by using the following formula:
compared with the prior art, the invention adopting the technical scheme has the following technical effects:
the invention improves the quality of defogged images and improves the accuracy and reliability of license plate identification, and if a peak signal-to-noise ratio (PSNR) is adopted to evaluate the defogging effect of a physical license plate, the PSNR of the traditional method is 27.51dB, and the PSNR of the invention is 28.27dB.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the attached drawings:
the present invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. In the drawings, components are exaggerated for clarity.
As shown in fig. 1, the invention discloses a method for identifying a license plate in rainy and foggy weather, which comprises the following steps:
step 1), collecting a license plate image influenced by rain and fog weather, and taking the license plate image as a rain and fog image;
step 2), establishing a rain and fog image model:
where x is the image coordinate, J c (x) Is a clear image after rain and fog are removed, I c (x) Is a rain-fog image, A c Is the atmospheric light value, t (x) is the transmittance;
step 3), performing minimization operation on the rain and fog image model to obtain:
according to dark channel prior theory, the dark channel of a sharp image is represented as:
wherein, J dark A dark channel representing a clear image, c represents a certain channel of three channels of an RGB color space, and omega (x) represents the neighborhood of a pixel point x;
the fog concentration C (x) of the rain fog image is positively correlated with the difference value of the brightness and the saturation of the rain fog image, certain pixels of a dark channel of the rain fog image are not 0 when the brightness is higher, and the set threshold value T =0.8 x max [ C (x) ]]When C (x) is less than or equal to T, the brightness of the rain and fog image is not high, and the dark channel is formedWhen C (x) > T, the brightness of the rain and fog image is higher, and the dark channel I is dark (x)=I gray (x) S (x), wherein I gray (x) Representing the gray value of a pixel point at a coordinate x in the rain and fog image, and s (x) representing the saturation at the coordinate x in the rain and fog image;
Step 4), traversing all pixel values of the rain and fog image to obtain an optimal segmentation value for segmenting the foreground and the atmosphere part of the rain and fog image, and segmenting the rain and fog image; selecting the maximum communication area of the atmosphere part as a target, converting the maximum communication area into a bright channel, and taking the average value of pixel values of the bright channel as an atmosphere light value A;
step 5), the image brightness is too high when the transmissivity t is too small, so the preset threshold value t of the transmissivity is used for judging the brightness of the image m And repairing the defogged image by using the following formula:
the example is realized by writing a matlab program, and the program flow is shown in fig. 1.
The software version used in this example is MATLAB R2018b, the operating system is a Microsolf Windows 10 professional 64-bit system, the central processing unit model is Intel (R) Core (TM) dual-Core i5-9300H CPU@2.40GHz, and the memory is 16GB.
PSNR was used to evaluate the defogging effect. The original algorithm and the algorithm of the invention are respectively defogged, and the PSNR of the original algorithm is 27.51dB; the PSNR of the algorithm of the present invention is 28.27dB.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only illustrative of the present invention and are not intended to limit the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. A method for identifying a license plate under rainy and foggy weather is characterized by comprising the following steps:
step 1), collecting a license plate image influenced by rain and fog weather, and taking the license plate image as a rain and fog image;
step 2), establishing a rain and fog image model:
where x is the image coordinate, J c (x) Is a clear image after rain and fog are removed, I c (x) Is a rain-fog image, A c Is the atmospheric light value, t (x) is the transmittance;
step 3), performing minimization operation on the rain and fog image model to obtain:
according to dark channel prior theory, the dark channel of a sharp image is represented as:
wherein, J dark A dark channel representing a clear image, c represents one of three channels of an RGB color space, and omega (x) represents the neighborhood of a pixel point x;
the fog density C (x) of the rain fog image is positively correlated with the difference value of the brightness and the saturation of the rain fog image, some pixels of a dark channel of the rain fog image are not 0 when the brightness is higher, and the threshold value T =0.8 max [ C (x) ]]When C (x) is less than or equal to T, the brightness of the rain and fog image is not high, and the dark channel is formedWhen C (x) > T, the brightness of the rain and fog image is higher, and the dark channel I is dark (x)=I gray (x) S (x), wherein I gray (x) Representing the gray value of a pixel point at a coordinate x in the rain and fog image, and s (x) representing the saturation at the coordinate x in the rain and fog image;
Step 4), traversing all pixel values of the rain and fog image to obtain an optimal segmentation value for segmenting the foreground and the atmosphere part of the rain and fog image, and segmenting the rain and fog image; selecting the maximum communication area of the atmosphere part as a target, converting the maximum communication area into a bright channel, and taking the average value of pixel values of the bright channel as an atmosphere light value A;
step 5), the image brightness is too high when the transmissivity t is too small, so the preset threshold value t of the transmissivity is used for judging the brightness of the image m And repairing the defogged image by using the following formula:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210805387.2A CN115376117A (en) | 2022-07-08 | 2022-07-08 | License plate recognition method in rainy and foggy weather |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210805387.2A CN115376117A (en) | 2022-07-08 | 2022-07-08 | License plate recognition method in rainy and foggy weather |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115376117A true CN115376117A (en) | 2022-11-22 |
Family
ID=84061300
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210805387.2A Pending CN115376117A (en) | 2022-07-08 | 2022-07-08 | License plate recognition method in rainy and foggy weather |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115376117A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115861996A (en) * | 2023-02-16 | 2023-03-28 | 青岛新比特电子科技有限公司 | Data acquisition method and system based on Internet of things perception and AI neural network |
-
2022
- 2022-07-08 CN CN202210805387.2A patent/CN115376117A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115861996A (en) * | 2023-02-16 | 2023-03-28 | 青岛新比特电子科技有限公司 | Data acquisition method and system based on Internet of things perception and AI neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886896B (en) | Blue license plate segmentation and correction method | |
CN107301623B (en) | Traffic image defogging method and system based on dark channel and image segmentation | |
CN110969160B (en) | License plate image correction and recognition method and system based on deep learning | |
CN109657632B (en) | Lane line detection and identification method | |
CN112036254B (en) | Moving vehicle foreground detection method based on video image | |
CN110210451B (en) | Zebra crossing detection method | |
CN106971155B (en) | Unmanned vehicle lane scene segmentation method based on height information | |
CN110084111B (en) | Rapid night vehicle detection method applied to self-adaptive high beam | |
CN111144301A (en) | Road pavement defect quick early warning device based on degree of depth learning | |
CN115376117A (en) | License plate recognition method in rainy and foggy weather | |
CN111462140A (en) | Real-time image instance segmentation method based on block splicing | |
CN110782409A (en) | Method for removing shadow of multi-motion object | |
CN110458029B (en) | Vehicle detection method and device in foggy environment | |
CN112800974A (en) | Subway rail obstacle detection system and method based on machine vision | |
CN109800693B (en) | Night vehicle detection method based on color channel mixing characteristics | |
CN117011143A (en) | Video image stabilizing method and system for automobile data recorder | |
CN110619335A (en) | License plate positioning and character segmentation method | |
CN111192275A (en) | Highway fog visibility identification method based on dark channel prior theory | |
CN111460989A (en) | Steering wheel hand separation detection method based on monocular vision | |
CN114882708B (en) | Vehicle identification method based on monitoring video | |
CN109741350B (en) | Traffic video background extraction method based on morphological change and active point filling | |
CN202854837U (en) | Vehicle lane mark line detection device | |
CN112699841A (en) | Traffic sign detection and identification method based on driving video | |
CN107506686B (en) | Night vehicle detection method based on significance detection | |
CN116052135B (en) | Foggy day traffic sign recognition method based on texture features |
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 |