CN113532801A - High/multispectral camera dead pixel detection method and system based on distribution quantile - Google Patents
High/multispectral camera dead pixel detection method and system based on distribution quantile Download PDFInfo
- Publication number
- CN113532801A CN113532801A CN202110706053.5A CN202110706053A CN113532801A CN 113532801 A CN113532801 A CN 113532801A CN 202110706053 A CN202110706053 A CN 202110706053A CN 113532801 A CN113532801 A CN 113532801A
- Authority
- CN
- China
- Prior art keywords
- gray scale
- camera
- wave band
- column
- quantile
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 70
- 238000005315 distribution function Methods 0.000 claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000002310 reflectometry Methods 0.000 claims abstract description 12
- 230000003595 spectral effect Effects 0.000 claims description 66
- 239000000126 substance Substances 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 8
- 238000003384 imaging method Methods 0.000 description 7
- 238000001228 spectrum Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010295 mobile communication Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000000701 chemical imaging Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
-
- 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
- G01J3/28—Investigating the spectrum
- G01J3/2823—Imaging spectrometer
-
- 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
- G01J3/28—Investigating the spectrum
- G01J3/2823—Imaging spectrometer
- G01J2003/2826—Multispectral imaging, e.g. filter imaging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to a high/multispectral camera dead pixel detection method and system based on a distribution quantile, and solves the problem that the current state of a camera cannot be conveniently, quickly and accurately obtained in the prior art. The method comprises the following steps: acquiring a high/multispectral image obtained by shooting a uniform reflectivity plate by a high/multispectral camera, and determining the corresponding relation between the row/column number of each wave band image and the camera pixel; sequentially calculating the row/column gray scale statistic of each wave band of the high/multi-spectral image, acquiring a distribution function of the row/column gray scale statistic of each wave band, calculating the quantile and the quantile distance of the distribution function of the row/column gray scale statistic of each wave band, setting a judgment interval, and judging the row/column number of an abnormal value in the row/column gray scale statistic of each wave band according to the judgment interval; and determining the position of the camera abnormal pixel according to the line/column number of the abnormal value of each wave band through the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained. The current state of the camera is conveniently, quickly and accurately acquired.
Description
Technical Field
The invention relates to the technical field of high/multispectral camera dead pixel detection, in particular to a high/multispectral camera dead pixel detection method and system based on a distribution quantile.
Background
The high/multi-spectral imaging technology is a technical means for acquiring spectral radiation information of a detection object in a certain wave band range. The high/multispectral camera overcomes the problem that the spectral information of the visible light camera and the infrared camera is limited, and the high/multispectral image can acquire not only the spatial information, but also rich spectral information. The more spectral information the high/multi-spectral camera acquires, the higher the requirement on the accuracy of the pixel response, while ensuring the spatial resolution.
The high/multi-spectral imaging equipment is different from a traditional camera, and not only can realize multi-spectral-band imaging of visible light wave bands, but also can realize multi-spectral-band imaging of near infrared wave bands; the high/multi-spectral camera has the characteristics of wide spectral domain of imaging wave bands, numerous image spectral bands, large wave band number, large data volume, remarkable imaging difference of different spectral bands and the like. Especially for high resolution high/multispectral cameras, the imaging data volume is large, but the imaging time is long. Therefore, before data acquisition is formally carried out, important prior knowledge can be provided for camera imaging quality supervision and subsequent output image post-processing by accurately knowing the camera dead pixel in advance, and therefore detection work that the accurate current state of the camera is conveniently and quickly obtained, and the judgment result has higher accuracy and robustness is particularly important.
Therefore, a high/multi-spectral camera dead pixel detection method and system based on a distribution quantile, which can conveniently and quickly acquire the current state of the camera, are lacked in the prior art.
Disclosure of Invention
In view of the foregoing analysis, embodiments of the present invention provide a method and a system for detecting a dead pixel of a high/multi-spectral camera based on a distributed quantile, so as to solve the problem that the current state of the camera cannot be conveniently, quickly and accurately obtained.
In one aspect, an embodiment of the present invention provides a high/multispectral camera dead pixel detection method based on a distribution quantile, including:
acquiring a high/multispectral image obtained by shooting a uniform reflectivity plate by a high/multispectral camera, and determining the corresponding relation between the row/column number of each wave band image and the camera pixel;
sequentially calculating the row/column gray scale statistic of each wave band of the high/multispectral image, acquiring a distribution function of the row/column gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the row/column gray scale statistic of each wave band;
setting a judgment interval according to the quantile and the quantile distance of the distribution function of each wave band, and judging the row/column number of an abnormal value in the row/column gray scale statistic of each wave band according to the judgment interval;
and determining the position of the camera abnormal pixel according to the line/column number of the abnormal value of each wave band through the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
Further, comprising:
when the high/multispectral camera scans the high/multispectral images according to columns, determining the corresponding relation between the line number of each wave band image and the camera pixel;
sequentially calculating the line gray scale statistic of each wave band of the high/multi-spectral image, acquiring a distribution function of the line gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the line gray scale statistic of each wave band;
setting a judgment interval according to the quantile and the quantile distance of the line gray scale statistic distribution function of each wave band, and judging the line number of an abnormal value in the line gray scale statistic of each wave band according to the judgment interval;
and determining the position of the camera abnormal pixel according to the line number of the abnormal value of each wave band and the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
Further, comprising:
the line gray scale statistic of each wave band is expressed as:
wherein the content of the first and second substances,
is the gray scale mean value of the pixel of the ith row in the p spectral band of the high/multi-spectral image, n is the column number of the high/multi-spectral image,
the gray value of the pixel at the ith row and the jth column in the high/multispectral image is obtained.
