CN111062309B - Method, storage medium and system for detecting traffic signs in rainy days - Google Patents

Method, storage medium and system for detecting traffic signs in rainy days Download PDF

Info

Publication number
CN111062309B
CN111062309B CN201911279424.5A CN201911279424A CN111062309B CN 111062309 B CN111062309 B CN 111062309B CN 201911279424 A CN201911279424 A CN 201911279424A CN 111062309 B CN111062309 B CN 111062309B
Authority
CN
China
Prior art keywords
image
traffic sign
connected region
gray
processing
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
Application number
CN201911279424.5A
Other languages
Chinese (zh)
Other versions
CN111062309A (en
Inventor
刘富
康馨匀
刘云
刘璐
孙韧韬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jilin University
Original Assignee
Jilin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jilin University filed Critical Jilin University
Priority to CN201911279424.5A priority Critical patent/CN111062309B/en
Publication of CN111062309A publication Critical patent/CN111062309A/en
Application granted granted Critical
Publication of CN111062309B publication Critical patent/CN111062309B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
    • 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
    • G06T7/155—Segmentation; Edge detection involving morphological operators
    • 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
    • G06T7/90—Determination of colour characteristics
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a method, a storage medium and a system for detecting traffic signs in rainy days, wherein the method comprises the following steps: carrying out gray processing on the acquired traffic sign image in rainy days to obtain a gray image; according to the gray level distribution of the gray level image, calculating the probability density and the cumulative distribution function of the gray level image under different gray levels and automatically determining a color threshold value; carrying out binarization processing on the gray level image by using a color threshold value to obtain a binarized image; sequentially carrying out maximum connected region detection, morphological processing and convex processing on the binarized image to obtain an image containing a connected region; and partitioning the connected region of the image, extracting a geometric feature descriptor, and completing traffic sign detection according to the geometric feature descriptor to obtain a result image. According to the method, the color threshold value is automatically determined according to the accumulated distribution functions of different gray levels, so that the method for detecting the traffic sign in the rainy day has higher detection rate and stronger robustness.

