CN108564631B - Method, device and computer-readable storage medium for detecting chromatic aberration of vehicle light - Google Patents

Method, device and computer-readable storage medium for detecting chromatic aberration of vehicle light Download PDF

Info

Publication number
CN108564631B
CN108564631B CN201810288504.6A CN201810288504A CN108564631B CN 108564631 B CN108564631 B CN 108564631B CN 201810288504 A CN201810288504 A CN 201810288504A CN 108564631 B CN108564631 B CN 108564631B
Authority
CN
China
Prior art keywords
light guide
color
vehicle light
image
color difference
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.)
Expired - Fee Related
Application number
CN201810288504.6A
Other languages
Chinese (zh)
Other versions
CN108564631A (en
Inventor
朱婉仪
穆平安
戴曙光
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.)
University of Shanghai for Science and Technology
Original Assignee
University of Shanghai for Science and Technology
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 University of Shanghai for Science and Technology filed Critical University of Shanghai for Science and Technology
Priority to CN201810288504.6A priority Critical patent/CN108564631B/en
Publication of CN108564631A publication Critical patent/CN108564631A/en
Application granted granted Critical
Publication of CN108564631B publication Critical patent/CN108564631B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
    • G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
    • G01J3/50—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • 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
    • 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
    • G06T2207/20081—Training; Learning
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)
  • Traffic Control Systems (AREA)

Abstract

本发明涉及一种车灯光导色差检测方法、装置及计算机可读存储介质，该方法包括制作车灯光导的训练图像库与学习分类模型；利用彩色摄像头获取待检测的车灯光导图像；将图像从RGB颜色空间转换至HSV颜色空间，分别对H、S、V三个颜色通道进行非等间隔量化，构成颜色特征向量；将提取的特征向量送入已选定的车灯光导类型对应的分类器模型中，计算获得待测光导的分类结果，并判定光导颜色是否合格。本发明还公开了一种车灯光导色差检测装置及计算机可读存储介质。本发明的车灯光导色差检测方法对光导色差的判断准确，适用于多种不同颜色、不同规格的车灯光导，相对于目前的人工检测方法，可提高检测速度与正确率，降低生产成本。

Figure 201810288504

The invention relates to a vehicle light guide color difference detection method, device and computer-readable storage medium. The method includes making a training image library of the vehicle light guide and a learning classification model; using a color camera to obtain the vehicle light guide image to be detected; Convert from RGB color space to HSV color space, and quantify the three color channels of H, S, and V at unequal intervals to form color feature vectors; send the extracted feature vectors to the classification corresponding to the selected vehicle light guide type In the device model, the classification result of the light guide to be tested is obtained by calculation, and whether the color of the light guide is qualified or not is determined. The invention also discloses a vehicle light guide color difference detection device and a computer-readable storage medium. The vehicle light guide chromatic aberration detection method of the invention accurately determines the light guide color difference, is suitable for a variety of different colors and different specifications of the vehicle light guide, and can improve the detection speed and accuracy and reduce the production cost compared with the current manual detection method.