Further, according to the distribution function of the line gray scale statistic of each wave band, calculating to obtain a first quartile of the line gray scale statistic of the p-th spectral wave band
Third quartile of the p spectral band line gray scale statistic
In the determination interval, the normal interval is expressed as:
wherein the content of the first and second substances,
a quartile distance which is the p spectral band line gray scale statistic;
line gray scale statistics as the p-th spectral band
Or
Corresponding to line number of p-th spectral band imageThe camera pixel is abnormal.
Further, comprising:
when the high/multispectral camera scans the high/multispectral image according to the line, determining the corresponding relation between the column number of each wave band image and the camera pixel;
sequentially calculating the column gray scale statistic of each wave band of the high/multispectral image, acquiring a distribution function of the column gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the column gray scale statistic of each wave band;
setting a judgment interval according to the quantile and the quantile distance of the column gray scale statistic distribution function of each wave band, and judging the column number of an abnormal value in the column gray scale statistic of each wave band according to the judgment interval;
and determining the position of the camera abnormal pixel according to the column number of the abnormal value of each wave band and the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
Further, comprising:
the column gray statistic of each band is expressed as:
wherein the content of the first and second substances,
is the gray level mean value of the j row pixel in the p spectral band of the high/multi-spectral image, m is the column number of the high/multi-spectral image,
the gray value of the pixel at the ith row and the jth column in the high/multispectral image is obtained.
Further, comprising:
according to the distribution function of the column gray scale statistic of each wave band, calculating to obtain a first quartile of the column gray scale statistic of the p-th spectral wave band
Third quartile of the p spectral band column gray scale statistic
In the determination interval, the normal interval is expressed as:
wherein the content of the first and second substances,
a quartile distance which is the p spectral band column gray scale statistic;
column gray scale statistics as the p-th spectral band
Or
And when the image element of the camera corresponding to the p-th spectral band image column number is abnormal.
On the other hand, the embodiment of the invention provides a high/multispectral camera dead pixel detection system based on distribution quantiles, which comprises the following steps:
the image acquisition module is used for acquiring a high/multispectral image obtained by shooting the uniform reflectivity plate by the high/multispectral camera and determining the corresponding relation between the row/column number of each wave band image and the pixel of the camera;
the statistic calculation module is used for calculating the row/column gray scale statistic of each wave band of the high/multispectral image in sequence, acquiring a distribution function of the row/column gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the row/column gray scale statistic of each wave band;
the judging module is used for setting a judging interval according to the quantile and the quantile distance of the distribution function of each wave band and judging the row/column number of an abnormal value in the row/column gray scale statistic of each wave band according to the judging interval;
and the detection module is used for determining the position of the camera abnormal pixel according to the row/column number of the abnormal value of each wave band through the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
In another aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the processor executes any one of the high/multi-spectral camera dead pixel detection methods based on a distribution quantile.
In another aspect, an embodiment of the present invention provides a computer device, including a processor and a memory storing a computer program, where when the computer program is executed by the processor, the processor executes any one of the methods for detecting a dead pixel of a high/multi-spectral camera based on a distribution quantile.
Compared with the prior art, the invention can realize at least one of the following beneficial effects:
1. the method effectively utilizes the key information corresponding to the camera pixel and the image pixel, does not need to add extra detection equipment and detection equipment, has strong adaptability and practicability to application scenes, and can conveniently realize the detection of the dead pixel of the camera;
2. the defect detection of the hyperspectral high/multispectral camera can be efficiently and quickly completed by utilizing the row/column gray value statistical information of each channel of the hyperspectral image;
3. by utilizing the advantage of low variance of the line/column statistics and combining the statistics distribution quantile judgment criterion and the quantile self-adaptive judgment criterion of the statistics distribution, the judgment result of the pixel abnormity of the camera in a specific waveband has higher accuracy and robustness.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
FIG. 1 is a flow chart of a distributed quantile-based high/multi-spectral camera dead pixel detection method according to an embodiment of the present disclosure;
FIG. 2 is a grayscale diagram of the 112 th band of a high/multi-spectral image according to another embodiment of the present application;
FIG. 3 is a schematic diagram illustrating the distribution of the gray scale statistics for the 112 th band of the high/multi-spectral image according to another embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a determination interval of the gray scale statistics of the 112 th band of the high/multi-spectral image according to another embodiment of the present application;
FIG. 5 is a schematic diagram of a system for dead pixel detection of a high/multi-spectral camera based on a distributed quantile according to another embodiment of the present disclosure;
fig. 6 is a schematic hardware configuration diagram of a computer device for distributed quantile-based high/multispectral camera dead pixel detection according to another embodiment of the present application.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
As shown in fig. 1, a specific embodiment of the present invention discloses a method for detecting a dead pixel of a high/multispectral camera based on a distributed quantile, which includes:
s10, acquiring a high/multi-spectral image obtained by shooting the uniform reflectivity plate by the high/multi-spectral camera, and determining the corresponding relation between the row/column number of each wave band image and the camera pixel;
specifically, a high/multispectral camera to be detected is used for shooting a uniform reflectivity plate to acquire a high/multispectral image, the scanning mode of the image acquired by the high/multispectral camera can be a column scanning mode or a line scanning mode, and the line/column number of the image acquired by scanning corresponds to a camera pixel according to the scanning mode of the camera to acquire the corresponding relation between the image line/column number and the camera pixel;
more specifically, when the high/multispectral camera scans the high/multispectral images according to columns, determining the corresponding relation between the line number of each wave band image and the camera pixel; when the high/multispectral camera scans the high/multispectral image according to the line, determining the corresponding relation between the column number of each wave band image and the camera pixel;
more specifically, the object to be photographed is a uniform reflectance plate, which is suitable for a wide spectral band and reflects with a full-spectrum band uniform reflectance in an effective spectral band range, including a full reflectance plate (reflectance is above 98%) or other reflectance plates (e.g., a uniform reflectance plate with a reflectance of 80%), and the uniform reflectance plate needs to cover the entire camera field of view during photographing. In specific implementation, the uniform reflectivity plate can cover the whole camera view by adjusting the size of the uniform reflectivity plate and the distance between the uniform reflectivity plate and the camera.