Description

Rainy day traffic sign detection method, storage medium and system
Technical Field
The invention relates to the technical field of image processing, in particular to a method, a storage medium and a system for detecting traffic signs in rainy days.
Background
In recent years, with the continuous development of science and technology and the improvement of economic level, the number of automobiles is increasing, and the research of intelligent transportation systems and driving assistance systems is receiving wide attention. The traffic sign detection and identification system (TSDR) is an important component of an advanced driving assistance system, and can sense the external environment, provide road information for drivers and improve driving safety.
In the real driving process, weather and road environment can change, and particularly under the rainy day condition, different illumination and complex environment can influence the road environment perception to a certain extent.
The current commonly used traffic sign detection methods are mainly classified into three types, namely color-based, shape-based and learning-based. Traffic signs have distinct colors (red, yellow, blue, green, etc.) and shape features (circles, rectangles, triangles, etc.), and the signs are generally segmented to locate the sign positions based on color and shape detection by using a fixed color threshold. The above method works well in detecting the identification, but still has the following problems:
1. the threshold value is fixed, so that under the conditions of large illumination change and complex road environment, traffic can not be effectively subjected to sign segmentation, and false detection and missing detection are easily caused in the subsequent shape detection;
2. the existing detection method does not consider that under the rainy day condition, the illumination change is complex, the contrast of a traffic sign image is reduced, and the robustness is poor under the rainy day condition;
3. after the mark threshold is used for segmentation, more noise exists, the influence of the noise cannot be completely filtered only by adopting a filtering mode, false detection is caused to subsequent shape detection, and the calculation complexity is increased.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
In view of the above defects in the prior art, an object of the present invention is to provide a method, a storage medium, and a system for detecting a traffic sign in rainy days, which are used to solve the problems of low detection rate and poor robustness in the existing method for detecting a traffic sign in rainy days.
The technical scheme of the invention is as follows:
a method for detecting traffic signs in rainy days comprises the following steps:
carrying out color enhancement processing on the acquired rainy traffic sign image;
graying the rainy traffic sign image subjected to color enhancement processing to obtain a grayscale image;
calculating probability density and cumulative distribution function of the gray level image under different gray levels according to the gray level distribution of the gray level image;
based on the color characteristics of the traffic sign, automatically determining a color threshold according to the accumulative distribution function of different gray levels;
performing binarization processing on the gray level image by using the color threshold value to obtain a binarized image;
sequentially carrying out maximum connected region detection, morphological processing and convex processing on the binarized image to obtain an image containing a connected region;
and partitioning the connected region of the image, extracting a geometric feature descriptor, and completing traffic sign detection according to the geometric feature descriptor to obtain a result image.
The method for detecting the traffic sign in the rainy day comprises the following steps before the acquired image of the traffic sign in the rainy day is subjected to color enhancement processing:
and carrying out normalization processing on the traffic sign image in rainy days.
The method for detecting the traffic sign in the rainy day comprises the following steps of:
performing color enhancement of red, blue and yellow on the traffic sign image in rainy days, wherein the color enhancement formula is as follows:
Figure BDA0002316291940000031
Figure BDA0002316291940000032
Figure BDA0002316291940000033
wherein x is R ，x G ，x B Is the R, G and B three-channel component value f of any pixel x in the traffic sign image in rainy days R (x)，f B (x)，f Y (x) Is the enhanced color component.
The method for detecting the traffic sign in the rainy day comprises the following steps of calculating probability distribution and accumulative distribution function of different gray levels according to the gray level distribution of the gray level image:
mapping the gray level image according to the gray level [0-255] to obtain the probability of different gray levels;
calculating the cumulative distribution function corresponding to the probability of the gray image under different gray levels according to the probability of different gray levels:
Figure BDA0002316291940000034
wherein M is a gray value, h (k) is the number of pixels corresponding to different gray levels, M and N are the length and width of the image, and k is a gray variable between the minimum gray value min and the maximum value max.
The rainy day traffic sign detection method comprises the following steps of automatically determining a color threshold value according to the cumulative distribution function of different gray levels based on the color characteristics of the traffic sign:
obtaining a gray value meeting the following conditions according to the cumulative distribution function: if m = m 1 And satisfy
Figure BDA0002316291940000035
And then, the m1 is the automatically determined color threshold, wherein alpha is a fixed parameter value set based on the color feature of the traffic sign, and the value of alpha is 0.96.
The method for detecting the traffic sign in rainy days comprises the steps of measuring the traffic sign in rainy days, wherein the geometric feature descriptor comprises an area, an aspect ratio, a roundness, a rectangularity and an elongation.
The method for detecting the traffic sign in the rainy day comprises the following steps:
Figure BDA0002316291940000036
Figure BDA0002316291940000041
the calculation formula of the squareness degree is as follows:
Figure BDA0002316291940000042
the elongation is calculated as:
Figure BDA0002316291940000043
Figure BDA0002316291940000044