Figure 201810288504

Description

Method and device for detecting light guide chromatic aberration of car lamp and computer readable storage medium
Technical Field
The invention relates to the field of automobile online detection, in particular to a method and a device for detecting light guide chromatic aberration of an automobile lamp.
Background
With the rapid development of the automobile industry and the continuous application of new energy sources, light guide lighting systems produced by combining light guide technology and LED green light sources are more and more widely applied to the design and manufacture of vehicle lamps.
In the industrial production process, due to the influences of errors of the installation position of the light source, defects of the light guide manufacturing process and the like, chromatic aberration can be generated when the light guide of the car lamp is turned on, so that the qualification rate of finished car lamp products is reduced, and therefore, the chromatic aberration detection of the light guide of the car lamp in industry becomes an important process. The application time of the prior light guide illumination technology in the automobile industry is short, the chromatic aberration detection of the light guide of the automobile lamp is mostly finished by manual or complex measuring instruments, the time and labor cost are high, and the detection efficiency and the detection accuracy can not meet the requirements of the automobile manufacturing industry.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a method and a device for detecting the light guide chromatic aberration of a car lamp, so as to solve the defects of the prior art.
In order to achieve the purpose, the technical scheme provided by the invention is as follows: a method for detecting the chromatic aberration of a car light guide comprises the following steps: firstly, acquiring the type information of the car light guide with detection, and selecting a corresponding parameter file in a preset classification model database according to the acquired information; acquiring a light guide image of a vehicle lamp to be detected; extracting HSV color histogram feature vectors of the car light guide; and then, the extracted feature vectors are sent into a classifier model corresponding to the selected car light guide type, a classification result of the light guide to be detected is obtained through calculation, and whether the color of the light guide is qualified or not is judged.
Further, the selecting a corresponding parameter file in a preset classification model database according to the acquired information includes:
if the classification model parameter file corresponding to the light guide type to be detected exists in the system, selecting the type;
if the preset classification model database does not have the corresponding parameter file, a new car light guide type needs to be added to manufacture a corresponding classification model.
Further, the step of adding a new car light guide type comprises: making an image library of the new type of light guide; acquiring images of the light guide sample piece through a color camera, wherein the images in an image library comprise M types of light guides with standard colors and car light guide images with various chromatic aberrations, and respectively labeling and storing category labels; extracting color characteristic vectors of M types of car light guide images in an image library; and for a training set consisting of M-class feature vectors and class labels, learning M two-class support vector machine classifiers by a one-to-many method, and storing corresponding classifier parameter model files for subsequent light guide classification detection.
Further, the acquiring of the light guide image of the vehicle lamp to be detected comprises: and lighting the car lamp to enable the light guide to emit light, acquiring an image of the light emitted by the light guide by using the color camera, and transmitting the image to the computer.
Further, the extracting the color feature vector of the car light guide comprises: converting the image from an RGB color space to an HSV color space; the H, S, V3 color channels are quantized at unequal intervals to form color feature vectors.
Further, the formula for converting the image from the RGB color space to the HSV color space is as follows:
Figure BDA0001616557620000021
in the formula, R, G, and B represent that the initial color information of the car light guide image is RGB values, and the converted HSV color space divides the color information of the car light guide into three elements: hue H, saturation S and brightness V, wherein H belongs to [0,360], S belongs to [0,1], V belongs to [0,1 ].
Further, the method for extracting the HSV color histogram feature vector of the car light guide comprises the following steps:
carrying out non-uniform quantization on three HSV components, wherein the H space is divided into 8 grades, S is divided into 3 grades, and V is divided into 3 grades:
Figure BDA0001616557620000031
Figure BDA0001616557620000032
Figure BDA0001616557620000033
and constructing a one-dimensional feature vector. According to the quantization method, the color components are synthesized into a one-dimensional feature vector G:
G＝HQSQV+SQV+V
wherein QSAnd QVThe number of quantization levels, i.e. Q, for the components S and V, respectivelyS＝3，QVIf 3, the formula translates to:
G＝9H+3S+V
a 72-handle one-dimensional histogram of G, i.e. the color feature vector of the car light guide image, is thus obtained.