Optionally, the dimension of the image collected by the high/multispectral camera can be uniformly cut into h × w × c according to the actual requirement of the image, where h is the height of the image, w is the width of the image, and c is the number of bands (i.e., the number of spectral channels) of the image.
Specifically, in the present embodiment, data of 2048 × 2930 × 192 dimensions is taken as an example;
s20, sequentially calculating the row/column gray scale statistic of each wave band of the high/multi-spectral image, acquiring the distribution function of the row/column gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the row/column gray scale statistic of each wave band;
specifically, the line gray scale statistics of each wave band of the high/multispectral image are sequentially calculated, a distribution function of the line gray scale statistics of each wave band is obtained, and the quantile distance of the distribution function of the line gray scale statistics of each wave band are calculated;
specifically, the line gray statistic of each band is expressed as:
wherein the content of the first and second substances,
is the gray scale mean value of the pixel of the ith row in the p spectral band of the high/multi-spectral image, n is the column number of the high/multi-spectral image,
the gray value of the ith row and the jth column of pixels in the high/multispectral image is obtained;
specifically, a distribution function of the line gray scale statistics is drawn according to the line gray scale statistics (i.e. the gray scale mean index) of each band, and more specifically, the distribution function of the line gray scale statistics of each band is a probability distribution of values of the gray scale statistics in each band within an interval.
Specifically, according to the distribution function of the line gray scale statistic of each wave band, calculating to obtain a first quartile of the line gray scale statistic of the p-th spectral wave band
Third quartile of the p spectral band line gray scale statistic
In particular, a quartile range of the row gray scale statistic, more specifically, a first quartile, is adaptively determined according to an empirical distribution function
The number which is equal to 25% of the number of the p spectral band line gray scale statistics after all the values are arranged from small to large; fourth quartile
Is equal to the first spectral band line gray scale statistic after all numerical values are arranged from small to largeA number of 75%;
specifically, the interquartile range of the p-th spectral band line gray scale statistic
Expressed as:
wherein the content of the first and second substances,
is the first quartile of the p-th spectral band line gray scale statistic,
is the third quartile of the p spectral band line gray scale statistic.
Specifically, calculating the column gray scale statistic of each wave band of the high/multispectral image in sequence, acquiring the distribution function of the column gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the column gray scale statistic of each wave band;
specifically, the column gray statistic of each band is expressed as:
wherein the content of the first and second substances,
is the gray level mean value of the j row pixel in the p spectral band of the high/multi-spectral image, m is the column number of the high/multi-spectral image,
the gray value of the ith row and the jth column of pixels in the high/multispectral image is obtained;
specifically, an empirical distribution function of the mean value is drawn according to the column gray level mean value index of each wave band;
specifically, according to the distribution function of the column gray scale statistic of each wave band, a first quartile of the column gray scale statistic of the p-th spectral wave band is calculated
Third quartile of the p spectral band column gray scale statistic
Specifically, a quartile range of the column gray scale statistic, more specifically, a first quartile, is adaptively determined according to an empirical distribution function
The number which is equal to 25% of the number of the p spectral band column gray scale statistics after the data are arranged from small to large; fourth quartile
The number is equal to 75% of the number of the p spectrum wave band column gray scale statistics after all the numerical values are arranged from small to large; the quartering difference is a robust statistic in representing the situation where variables are scattered in the statistic.
Specifically, the quartile range of the p-th spectral band column gray scale statistic is expressed as:
wherein the content of the first and second substances,
a first quartile of the p spectral band column gray scale statistic;
a third quartile of the p spectral band column gray scale statistic;
more specifically, the pixel gray value statistic is the mean value of the pixel gray values, and has smaller variance compared with the pixel gray values, the distribution of the statistic has more concentrated trend compared with the distribution of the gray values, and the statistic has smaller quantile intervals under the condition of determining the quantile interval, particularly under the premise of specifying the quantile.
S30, setting a judgment interval according to the quantile and the quantile distance of the distribution function of each wave band, and judging the row/column number of an abnormal value in the row/column gray scale statistic of each wave band according to the judgment interval;
specifically, a judgment interval is set according to the quantile and the quantile distance of the line gray scale statistic distribution function of each wave band, and the line number of an abnormal value in the line gray scale statistic of each wave band is judged according to the judgment interval; specifically, normal data are arranged in a calibrated normal interval, and abnormal data are arranged on both sides of the calibrated normal interval;
in the determination interval, the normal interval is expressed as:
wherein the content of the first and second substances,
a quartile distance which is the p spectral band line gray scale statistic;
specifically, the line gray scale statistic when the p-th spectral band
Or
And when the image element of the camera corresponding to the p-th spectral band image line number is abnormal.