wherein A is r The sum of all pixels in the connected region, L is the perimeter of the connected region, W is the length of the connected region in the x direction, and H is the length of the region of interest in the y direction.
A storage medium, wherein the storage medium stores one or more programs, which are executed by one or more processors to implement the steps of the rainy traffic sign detection method of the present invention.
A rainy traffic sign detection system comprises at least one processor, a display screen, a memory, a communication interface and a bus, wherein the processor, the display screen, the memory and the communication interface are communicated with each other through the bus, and the processor calls a logic instruction in the memory to execute the steps of the rainy traffic sign detection method.
Has the beneficial effects that: according to the method, the color threshold value is automatically determined according to the accumulated distribution functions of different gray levels, so that the method for detecting the traffic sign in rainy days has higher detection rate and stronger robustness; according to the method, after the maximum connected region detection, the morphological processing and the convex processing are sequentially carried out on the binarized image, noise can be effectively removed, the subsequent shape detection is prevented from being mistakenly detected, the calculation complexity is reduced, and the detection efficiency is improved.
Drawings
Fig. 1 is a flowchart of a method for detecting traffic signs in rainy days according to a preferred embodiment of the present invention.
Fig. 2 is a normalized raw rainy traffic sign image.
Fig. 3 is a rainy traffic sign image subjected to color enhancement processing.
Fig. 4 is a rainy day traffic sign image after color threshold segmentation.
Fig. 5 is a rainy day traffic sign image after maximum connected region detection and morphological processing.
Fig. 6 is a result image of the rainy traffic sign image passing through the rainy traffic sign detection.
Fig. 7 is a block diagram of a system for detecting traffic signs in rainy days according to the present invention.
Detailed Description
The invention provides a method, a storage medium and a system for detecting traffic signs in rainy days, which are further described in detail below in order to make the purpose, technical scheme and effect of the invention clearer and clearer. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for detecting a traffic sign in a rainy day according to a preferred embodiment of the present invention, as shown in the figure, the method includes the following steps:
s10, performing color enhancement processing on the acquired traffic sign image in rainy days;
s20, carrying out gray level processing on the rainy-day traffic sign image subjected to the color enhancement processing to obtain a gray level image;
s30, calculating probability densities and cumulative distribution functions of the gray images under different gray levels according to the gray level distribution of the gray images;
s40, automatically determining a color threshold value according to the accumulative distribution function of different gray levels based on the color characteristics of the traffic identification;
s50, performing binarization processing on the gray level image by using the color threshold value to obtain a binarized image;
s60, sequentially carrying out maximum connected region detection, morphological processing and convex processing on the binarized image to obtain an image containing a connected region;
and S70, partitioning the connected region of the image, extracting a geometric feature descriptor, and completing traffic sign detection according to the geometric feature descriptor to obtain a result image.
In the embodiment, the method for detecting the traffic sign in the rainy day has the advantages that the color threshold is automatically determined according to the accumulative distribution functions of different gray levels, so that the method for detecting the traffic sign in the rainy day has higher detection rate and stronger robustness; according to the method, after the maximum connected region detection, the morphological processing and the convex processing are sequentially carried out on the binarized image, noise can be effectively removed, the subsequent shape detection is prevented from being mistakenly detected, the calculation complexity is reduced, and the detection efficiency is improved.
In some embodiments, to save processing time and computational complexity for the rainy traffic sign image, the embodiment further includes, before performing color enhancement processing on the acquired rainy traffic sign image, the steps of: and carrying out normalization processing on the rainy-day traffic sign image, and adjusting the size of the rainy-day traffic sign image.
In some embodiments, because the contrast of the traffic sign image is low in rainy days, and the traffic sign is bright in color and mostly has the characteristics of red, yellow and blue, the RBY color enhancement is performed on the traffic sign image in rainy days, and the image contrast is improved. In this embodiment, the step of performing color enhancement processing on the traffic sign image in rainy days after normalization processing includes:
performing color enhancement of red, blue and yellow on the traffic sign image in rainy days, wherein the color enhancement formula is as follows:
Figure BDA0002316291940000061
Figure BDA0002316291940000062
Figure BDA0002316291940000063
wherein x is R ，x G ，x B Is the R, G and B three-channel component value f of any pixel x in the traffic sign image in rainy days R (x)，f B (x)，f Y (x) Is the enhanced color component, and the enhanced color component value is used as the new R, G, B color component value of the pixel x to obtain the color enhanced image, as shown in fig. 2.
In some embodiments, the rainy traffic sign image after the color enhancement processing is subjected to a graying processing, so as to obtain a grayscale image as shown in fig. 3. Further according to the gray level distribution of the gray level image, calculating the probability distribution and the cumulative distribution function of different gray levels, specifically, the gray level image is arranged in a histogram according to the gray level [ 0-255%]Mapping is carried out to obtain the probability of different gray levels; calculating the cumulative distribution function corresponding to the probability of the gray image under different gray levels according to the probability of different gray levels:
Figure BDA0002316291940000064
wherein h (k) is the number of pixels corresponding to different gray levels, M and N are the length and width of the image, and k is the gray variable between the minimum gray value min and the maximum value max.