A car light guide chromatic aberration detection device for realizing a car light guide chromatic aberration detection method, the car light guide chromatic aberration detection device comprising: the device comprises a memory, a processor and a car light guide color difference detection program which is stored on the memory and can run on the processor.
A computer-readable storage medium for a vehicle light guide color difference detection method, the computer-readable storage medium having stored thereon a light guide color difference detection program, which when executed by a processor, implements the light guide color difference detection method steps.
The invention has the beneficial effects that:
according to the method, the car light guide image is obtained, a training image library and a learning classification model of the car light guide are manufactured, the car light guide color feature vector to be detected is extracted, the feature vector is sent into a classifier model corresponding to the selected car light guide type for classification detection, the classification result of the light guide to be detected is obtained, if the classification result is the standard color, the classification result is qualified, and if the classification result is other color cast, the classification result is unqualified. Therefore, the chromatic aberration detection of the car light guide is realized, and compared with the existing manual detection method, the method can improve the detection speed and the accuracy and reduce the production cost.
Drawings
FIG. 1 is a schematic structural diagram of a terminal of a vehicular lamp light guide chromatic aberration detection apparatus according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of the method for detecting chromatic aberration of a vehicle light guide according to the present invention.
Detailed Description
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The terminal of the embodiment of the invention can be a PC. As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a camera interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The camera interface 1004 may optionally include standard serial, parallel, USB, IEEE1394, etc. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the terminal may further include a sensor, a voltage current detection circuit, a communication module, and the like.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operation server, an image capturing module, a user interface module, and a car light guide color difference detection program.
In the terminal shown in fig. 1, the camera interface 1004 is mainly used for connecting a color camera and collecting images for subsequent color difference detection; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call a car light guide color difference detection program stored in the memory 1005.
In this embodiment, the vehicular lamp light guide color difference detection device includes: a memory 1005, a processor 1001 and a car light guide chromatic aberration detection program stored on the memory 1005 and executable on the processor 1001, wherein when the processor 1001 calls the car light guide chromatic aberration detection program stored in the memory 1005, the following operations are performed:
acquiring the type information of the car light guide with detection, and selecting a corresponding parameter file in a preset classification model database according to the acquired information;
acquiring a light guide image of a vehicle lamp to be detected;
extracting HSV color histogram feature vectors of the car light guide;
and sending the extracted feature vectors into a classifier model corresponding to the selected car light guide type, calculating to obtain a classification result of the light guide to be detected, and judging whether the color of the light guide is qualified.
Further, the processor 1001 may call a car light guide color difference detection program stored in the memory 1005, and further perform the following operations:
if the classification model parameter file corresponding to the light guide type to be detected exists in the system, selecting the type;
if the preset classification model database does not have the corresponding parameter file, a new car light guide type needs to be added to manufacture a corresponding classification model.
Further, the processor 1001 may call a car light guide color difference detection program stored in the memory 1005, and further perform the following operations:
and lighting the car lamp to enable the light guide to emit light, acquiring an image of the light emitted by the light guide by using the color camera, and transmitting the image to the computer.
Further, the processor 1001 may call a car light guide color difference detection program stored in the memory 1005, and further perform the following operations:
converting the image from an RGB color space to an HSV color space;
the 3 color channels of H, S, V are quantized at unequal intervals to form color feature vectors.
Further, the processor 1001 may call a car light guide color difference detection program stored in the memory 1005, and further perform the following operations:
making an image library of a new type of light guide, wherein the images in the image library comprise light guides with standard colors and car light guide images with various chromatic aberrations, and the image library is respectively marked with category labels and stored, and the step of acquiring the images is as in claim 3;
extracting color feature vectors of the M types of car light guide images in the image library, wherein the steps are as in claim 4;
for a training set consisting of M-class feature vectors and class labels, a one-to-many method is adopted to learn M two-class Support Vector Machine (SVM) classifiers, and corresponding classifier parameter model files are stored for subsequent light guide classification detection.