Specifically, a judgment interval is set according to the quantile and the quantile distance of the column gray scale statistic distribution function of each wave band, and the column number of an abnormal value in the column gray scale statistic of each wave band is judged according to the judgment interval; specifically, normal data are arranged inside the calibrated normal interval, and abnormal data are arranged on both sides of the calibrated normal interval;
in the determination interval, the normal interval is expressed as:
wherein the content of the first and second substances,
a quartile distance which is the p spectral band column gray scale statistic;
specifically, in this embodiment, the abnormal value identification standard provided by the box chart is used as the standard, the standard range is derived from empirical judgment, and all the related statistical points can be realized by the percentile calculation method of all the gray scale statistics. More specifically, the drawing of the box diagram depends on actual data, the data does not need to be assumed to obey a specific distribution form in advance, no limitation is made on the data, and the box diagram only truly and intuitively represents the original appearance of the data shape; on the other hand, the criterion for judging the abnormal value by the box chart is based on the quartile and the quartile distance, the quartile has certain resistance, up to 25% of data can be changed to any distance without greatly disturbing the quartile, so the abnormal value cannot influence the criterion, and the result of identifying the abnormal value by the box chart is objective, so the judgment interval in the embodiment selects the box chart to identify the abnormal value, and has certain superiority.
Specifically, the column gray scale statistic when the p-th spectral band
Or
And when the image element of the camera corresponding to the p-th spectral band image column number is abnormal.
And S40, determining the position of the camera abnormal pixel according to the line/column number of the abnormal value of each wave band through the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
Specifically, according to the line number of the abnormal value of each wave band, the position of the abnormal pixel of the camera is determined through the corresponding relation until the abnormal pixel of the camera corresponding to all the wave bands is obtained, and according to the current spectrum segment number and the image line number of the high/multi-spectrum image, the conclusion that the specific pixel responds to abnormality in the specific wave band is returned.
Specifically, according to the column number of the abnormal value of each wave band, the position of the abnormal pixel of the camera is determined through the corresponding relation until the abnormal pixel of the camera corresponding to all the wave bands is obtained, and according to the current spectrum segment number and the image column number of the high/multispectral image, the conclusion that the specific pixel responds to abnormality in the specific wave band is returned.
In the embodiment, the key information corresponding to the camera pixel and the image pixel is effectively utilized, additional detection equipment and detection equipment are not required, the adaptability and the practicability to an application scene are strong, and the detection of the camera dead pixel can be conveniently realized; the defect detection of the hyperspectral high/multispectral camera can be efficiently and quickly completed by utilizing the row/column gray value statistical information of each channel of the hyperspectral image; by utilizing the advantage of low variance of the line/column statistics and combining the statistics distribution quantile judgment criterion and the quantile self-adaptive judgment criterion of the statistics distribution, the judgment result of the pixel abnormity of the camera in a specific waveband has higher accuracy and robustness.
With reference to fig. 2-4, distribution quantile-based high/multi-spectral camera dead pixel detection is described in detail by way of specific embodiments.
Specifically, in this embodiment, the high/multispectral image obtained by the full-reflectivity plate is captured by scanning in columns, and the high/multispectral image is cut into data with dimensions of 2048 × 2930 × 192, where fig. 2 is a grayscale map of a 112 th waveband in the high/multispectral image, which is data with dimensions of 2048 × 2930; fig. 3 is a row gray scale statistic distribution diagram of a high/multispectral image 112 band calculated by rows, in which an abscissa is a row gray scale statistic and an ordinate is a distribution probability of the row gray scale statistic, an adaptive decision interval is calculated according to a distribution function of the row gray scale statistic, a decision interval is calibrated on the distribution function by using a distribution quantile decision rule, and a visual detection result is as shown in fig. 4, in which the abscissa is the row gray scale statistic and the ordinate is the distribution probability of the row gray scale statistic, a normal sample is in the interval, and both sides of the interval are abnormal samples; according to the current wave band number and the image line number of the high/multi-spectral image, returning a conclusion that the specific pixel responds abnormally in the specific wave band; and by analogy, judging the abnormal pixels of all the wave bands to obtain the abnormal pixels of the camera corresponding to all the wave bands.
As shown in fig. 5, another embodiment of the present invention discloses a system for detecting a bad pixel of a high/multispectral camera based on a distributed quantile, which comprises:
the image acquisition module 10 is used for acquiring a high/multispectral image obtained by shooting the uniform reflectivity plate by the high/multispectral camera and determining the corresponding relation between the row/column number of each wave band image and the pixel of the camera;
a statistic calculation module 20, configured to sequentially calculate a row/column gray scale statistic of each band of the high/multispectral image, obtain a distribution function of the row/column gray scale statistic of each band, and calculate a quantile and a quantile distance of the distribution function of the row/column gray scale statistic of each band; specifically, the method comprises the following steps:
the line statistic calculation unit is used for calculating the line gray scale statistic of each wave band of the high/multispectral image; the line gray scale statistic of each wave band is expressed as:
wherein the content of the first and second substances,
is the gray scale mean value of the pixel of the ith row in the p spectral band of the high/multi-spectral image, n is the column number of the high/multi-spectral image,
the gray value of the ith row and the jth column of pixels in the high/multispectral image is obtained;
the column statistic calculation unit is used for calculating column gray statistic of each wave band of the high/multispectral image; the column gray statistic of each band is expressed as:
wherein the content of the first and second substances,
is the gray level mean value of the j row pixel in the p spectral band of the high/multi-spectral image, m is the column number of the high/multi-spectral image,
the gray value of the pixel at the ith row and the jth column in the high/multispectral image is obtained.
A judging module 30, configured to set a judgment interval according to the quantile and the quantile distance of the distribution function in each band, and judge, according to the judgment interval, a row/column number of an abnormal value in the row/column grayscale statistics of each band; specifically, the method comprises the following steps:
a line judgment unit for calculating the first quartile of the line gray statistic of the p-th spectrum band according to the distribution function of the line gray statistic of each band
Third quartile of the p spectral band line gray scale statistic
In the determination interval, the normal interval is expressed as:
wherein the content of the first and second substances,
for line grey scale statistics of the p-th spectral bandA four-bit distance;
line gray scale statistics as the p-th spectral band
Or
When the image element of the camera corresponding to the p-th spectral band image line number is abnormal;
a column judgment unit for calculating the first quartile of the column gray statistic of the p-th spectral band according to the distribution function of the column gray statistic of each band
Third quartile of the p spectral band column gray scale statistic
In the determination interval, the normal interval is expressed as:
wherein the content of the first and second substances,
a quartile distance which is the p spectral band column gray scale statistic;
column gray scale statistics as the p-th spectral band
Or
And when the image element of the camera corresponding to the p-th spectral band image column number is abnormal.