In some embodimentsIn the formula, based on the color characteristics of the traffic sign, the color threshold is automatically determined according to the cumulative distribution function of different gray levels: obtaining the gray value meeting the following conditions according to the cumulative distribution function: if m = m 1 And satisfy
Figure BDA0002316291940000071
And then m1 is the automatically determined color threshold, wherein alpha is a fixed parameter value set based on the color characteristics of the traffic sign, and the value range of alpha is 0.96.
In some embodiments, the grayscale image is binarized using the automatically determined color threshold to obtain a binarized image as shown in fig. 4. Specifically, 255 is assigned to the part of the gray scale value of each pixel point in the gray scale image which is larger than the color threshold, and 0 is assigned to the part of the gray scale value which is smaller than the color threshold, that is, 0 is assigned to the part of the gray scale value of each pixel point in the gray scale image which is smaller than the color threshold
Figure BDA0002316291940000072
In some embodiments, the binarized image after binarization processing is sequentially subjected to maximum connected region detection, morphological processing and convex processing, so as to obtain an image containing connected regions. Specifically, according to the connectivity of the traffic sign, the maximum connected region detection is carried out on the binarized image. For example, a maximum connected region function is called, parameters such as a gray value variation, a connected region area range and maximum stability in the function are adjusted according to parameter setting in the function, and a maximum connected region N (N =1,2, 3.) in the image is determined to remove noise, so that a processed image is obtained; carrying out morphological processing of corrosion and expansion, opening operation and closing operation on the processed image, and removing isolated points; and finally, carrying out convex processing on the image subjected to morphological processing, and filling the interior of the binarization region to obtain an image containing a connected region as shown in figure 5, thereby providing convenience for subsequent traffic sign detection in rainy days.
In some embodiments, the connected region of the image is segmented and a geometric feature descriptor is extracted, and traffic sign detection is completed according to the geometric feature descriptor to obtain a result image. Specifically, extracting a geometric feature descriptor from each connected region in the image shown in fig. 5, obtaining a geometric constraint condition of the mark according to the shape feature of the traffic mark, wherein a binarization region corresponding to the geometric feature descriptor meeting the condition is a traffic mark region; and marking the coordinate value of the minimum circumscribed rectangle corresponding to the connected region, and enclosing a traffic sign region in the original image according to the coordinate value to obtain an image shown in figure 6, namely completing the traffic sign detection of the traffic sign image in rainy days.
In some embodiments, the geometric feature descriptor includes an area, an aspect ratio, a roundness, a squareness, and an elongation, the roundness being calculated by the formula:
Figure BDA0002316291940000081
the calculation formula of the squareness degree is as follows:
Figure BDA0002316291940000082
the elongation is calculated by the formula:
Figure BDA0002316291940000083
wherein A is r The sum of all pixels of the connected region, L is the perimeter of the connected region, W is the length of the connected region in the x direction, and H is the length of the region of interest in the y direction.
A storage medium storing one or more programs for execution by one or more processors to perform the steps of the method for detecting a traffic sign in rainy weather according to the present invention.
In some embodiments, a system for detecting traffic signs in rainy days is also provided, as shown in fig. 7, which includes at least one processor 20, a display screen 21, a memory 22, a communication interface 23 and a bus 24, wherein the processor 20, the display screen 21, the memory 22 and the communication interface 23 can communicate with each other through the bus 24. The display screen 21 is configured to display a user guidance interface preset in the initial setting mode. The communication interface 23 may transmit information. The processor 20 may invoke logic instructions in the memory 22 to perform the steps of the rainy traffic sign detection method described in the above embodiments.
Furthermore, the logic instructions in the memory 22 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product.
The memory 22, which is a computer-readable storage medium, may be configured to store a software program, a computer-executable program, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 30 executes the software programs, instructions or modules stored in the memory 22 to execute functional applications and data processing, i.e., to implement the methods in the above-described embodiments.
The memory 22 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal device, and the like. Further, the memory 22 may include a high speed random access memory and may also include a non-volatile memory. For example, a variety of media that can store program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, may also be transient storage media.
In summary, the method for detecting the traffic sign in the rainy day has the advantages that the color threshold is automatically determined according to the accumulated distribution functions of different gray levels, so that the method for detecting the traffic sign in the rainy day has higher detection rate and stronger robustness; according to the invention, after the maximum connected region detection, the morphological processing and the convex processing are sequentially carried out on the binarized image, the noise can be effectively removed, the false detection of the subsequent shape detection can be avoided, the calculation complexity is reduced, and the detection efficiency is improved.
It will be understood that the invention is not limited to the examples described above, but that modifications and variations will occur to those skilled in the art in light of the above teachings, and that all such modifications and variations are considered to be within the scope of the invention as defined by the appended claims.