The invention further provides a car light guide chromatic aberration detection method, and referring to fig. 2, fig. 2 is a flow diagram of the car light guide chromatic aberration detection method of the invention.
In the embodiment, the color difference of the car light guide is detected by using a machine vision method, and the detection method comprises the following steps:
step S10, obtaining the car light guide type information with detection, and selecting the corresponding parameter file in the preset classification model database according to the obtained information;
in this embodiment, if the classification model parameter file corresponding to the light guide type to be detected already exists in the system, the type is selected; if the preset classification model database does not have the corresponding parameter file, a new car light guide type needs to be added, and a corresponding classification learning model is manufactured.
When a new car lamp light guide type is added, firstly, obtaining an image of a car lamp light guide sample piece through a color camera, and making an image library of the new type light guide, wherein the image in the image library comprises M types of light guides with standard colors and car lamp light guide images with various chromatic aberrations, and respectively labeling and storing a category label; further, converting the M-type car lamp light guide images in the image library from an RGB color space to an HSV color space, and then extracting HSV color feature vectors; further, a training set formed by the M-class feature vectors and class labels is used for learning M two-class Support Vector Machine (SVM) classifiers by a one-to-many method, and corresponding classifier parameter model files are stored for subsequent light guide classification detection.
Step S20, acquiring a light guide image of the vehicle lamp to be detected;
in this embodiment, the light of the vehicle is controlled by a program to illuminate, the light guide is caused to emit light, an image of the light emitted by the light guide is acquired by the color camera, and the image is transmitted to the computer.
Step S30, extracting HSV color histogram feature vectors of the car light guide;
in this embodiment, first, the image is converted from RGB color space to HSV color space by the following formula:
Figure BDA0001616557620000071
in the formula, R, G, and B represent that the initial color information of the car light guide image is RGB values, and the converted HSV color space divides the color information of the car light guide into three elements: hue H (Hue), saturation S (Satution), and lightness V (value), where H ∈ [0,360], S ∈ [0,1], and V ∈ [0,1 ].
The three color channels of H, S, V are then quantized at unequal intervals to form a 72-bin color feature vector. The method for extracting the HSV color histogram feature vector of the car light guide comprises the following steps:
the three components of HSV are non-uniformly quantized according to the following method, wherein H space is divided into 8 grades, S is divided into 3 grades, and V is divided into 3 grades:
Figure BDA0001616557620000081
Figure BDA0001616557620000082
Figure BDA0001616557620000083
and constructing a one-dimensional feature vector. According to the quantization method, the color components are synthesized into a one-dimensional feature vector:
G＝HQSQV+SQv+V
wherein QSAnd QVThe number of quantization levels, i.e. Q, for the components S and V, respectivelyS＝3，QVIf 3, the formula translates to:
G＝9H+3S+V
a 72-handle one-dimensional histogram of G, i.e. the color feature vector of the car light guide image, is thus obtained.
And step S40, sending the extracted HSV color feature vectors into a classifier model corresponding to the selected car light guide type, calculating to obtain a classification result of the light guide to be detected, and judging whether the light guide color is qualified.
In the embodiment, if the classification result is the standard color, the color is qualified, and if the classification result is other color cast, the color is unqualified, and meanwhile, the color difference condition of the light guide can be obtained according to the unqualified light guide color label, and the light guide is improved.
The method for detecting the car lamp light guide chromatic aberration comprises the steps of obtaining a car lamp light guide image, manufacturing a training image library and a learning classification model of the car lamp light guide, extracting a feature vector of the color of the car lamp light guide to be detected, sending the feature vector into a classifier model corresponding to the selected car lamp light guide type for classification detection, obtaining a classification result of the light guide to be detected, and determining that the light guide to be detected is qualified if the classification result is a standard color and determining that the light guide to be detected is unqualified if the classification result is other color cast. Therefore, the chromatic aberration detection of the car light guide is realized, and compared with the existing detection method, the method can improve the detection speed and the accuracy and reduce the production cost.
The present invention further provides a computer-readable storage medium, in this embodiment, a light guide color difference detection program is stored on the computer-readable storage medium, and the steps of the color difference detection method for a light guide of a vehicle lamp can be implemented.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (7)