And the detection module 40 is used for determining the positions of the abnormal pixels of the camera according to the row/column numbers of the abnormal values of each wave band through the corresponding relation until the abnormal pixels of the camera corresponding to all the wave bands are obtained.
The present invention further provides a readable storage medium for executing the high/multispectral camera dead pixel detection method based on the distribution quantiles in the above embodiments, and in particular, the storage medium stores a computer program, and in particular, the computer program is used for storing a nonvolatile software program, a nonvolatile computer executable program and a module, and when the computer program is executed by a processor, the processor executes the high/multispectral camera dead pixel detection method based on the distribution quantiles in the above embodiments. More specifically, embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by an electronic device, cause the electronic device to execute the high/multispectral camera dead pixel detection method based on distribution quantiles in any of the above method embodiments.
Referring to fig. 6, another embodiment of the present invention further provides a computer device for performing the high/multi-spectral camera dead pixel detection method based on the distribution quantile in the above embodiment. The computer device includes:
one or more processors 710 and a memory 720 storing a computer program, which when executed by the processors, performs the high/multi-spectral camera dead pixel detection method based on distribution quantiles in the above embodiments, for example, one processor 710 in fig. 6.
The electronic device performing the high/multi-spectral camera dead pixel detection method based on the distribution quantile may further include: an input device 730 and an output device 740.
The processor 710, the memory 720, the input device 730, and the output device 740 may be connected by a bus or other means, such as the bus connection in fig. 6.
The memory 720, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules (units) corresponding to the distributed quantile-based high/multi-spectral camera dead pixel detection method in the embodiments of the present invention. The processor 710 executes various functional applications of the server and data processing by running nonvolatile software programs, instructions and modules stored in the memory 720, that is, implements the icon display method of the above-described method embodiment.
The memory 720 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 information on the number of acquired reminders for the application program, and the like. Further, the memory 720 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 720 may optionally include memory located remotely from processor 710, which may be connected over a network to a processing device operating the list items. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 730 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the high/multispectral camera dead-spot detection device based on the distribution quantile. The output device 740 may include a display device such as a display screen.
The one or more modules are stored in the memory 720 and, when executed by the one or more processors 710, perform the distribution quantile-based high/multi-spectral camera dead pixel detection method of any of the method embodiments described above.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
The electronic device of embodiments of the present invention may exist in a variety of forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include: smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, as well as smart toys and portable car navigation devices.
(4) A server: the device for providing the computing service comprises a processor, a hard disk, a memory, a system bus and the like, and the server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing high-reliability service.
(5) Other electronic devices with reminding item recording function.
The above-described embodiments of the apparatus are merely illustrative, and the units (modules) described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Embodiments of the present invention provide a computer program product, wherein the computer program product comprises a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, wherein the program instructions, when executed by an electronic device, cause the electronic device to perform the method for distributed quantile-based high/multispectral camera dead pixel detection in any of the above method embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A high/multispectral camera dead pixel detection method based on distribution quantiles is characterized by comprising the following steps:
acquiring a high/multispectral image obtained by shooting a uniform reflectivity plate by a high/multispectral camera, and determining the corresponding relation between the row/column number of each wave band image and the camera pixel;
sequentially calculating the row/column gray scale statistic of each wave band of the high/multispectral image, acquiring a distribution function of the row/column gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the row/column gray scale statistic of each wave band;
setting a judgment interval according to the quantile and the quantile distance of the distribution function of each wave band, and judging the row/column number of an abnormal value in the row/column gray scale statistic of each wave band according to the judgment interval;
and determining the position of the camera abnormal pixel according to the line/column number of the abnormal value of each wave band through the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
2. The method for detecting the dead pixel of the high/multi-spectral camera based on the distributed quantile according to claim 1, comprising the following steps:
when the high/multispectral camera scans the high/multispectral images according to columns, determining the corresponding relation between the line number of each wave band image and the camera pixel;
sequentially calculating the line gray scale statistic of each wave band of the high/multi-spectral image, acquiring a distribution function of the line gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the line gray scale statistic of each wave band;
setting a judgment interval according to the quantile and the quantile distance of the line gray scale statistic distribution function of each wave band, and judging the line number of an abnormal value in the line gray scale statistic of each wave band according to the judgment interval;
and determining the position of the camera abnormal pixel according to the line number of the abnormal value of each wave band and the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
3. The method for detecting the bad pixel of the high/multi-spectral camera based on the distributed quantile according to claim 2, comprising:
the line gray scale statistic of each wave band is expressed as:
wherein the content of the first and second substances,
is the gray scale mean value of the pixel of the ith row in the p spectral band of the high/multi-spectral image, n is the column number of the high/multi-spectral image,
the gray value of the ith row and the jth column of pixels in the high/multispectral image is obtained.
4. The method for distributed quantile-based high/multi-spectral camera dead pixel detection according to claim 3,
according to the distribution function of the line gray scale statistic of each wave band, calculating to obtain a first quartile of the line gray scale statistic of the p-th spectral wave band
Third quartile of the p spectral band line gray scale statistic
In the determination interval, the normal interval is expressed as:
wherein the content of the first and second substances,
a quartile distance which is the p spectral band line gray scale statistic;
line gray scale statistics as the p-th spectral band
Or
And when the image element of the camera corresponding to the p-th spectral band image line number is abnormal.