Claims (3)

1. A method for detecting traffic signs in rainy days is characterized by comprising the following steps:
carrying out color enhancement processing on the acquired traffic sign image in rainy days;
graying the rainy traffic sign image subjected to color enhancement processing to obtain a grayscale image;
calculating probability density and cumulative distribution function of the gray level image under different gray levels according to the gray level distribution of the gray level image;
based on the color characteristics of the traffic sign, automatically determining a color threshold according to the accumulative distribution function of different gray levels;
performing binarization processing on the gray level image by using the color threshold value to obtain a binarized image;
sequentially carrying out maximum connected region detection, morphological processing and convex processing on the binarized image to obtain an image containing a connected region;
partitioning the connected region of the image, extracting a geometric feature descriptor, and completing traffic sign detection according to the geometric feature descriptor to obtain a result image;
sequentially carrying out maximum connected region detection, morphological processing and convex processing on the binarized image to obtain an image containing a connected region, wherein the method comprises the following steps of:
calling a maximum connected region function, setting according to parameters in the function, adjusting the gray value variation, the area range of the connected region and the maximum stability parameter, and determining the maximum connected region in the binarized image to remove noise to obtain a processed image; carrying out morphological processing of corrosion and expansion, opening operation and closing operation on the processed image, and removing isolated points; carrying out convex processing on the image subjected to morphological processing, and filling the interior of a binarization region to obtain an image containing a communication region;
partitioning the connected region of the image, extracting a geometric feature descriptor, completing traffic sign detection according to the geometric feature descriptor, and obtaining a result image, wherein the step of obtaining the result image comprises the following steps:
extracting geometric feature descriptors from each connected region of the image, obtaining geometric constraint conditions of the signs according to the shape features of the traffic signs, and enabling the binarization regions corresponding to the geometric feature descriptors meeting the conditions to be traffic sign regions; marking coordinate values of the minimum circumscribed rectangle corresponding to the connected region, and according to the coordinate values, enclosing a traffic sign region in the original image to obtain a result image;
the method also comprises the following steps before the color enhancement processing is carried out on the acquired rainy traffic sign image:
normalizing the rainy day traffic sign image;
the step of performing color enhancement processing on the acquired rainy traffic sign image comprises the following steps:
performing color enhancement of red, blue and yellow on the traffic sign image in rainy days, wherein the color enhancement formula is as follows:
Figure FDA0003914782970000021
Figure FDA0003914782970000022
Figure FDA0003914782970000023
wherein x is R ，x G ，x B Is the R, G and B three-channel component value f of any pixel x in the traffic sign image in rainy days R (x)，f B (x)，f Y (x) Is the enhanced color component;
the step of calculating the probability distribution and the cumulative distribution function of different gray levels according to the gray level distribution of the gray level image comprises the following steps:
mapping the gray level image according to the gray level [0-255] to obtain the probability of different gray levels;
according to whatCalculating the cumulative distribution function corresponding to the probability of the gray image under different gray levels according to the probability of different gray levels:
Figure FDA0003914782970000024
wherein M is a gray value, h (k) is the number of pixels corresponding to different gray levels, M and N are the length and width of the image, and k is a gray variable between the minimum gray value min and the maximum value max;
the step of automatically determining the color threshold according to the cumulative distribution function of different gray levels based on the color characteristics of the traffic sign comprises the following steps:
obtaining a gray value meeting the following conditions according to the cumulative distribution function: if m = m 1 And satisfy
Figure FDA0003914782970000031
Then, m1 is the automatically determined color threshold, wherein alpha is a fixed parameter value set based on the color feature of the traffic sign, and the value of alpha is 0.96;
the geometric feature descriptors include area, aspect ratio, roundness, squareness, and elongation;
the calculation formula of the roundness is as follows:
Figure FDA0003914782970000032
the calculation formula of the squareness degree is as follows:
Figure FDA0003914782970000033
Figure FDA0003914782970000034
the elongation is calculated by the formula:
Figure FDA0003914782970000035
wherein A is r The sum of all pixels in the connected region, L is the perimeter of the connected region, W is the length of the connected region in the x direction, and H is the length of the region of interest in the y direction.
2. A storage medium storing one or more programs, the one or more programs being executable by one or more processors to perform the steps of the method of claim 1.
3. A system for detecting traffic signs in rainy days, comprising at least one processor, a display screen, a memory, a communication interface and a bus, wherein the processor, the display screen, the memory and the communication interface complete mutual communication through the bus, and the processor calls logic instructions in the memory to execute the steps of the method for detecting traffic signs in rainy days according to claim 1.
CN201911279424.5A 2019-12-13 2019-12-13 Method, storage medium and system for detecting traffic signs in rainy days Active CN111062309B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911279424.5A CN111062309B (en) 2019-12-13 2019-12-13 Method, storage medium and system for detecting traffic signs in rainy days

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911279424.5A CN111062309B (en) 2019-12-13 2019-12-13 Method, storage medium and system for detecting traffic signs in rainy days

Publications (2)

Publication Number Publication Date
CN111062309A CN111062309A (en) 2020-04-24
CN111062309B true CN111062309B (en) 2022-12-30

Family

ID=70300779

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911279424.5A Active CN111062309B (en) 2019-12-13 2019-12-13 Method, storage medium and system for detecting traffic signs in rainy days

Country Status (1)