1.一种车灯光导色差检测方法，其特征在于，其步骤为：首先，获取带检测的车灯光导类型信息，根据获取的信息选择预设分类模型数据库中对应的参数文件；获取待检测车灯光导图像；再提取车灯光导的HSV颜色直方图特征向量；然后，将提取的特征向量送入已选定的车灯光导类型对应的分类器模型中，计算获得待测光导的分类结果，并判定光导颜色是否合格；所述提取车灯光导的颜色特征向量步骤包括：将图像从RGB颜色空间转换至HSV颜色空间；分别对H、S、V的三个颜色通道进行非等间隔量化，构成颜色特征向量；所述提取车灯光导的HSV颜色直方图特征向量的方法为：1. A vehicle light guide color difference detection method, characterized in that the steps are: first, obtain information on the type of vehicle light guide with detection, and select a corresponding parameter file in a preset classification model database according to the obtained information; obtain to-be-detected Car light guide image; then extract the HSV color histogram feature vector of the car light guide; then, send the extracted feature vector into the classifier model corresponding to the selected car light guide type, and calculate the classification result of the light guide to be measured. , and determine whether the color of the light guide is qualified; the step of extracting the color feature vector of the vehicle light guide includes: converting the image from the RGB color space to the HSV color space; respectively quantizing the three color channels of H, S, and V at unequal intervals , constitute a color feature vector; the method for extracting the HSV color histogram feature vector of the headlight guide is: 将HSV三个分量进行非均匀量化，H空间分为8个等级，S分为3个等级，V分为3个等级：The three components of HSV are non-uniformly quantized, the H space is divided into 8 levels, S is divided into 3 levels, and V is divided into 3 levels:
Figure FDA0003029135200000011
Figure FDA0003029135200000011
Figure FDA0003029135200000012
Figure FDA0003029135200000012
Figure FDA0003029135200000013
Figure FDA0003029135200000013
 构造一维特征向量，按照以上的量化方法，把各颜色分量合成为一维特征向量G：Construct a one-dimensional feature vector, and synthesize each color component into a one-dimensional feature vector G according to the above quantization method: G＝HQSQV+SQV+VG=HQ S Q V +SQ V +V 其中QS和QV分别为分量S和V的量化级数，即QS＝3，QV＝3，则公式转化为：Where Q S and Q V are the quantization levels of the components S and V, respectively, that is Q S =3, Q V =3, then the formula is transformed into: G＝9H+3S+VG=9H+3S+V 由此获得G的72柄一维直方图，即车灯光导图像的颜色特征向量。Thus, the 72-handle one-dimensional histogram of G is obtained, that is, the color feature vector of the headlight guide image. 2.根据权利要求1所述的车灯光导色差检测方法，其特征在于：所述根据获取信息选择预设分类模型数据库中对应的参数文件，包括：2. The vehicle light guide color difference detection method according to claim 1, wherein the selecting the corresponding parameter file in the preset classification model database according to the acquired information comprises: 若待检测的光导类型对应的分类模型参数文件在本系统中已存在，则选择此类型；If the classification model parameter file corresponding to the type of light guide to be detected already exists in the system, select this type; 若预设分类模型数据库中不存在对应的参数文件，则需要添加新的车灯光导类型，制作相应的分类模型。If there is no corresponding parameter file in the preset classification model database, you need to add a new type of light guide to create a corresponding classification model. 3.根据权利要求2所述的车灯光导色差检测方法，其特征在于，所述添加新的车灯光导类型的步骤包括：制作新类型光导的图像库；通过彩色摄像头获取光导样件的图像，图像库中的图像包括标准颜色的光导和有各种色差的车灯光导图像共M类，分别标注类别标签并保存；将图像库中的M类车灯光导图像进行颜色特征向量提取；对由M类特征向量和类别标签构成的训练集，采用一对多方法学习M个二分类的支持向量机分类器，并保存相应的分类器参数模型文件，用于后续的光导分类检测。