5. The method for detecting the dead pixel of the high/multi-spectral camera based on the distributed quantile according to claim 1, comprising the following steps:
when the high/multispectral camera scans the high/multispectral image according to the line, determining the corresponding relation between the column number of each wave band image and the camera pixel;
sequentially calculating the column gray scale statistic of each wave band of the high/multispectral image, acquiring a distribution function of the column gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the column gray scale statistic of each wave band;
setting a judgment interval according to the quantile and the quantile distance of the column gray scale statistic distribution function of each wave band, and judging the column number of an abnormal value in the column gray scale statistic of each wave band according to the judgment interval;
and determining the position of the camera abnormal pixel according to the column number of the abnormal value of each wave band and the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
6. The method for detecting the bad pixel of the high/multi-spectral camera based on the distributed quantile according to claim 5, comprising:
the column gray statistic of each band is expressed as:
wherein the content of the first and second substances,
is the gray level mean value of the j row pixel in the p spectral band of the high/multi-spectral image, m is the column number of the high/multi-spectral image,
the gray value of the ith row and the jth column of pixels in the high/multispectral image is obtained.
7. The method for high/multispectral camera dead pixel detection based on distributed quantiles according to claim 6, comprising:
according to the distribution function of the column gray scale statistic of each wave band, calculating to obtain a first quartile of the column gray scale statistic of the p-th spectral wave band
Third quartile of the p spectral band column gray scale statistic
In the decision interval, the normal interval is expressed as
Wherein the content of the first and second substances,
a quartile distance which is the p spectral band column gray scale statistic;
column gray scale statistics as the p-th spectral band
Or
And when the image element of the camera corresponding to the p-th spectral band image column number is abnormal.
8. A high/multispectral camera dead pixel detection system based on a distribution quantile is characterized by comprising:
the image acquisition module is used for acquiring a high/multispectral image obtained by shooting the uniform reflectivity plate by the high/multispectral camera and determining the corresponding relation between the row/column number of each wave band image and the pixel of the camera;
the statistic calculation module is used for calculating the row/column gray scale statistic of each wave band of the high/multispectral image in sequence, acquiring a distribution function of the row/column gray scale statistic of each wave band, and calculating the quantile and the quantile distance of the distribution function of the row/column gray scale statistic of each wave band;
the judging module is used for setting a judging interval according to the quantile and the quantile distance of the distribution function of each wave band and judging the row/column number of an abnormal value in the row/column gray scale statistic of each wave band according to the judging interval;
and the detection module is used for determining the position of the camera abnormal pixel according to the row/column number of the abnormal value of each wave band through the corresponding relation until the camera abnormal pixel corresponding to all the wave bands is obtained.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, causes the processor to carry out the method according to any one of claims 1-7.
10. A computer device comprising a processor and a memory storing a computer program, characterized in that the computer program, when executed by the processor, performs the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110706053.5A CN113532801A (en) | 2021-06-24 | 2021-06-24 | High/multispectral camera dead pixel detection method and system based on distribution quantile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110706053.5A CN113532801A (en) | 2021-06-24 | 2021-06-24 | High/multispectral camera dead pixel detection method and system based on distribution quantile |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113532801A true CN113532801A (en) | 2021-10-22 |
Family
ID=78096678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110706053.5A Pending CN113532801A (en) | 2021-06-24 | 2021-06-24 | High/multispectral camera dead pixel detection method and system based on distribution quantile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113532801A (en) |
Citations (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6118846A (en) * | 1999-02-23 | 2000-09-12 | Direct Radiography Corp. | Bad pixel column processing in a radiation detection panel |
| US20060221214A1 (en) * | 2005-03-31 | 2006-10-05 | Yanof Arnold W | System and method for bad pixel replacement in image processing |
| CN101210890A (en) * | 2006-12-28 | 2008-07-02 | 夏普株式会社 | Defect detecting device and method, image sensor device and module |
| CN101212703A (en) * | 2006-12-29 | 2008-07-02 | 华晶科技股份有限公司 | Real-time bad image pixel detection method |
| WO2008087961A1 (en) * | 2007-01-16 | 2008-07-24 | Olympus Corporation | Defect detecting device, and defect detecting method |
| CN101304485A (en) * | 2008-05-26 | 2008-11-12 | 北京中星微电子有限公司 | Method and apparatus for compensating bad point |