Country Link
CN (1) CN111062309B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111783651B (en) * 2020-06-30 2024-01-12 北京百度网讯科技有限公司 Pavement element identification method, pavement element identification device, electronic equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016191556A (en) * 2015-03-30 2016-11-10 三菱日立パワーシステムズ株式会社 Image processing method, method of evaluating life of object, and image processing system
CN106204552A (en) * 2016-06-30 2016-12-07 北京奇艺世纪科技有限公司 The detection method of a kind of video source and device
CN107301405A (en) * 2017-07-04 2017-10-27 上海应用技术大学 Method for traffic sign detection under natural scene

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7466841B2 (en) * 2004-08-16 2008-12-16 Siemens Corporate Research, Inc. Method for traffic sign detection
CN104268859A (en) * 2014-09-16 2015-01-07 奇瑞汽车股份有限公司 Image preprocessing method for night lane line detection
CN105931217A (en) * 2016-04-05 2016-09-07 李红伟 Image processing technology-based airport pavement FOD (foreign object debris) detection method
CN108765443B (en) * 2018-05-22 2021-08-24 杭州电子科技大学 Sign enhancement processing method for self-adaptive color threshold segmentation
CN109446984A (en) * 2018-10-26 2019-03-08 重庆大学 Traffic sign recognition method in natural scene

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016191556A (en) * 2015-03-30 2016-11-10 三菱日立パワーシステムズ株式会社 Image processing method, method of evaluating life of object, and image processing system
CN106204552A (en) * 2016-06-30 2016-12-07 北京奇艺世纪科技有限公司 The detection method of a kind of video source and device
CN107301405A (en) * 2017-07-04 2017-10-27 上海应用技术大学 Method for traffic sign detection under natural scene

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
"A No Reference Image Blur Detection using Cumulative probability Blur Detection (CPBD) Metric";Pooja Bhor 等;《https://www.ijisme.org/wp-content/uploads/papers/v1i5/E0209041513.pdf》;20130430;1-5 *
"OFDM Chirp Radar Target Detection and Adaptive Design In Clutter Environment";Shaddrack Yaw Nusenu 等;《https://ieeexplore.ieee.org/document/8506724》;20181025;1-7 *
变压器套管油位雾霾图像检测方法;石林玉等;《电子测量与仪器学报》;20160615(第06期);854-861 *
基于累积差分图像和高斯背景统计模型的烟尘目标检测;魏旭宾等;《宇航计测技术》;20070425(第02期);58-61 *
融合重建滤波器和暗特征的渗出物检测算法;赖小波等;《光电子.激光》;20130615(第06期);1238-1244 *

Also Published As

Publication number Publication date
CN111062309A (en) 2020-04-24

Similar Documents

Publication Publication Date Title
EP2575077B1 (en) Road sign detecting method and road sign detecting apparatus
WO2020177470A1 (en) Verification code recognition method and apparatus, terminal, and storage medium
KR101992398B1 (en) Method and Apparatus for Recognizing Road Symbols and Lanes
CN107301405A (en) Method for traffic sign detection under natural scene
JP5223675B2 (en) Vehicle detection device, vehicle detection method, and vehicle detection program
CN101334836A (en) License plate positioning method incorporating color, size and texture characteristic
CN108090459B (en) Traffic sign detection and identification method suitable for vehicle-mounted vision system
Chen et al. Detection and Recognition of Traffic Signs Based on HSV Vision Model and Shape features.
CN110782409B (en) Method for removing shadow of multiple moving objects
CN107563301A (en) Red signal detection method based on image processing techniques
CN113537037A (en) Pavement disease identification method, system, electronic device and storage medium
CN109522768A (en) The recognition methods of QR code and device
CN114862889A (en) Road edge extraction method and device based on remote sensing image
CN107392115B (en) Traffic sign identification method based on hierarchical feature extraction
CN112052777A (en) Cross-water bridge extraction method and device based on high-resolution remote sensing image
CN111062309B (en) Method, storage medium and system for detecting traffic signs in rainy days
CN108877030B (en) Image processing method, device, terminal and computer readable storage medium
Jia et al. Design of Traffic Sign Detection and Recognition Algorithm Based on Template Matching
CN117037082A (en) Parking behavior recognition method and system
CN111723650A (en) Night vehicle detection method, device, equipment and storage medium
CN114782413B (en) Star-stalk algae cell statistical method based on microscope image
CN111695374A (en) Method, system, medium, and apparatus for segmenting zebra crossing region in monitoring view
CN116052129A (en) Traffic sign detection method and device based on multi-feature fusion and storage medium
CN115690470A (en) Method for identifying state of switch indicator and related product
CN111881897B (en) Parking lot ground Chinese sign recognition method and system and storage medium thereof

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