3. The method for detecting chromatic aberration of vehicle light guides according to claim 2, wherein the step of adding a new type of vehicle light guide comprises: making an image library of the new type of light guide; acquiring an image of the light guide sample through a color camera , the images in the image library include standard color light guides and car light guide images with various chromatic aberrations, and there are M categories, which are marked with category labels and saved; the color feature vector extraction is performed on the M-type car light guide images in the image library; The training set consisting of M types of feature vectors and category labels uses a one-to-many method to learn M two-category SVM classifiers, and save the corresponding classifier parameter model files for subsequent light guide classification and detection. 4.根据权利要求1所述的车灯光导色差检测方法，其特征在于：所述获取待检测车灯光导图像，包括：点亮车灯，使光导发光，利用彩色摄像头获取光导发光的图像，并将图像传输至计算机。4. The method for detecting chromatic aberration of vehicle light guides according to claim 1, wherein the acquiring the image of the vehicle light guide to be detected comprises: lighting the vehicle lights, making the light guide emit light, and using a color camera to obtain the image of the light guide emitting light, and transfer the image to the computer. 5.根据权利要求1所述的车灯光导色差检测方法，其特征在于，所述将图像从RGB颜色空间转换至HSV颜色空间的公式为：5. The vehicle light guide color difference detection method according to claim 1, wherein the formula for converting the image from the RGB color space to the HSV color space is:
Figure FDA0003029135200000031
Figure FDA0003029135200000031
 式中，R,G,B表示车灯光导图像最初的颜色信息为RGB值，转换后的HSV颜色空间将车灯光导的颜色信息分为三个要素：色调H、饱和度S和亮度V，其中，H∈[0,360]，S∈[0,1]，V∈[0,1]。In the formula, R, G, B indicate that the original color information of the headlight guide image is RGB value, and the converted HSV color space divides the color information of the headlight guide into three elements: hue H, saturation S and brightness V, Among them, H∈[0,360], S∈[0,1], V∈[0,1]. 6.一种用于权利要求1至5中任一项所述的车灯光导色差检测方法的车灯光导色差检测装置，其特征在于：所述车灯光导色差检测装置包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的车灯光导色差检测程序。6. A vehicle light guide color difference detection device for the vehicle light guide color difference detection method according to any one of claims 1 to 5, wherein the vehicle light guide color difference detection device comprises: a memory, a processor and a vehicle light guide color difference detection program stored on the memory and executable on the processor. 7.一种用于权利要求1至5中任一项所述的车灯光导色差检测方法的计算机可读存储介质，其特征在于：所述计算机可读存储介质上存储有灯光导色差检测程序，所述灯光导色差检测程序被处理器执行时实现所述灯光导色差检测方法步骤。7. A computer-readable storage medium for the method for detecting color difference of vehicle light guide according to any one of claims 1 to 5, characterized in that: a light guide color difference detection program is stored on the computer-readable storage medium , when the light guide color difference detection program is executed by the processor, the steps of the light guide color difference detection method are implemented.
CN201810288504.6A 2018-04-03 2018-04-03 Method, device and computer-readable storage medium for detecting chromatic aberration of vehicle light Expired - Fee Related CN108564631B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810288504.6A CN108564631B (en) 2018-04-03 2018-04-03 Method, device and computer-readable storage medium for detecting chromatic aberration of vehicle light