| US20090040343A1 (en) * | 2007-08-06 | 2009-02-12 | Mediatek Inc. | Methods and apparatuses for defective pixel detection and correction |
| KR20090081653A (en) * | 2008-01-24 | 2009-07-29 | 삼성전자주식회사 | Method of storing location information of bad pixels by defining bad pixel patterns |
| CN101588505A (en) * | 2008-05-21 | 2009-11-25 | 英华达（南京）科技有限公司 | The digital photographing apparatus of the bad point of the method for correcting dead pixel on digital camera device point and tool zero offset capability |
| CN102156981A (en) * | 2011-03-10 | 2011-08-17 | 北京航空航天大学 | Regularized high-order statistics based hyperspectral space multi-target detection method |
| CN102663693A (en) * | 2012-03-26 | 2012-09-12 | 航天恒星科技有限公司 | Least square method-based adaptive radiation correction method for linear array push-broom image |
| CN102957878A (en) * | 2011-08-29 | 2013-03-06 | 深圳市蓝韵实业有限公司 | Method and system for automatically detecting defective pixel on medical image |
| CN103218779A (en) * | 2013-03-26 | 2013-07-24 | 华东师范大学 | Method for detecting and correcting hyperspectral data dead pixels of interference imaging spectrometer |
| CN103425995A (en) * | 2013-07-22 | 2013-12-04 | 西安电子科技大学 | Hyperspectral image classification method based on area similarity low rank expression dimension reduction |
| US20140133774A1 (en) * | 2012-11-09 | 2014-05-15 | Industrial Technology Research Institute | Image processor and image dead pixel detection method thereof |
| CN104104945A (en) * | 2014-07-22 | 2014-10-15 | 西北工业大学 | Star sky image defective pixel robustness detection method |
| CN104754327A (en) * | 2015-03-26 | 2015-07-01 | 山东大学 | Method for detecting and eliminating defective pixels of high spectral image |
| CN105491372A (en) * | 2015-11-24 | 2016-04-13 | 努比亚技术有限公司 | Mobile terminal and information processing method |
| CN106228517A (en) * | 2016-07-15 | 2016-12-14 | 西安诺瓦电子科技有限公司 | Image collecting device image-forming component defect calibration steps |
| CN106897941A (en) * | 2017-01-03 | 2017-06-27 | 北京国能日新系统控制技术有限公司 | A kind of blower fan method for processing abnormal data and device based on quartile box traction substation |
| KR20170080822A (en) * | 2015-12-30 | 2017-07-11 | 엘지디스플레이 주식회사 | Method for detecting defect pixel of organic light emitting display and organic light emitting display using the same |
| CN107016669A (en) * | 2017-03-27 | 2017-08-04 | 福州瑞芯微电子股份有限公司 | A kind of dead pixel points of images detection method and device |
| CN107403344A (en) * | 2017-08-03 | 2017-11-28 | 浙江极赢信息技术有限公司 | A kind of analysis method and device of the Internet activity effect |
| CN107480187A (en) * | 2017-07-10 | 2017-12-15 | 北京京东尚科信息技术有限公司 | User's value category method and apparatus based on cluster analysis |
| CN107704802A (en) * | 2017-08-24 | 2018-02-16 | 西安电子科技大学 | The measurement of high spectrum image clutter and the performance prediction method of Outlier Detection Algorithm |
| CN108490656A (en) * | 2018-04-13 | 2018-09-04 | 凌云光技术集团有限责任公司 | Liquid crystal display image detection method and device |
| CN109242322A (en) * | 2018-09-17 | 2019-01-18 | 江阴利港发电股份有限公司 | Thermal power generation unit general level of the health appraisal procedure based on data analysis |
| CN110458827A (en) * | 2019-08-12 | 2019-11-15 | 深圳蓝韵医学影像有限公司 | Detection method, device, equipment and the medium of medical image bad point |
| CN111713099A (en) * | 2019-06-28 | 2020-09-25 | 深圳市大疆创新科技有限公司 | Image correction method, image correction device and electronic equipment |
| CN112365435A (en) * | 2019-07-25 | 2021-02-12 | 天津大学青岛海洋技术研究院 | Image dead pixel detection and edge-based restoration algorithm |
| CN112583999A (en) * | 2020-12-02 | 2021-03-30 | 广州立景创新科技有限公司 | Lens contamination detection method for camera module |
| CN112656435A (en) * | 2020-12-21 | 2021-04-16 | 明峰医疗系统股份有限公司 | Method for automatically detecting detector dead pixel |
| CN112804426A (en) * | 2020-12-30 | 2021-05-14 | 凌云光技术股份有限公司 | Multi-line linear array camera capable of correcting defective pixels and method |
-
2021
- 2021-06-24 CN CN202110706053.5A patent/CN113532801A/en active Pending
Patent Citations (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6118846A (en) * | 1999-02-23 | 2000-09-12 | Direct Radiography Corp. | Bad pixel column processing in a radiation detection panel |
| US20060221214A1 (en) * | 2005-03-31 | 2006-10-05 | Yanof Arnold W | System and method for bad pixel replacement in image processing |
| CN101210890A (en) * | 2006-12-28 | 2008-07-02 | 夏普株式会社 | Defect detecting device and method, image sensor device and module |
| CN101212703A (en) * | 2006-12-29 | 2008-07-02 | 华晶科技股份有限公司 | Real-time bad image pixel detection method |
| WO2008087961A1 (en) * | 2007-01-16 | 2008-07-24 | Olympus Corporation | Defect detecting device, and defect detecting method |
| US20090040343A1 (en) * | 2007-08-06 | 2009-02-12 | Mediatek Inc. | Methods and apparatuses for defective pixel detection and correction |
| KR20090081653A (en) * | 2008-01-24 | 2009-07-29 | 삼성전자주식회사 | Method of storing location information of bad pixels by defining bad pixel patterns |
| CN101588505A (en) * | 2008-05-21 | 2009-11-25 | 英华达（南京）科技有限公司 | The digital photographing apparatus of the bad point of the method for correcting dead pixel on digital camera device point and tool zero offset capability |
| CN101304485A (en) * | 2008-05-26 | 2008-11-12 | 北京中星微电子有限公司 | Method and apparatus for compensating bad point |
| CN102156981A (en) * | 2011-03-10 | 2011-08-17 | 北京航空航天大学 | Regularized high-order statistics based hyperspectral space multi-target detection method |
| CN102957878A (en) * | 2011-08-29 | 2013-03-06 | 深圳市蓝韵实业有限公司 | Method and system for automatically detecting defective pixel on medical image |
| CN102663693A (en) * | 2012-03-26 | 2012-09-12 | 航天恒星科技有限公司 | Least square method-based adaptive radiation correction method for linear array push-broom image |
| US20140133774A1 (en) * | 2012-11-09 | 2014-05-15 | Industrial Technology Research Institute | Image processor and image dead pixel detection method thereof |
| CN103218779A (en) * | 2013-03-26 | 2013-07-24 | 华东师范大学 | Method for detecting and correcting hyperspectral data dead pixels of interference imaging spectrometer |
| CN103425995A (en) * | 2013-07-22 | 2013-12-04 | 西安电子科技大学 | Hyperspectral image classification method based on area similarity low rank expression dimension reduction |
| CN104104945A (en) * | 2014-07-22 | 2014-10-15 | 西北工业大学 | Star sky image defective pixel robustness detection method |
| CN104754327A (en) * | 2015-03-26 | 2015-07-01 | 山东大学 | Method for detecting and eliminating defective pixels of high spectral image |
| CN105491372A (en) * | 2015-11-24 | 2016-04-13 | 努比亚技术有限公司 | Mobile terminal and information processing method |
| KR20170080822A (en) * | 2015-12-30 | 2017-07-11 | 엘지디스플레이 주식회사 | Method for detecting defect pixel of organic light emitting display and organic light emitting display using the same |
| CN106228517A (en) * | 2016-07-15 | 2016-12-14 | 西安诺瓦电子科技有限公司 | Image collecting device image-forming component defect calibration steps |
| CN106897941A (en) * | 2017-01-03 | 2017-06-27 | 北京国能日新系统控制技术有限公司 | A kind of blower fan method for processing abnormal data and device based on quartile box traction substation |
| CN107016669A (en) * | 2017-03-27 | 2017-08-04 | 福州瑞芯微电子股份有限公司 | A kind of dead pixel points of images detection method and device |
| CN107480187A (en) * | 2017-07-10 | 2017-12-15 | 北京京东尚科信息技术有限公司 | User's value category method and apparatus based on cluster analysis |
| CN107403344A (en) * | 2017-08-03 | 2017-11-28 | 浙江极赢信息技术有限公司 | A kind of analysis method and device of the Internet activity effect |
| CN107704802A (en) * | 2017-08-24 | 2018-02-16 | 西安电子科技大学 | The measurement of high spectrum image clutter and the performance prediction method of Outlier Detection Algorithm |
| CN108490656A (en) * | 2018-04-13 | 2018-09-04 | 凌云光技术集团有限责任公司 | Liquid crystal display image detection method and device |
| CN109242322A (en) * | 2018-09-17 | 2019-01-18 | 江阴利港发电股份有限公司 | Thermal power generation unit general level of the health appraisal procedure based on data analysis |
| CN111713099A (en) * | 2019-06-28 | 2020-09-25 | 深圳市大疆创新科技有限公司 | Image correction method, image correction device and electronic equipment |
| CN112365435A (en) * | 2019-07-25 | 2021-02-12 | 天津大学青岛海洋技术研究院 | Image dead pixel detection and edge-based restoration algorithm |
| CN110458827A (en) * | 2019-08-12 | 2019-11-15 | 深圳蓝韵医学影像有限公司 | Detection method, device, equipment and the medium of medical image bad point |
| CN112583999A (en) * | 2020-12-02 | 2021-03-30 | 广州立景创新科技有限公司 | Lens contamination detection method for camera module |
| CN112656435A (en) * | 2020-12-21 | 2021-04-16 | 明峰医疗系统股份有限公司 | Method for automatically detecting detector dead pixel |
| CN112804426A (en) * | 2020-12-30 | 2021-05-14 | 凌云光技术股份有限公司 | Multi-line linear array camera capable of correcting defective pixels and method |
Non-Patent Citations (4)
| Title |
|---|
| 周雨霁等: "EO-1 Hyperion高光谱数据的质量评价", 《地球信息科学》 * |
| 张潘峰等: "浅析摄像机成像坏点噪点的检测与修复", 《现代电视技术》 * |
| 窦兆玉等: "基于机器视觉的液晶屏幕坏点检测", 《北京信息科技大学学报(自然科学版)》 * |
| 邸帅: "风电机组关键部件故障预测技术研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034078B (en) | Training method of age identification model, age identification method and related equipment | |
| US20190205629A1 (en) | Behavior predicton method, behavior predicton system, and non-transitory recording medium | |
| CN112162930B (en) | Control identification method, related device, equipment and storage medium | |
| CN109815770B (en) | Two-dimensional code detection method, device and system | |
| US8750573B2 (en) | Hand gesture detection | |
| CN107613202B (en) | Shooting method and mobile terminal | |
| CN110493595B (en) | Camera detection method and device, storage medium and electronic device | |
| US20120027252A1 (en) | Hand gesture detection | |
| US8189942B2 (en) | Method for discriminating focus quality of image pickup device | |
| CN109116129B (en) | Terminal detection method, detection device, system and storage medium | |
| CN111935479B (en) | Target image determination method and device, computer equipment and storage medium | |
| CN110059666B (en) | Attention detection method and device | |
| CN111598049B (en) | Cheating identification method and device, electronic equipment and medium | |
| US20230214989A1 (en) | Defect detection method, electronic device and readable storage medium | |
| CN111028222A (en) | Video detection method and device, computer storage medium and related equipment | |
| CN110796651A (en) | Image quality prediction method and device, electronic device and storage medium | |
| US8229879B2 (en) | System and method for auto-adaptive network | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| CN116993654B (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN113532801A (en) | High/multispectral camera dead pixel detection method and system based on distribution quantile | |
| CN110008907B (en) | Age estimation method and device, electronic equipment and computer readable medium | |
| CN115004245A (en) | Target detection method, target detection device, electronic equipment and computer storage medium | |
| CN113870210A (en) | Image quality evaluation method, device, equipment and storage medium | |
| CN113391779A (en) | Parameter adjusting method, device and equipment for paper-like screen | |
| CN112418244A (en) | Target detection method, device and electronic system |
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 |