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810288504.6A CN108564631B (en) 2018-04-03 2018-04-03 Method, device and computer-readable storage medium for detecting chromatic aberration of vehicle light

Publications (2)

Publication Number Publication Date
CN108564631A CN108564631A (en) 2018-09-21
CN108564631B true CN108564631B (en) 2021-07-09

Family

ID=63533903

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810288504.6A Expired - Fee Related CN108564631B (en) 2018-04-03 2018-04-03 Method, device and computer-readable storage medium for detecting chromatic aberration of vehicle light

Country Status (1)

Country Link
CN (1) CN108564631B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109521029B (en) * 2018-11-30 2021-07-13 湘潭大学 A detection method for side appearance defects of bayonet-type automobile lamp caps
CN109800693B (en) * 2019-01-08 2021-05-28 西安交通大学 A night-time vehicle detection method based on color channel mixing features
CN110288634A (en) * 2019-06-05 2019-09-27 成都启泰智联信息科技有限公司 A kind of method for tracking target based on Modified particle swarm optimization algorithm
CN112317362A (en) * 2020-09-24 2021-02-05 赣州好朋友科技有限公司 Method and device for sorting quartz associated gold ore and readable storage medium
CN112365484A (en) * 2020-11-16 2021-02-12 北京霍里思特科技有限公司 Classification method, classification system and mineral product classifier
CN114577442A (en) * 2020-12-01 2022-06-03 常州星宇车灯股份有限公司 Car light detection device, method and system
CN113592787B (en) * 2021-07-13 2024-10-25 苏州汇川控制技术有限公司 Light emitting component detection method, device, terminal equipment and storage medium
CN114240929B (en) * 2021-12-28 2024-07-19 季华实验室 Color difference detection method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102385753A (en) * 2011-11-17 2012-03-21 江苏大学 Illumination-classification-based adaptive image segmentation method
CN102915446A (en) * 2012-09-20 2013-02-06 复旦大学 Plant disease and pest detection method based on SVM (support vector machine) learning
CN105809181A (en) * 2014-12-31 2016-07-27 阿里巴巴集团控股有限公司 Logo detection method and device
CN106709529A (en) * 2017-01-18 2017-05-24 河北工业大学 Visual detection method for color difference classification of photovoltaic cells

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8311338B2 (en) * 2009-09-15 2012-11-13 Tandent Vision Science, Inc. Method and system for learning a same-material constraint in an image
US8848991B2 (en) * 2012-03-16 2014-09-30 Soek Gam Tjioe Dental shade matching device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102385753A (en) * 2011-11-17 2012-03-21 江苏大学 Illumination-classification-based adaptive image segmentation method
CN102915446A (en) * 2012-09-20 2013-02-06 复旦大学 Plant disease and pest detection method based on SVM (support vector machine) learning
CN105809181A (en) * 2014-12-31 2016-07-27 阿里巴巴集团控股有限公司 Logo detection method and device
CN106709529A (en) * 2017-01-18 2017-05-24 河北工业大学 Visual detection method for color difference classification of photovoltaic cells

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于计算机视觉的车灯光导色差检测;王晨等;《电子测量技术》;20160831;第39卷(第8期);90-95页 *

Also Published As

Publication number Publication date
CN108564631A (en) 2018-09-21

Similar Documents

Publication Publication Date Title
CN108564631B (en) Method, device and computer-readable storage medium for detecting chromatic aberration of vehicle light
CN109520706B (en) Screw hole coordinate extraction method of automobile fuse box
US20240013348A1 (en) Image generation method and apparatus, device, and storage medium
CN111681220B (en) Method, device, system and storage medium for constructing defect detection model
CN111950469A (en) Road sign detection method, system, equipment and medium
CN109035235B (en) Car light guide chromatic aberration detection method
CN117173154A (en) Online image detection system and method for glass bottle
CN115575790B (en) Method and device for detecting defects of micron light emitting diode chip and storage medium
CN114972888B (en) A communication maintenance tool identification method based on YOLO V5
CN114926661B (en) Textile surface color data processing and identifying method and system
CN113557522A (en) Image frame pre-processing based on camera statistics
US20210287030A1 (en) Systems and Methods for Detecting Light Signatures and Performing Actions in Response Thereto
CN111652200A (en) Processing method, device and equipment for distinguishing multiple vehicles from pictures in vehicle insurance case
CN111709991A (en) A detection method, system, device and storage medium for railway tools
CN101118183A (en) A Color Automatic Recognition System
CN106096144A (en) A kind of automobile brand gene analysis method based on front face moulding
KR101694824B1 (en) Energy saving signboard using dual smart camer and the method thereof
CN115205596A (en) Image classification method, device, equipment and storage medium
CN111428796B (en) General object detection method and system based on deep learning
CN116485992A (en) Composite three-dimensional scanning method and device and three-dimensional scanner
CN109508635B (en) Traffic light identification method based on TensorFlow combined with multilayer CNN network
CN112183485A (en) Deep learning-based traffic cone detection positioning method and system and storage medium
WO2020075468A1 (en) Environmental similarity display device, environmental similarity display method, and environmental similarity display algorithm
CN111402341A (en) Camera parameter determination method and device, electronic equipment and readable storage medium
CN112766358A (en) Training method of neural network for dust suction intensity control

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
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210709