CN113569713A - Stripe detection method and device for video image and computer readable storage medium - Google Patents
Stripe detection method and device for video image and computer readable storage medium Download PDFInfo
- Publication number
- CN113569713A CN113569713A CN202110839815.9A CN202110839815A CN113569713A CN 113569713 A CN113569713 A CN 113569713A CN 202110839815 A CN202110839815 A CN 202110839815A CN 113569713 A CN113569713 A CN 113569713A
- Authority
- CN
- China
- Prior art keywords
- image
- video
- stripe
- gradient
- determining
- 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 114
- 230000002159 abnormal effect Effects 0.000 claims abstract description 103
- 238000001228 spectrum Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000013139 quantization Methods 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 28
- 230000006835 compression Effects 0.000 claims description 26
- 238000007906 compression Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 230000001629 suppression Effects 0.000 claims description 5
- 230000002547 anomalous effect Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000004422 calculation algorithm Methods 0.000 description 25
- 230000000737 periodic effect Effects 0.000 description 5
- 230000010339 dilation Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a stripe detection method and device for a video image and a computer readable storage medium. The detection method comprises the following steps: compressing the video texture map to obtain a mask image, wherein the video texture map is an image obtained by preprocessing the video image; carrying out quantization processing on continuous smooth areas in the mask image, and respectively determining projection variances of the quantized image in different directions; counting abnormal bright spots in the image frequency spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots with frequency lower than a preset frequency; and determining the fringe detection result of the video image based on the projection variance and the abnormal bright spots. The invention solves the technical problems of poor robustness and low efficiency of video image stripe detection in the related technology.
Description
Technical Field
The invention relates to the technical field of video image processing, in particular to a method and a device for detecting stripes of a video image and a computer readable storage medium.
Background
With the popularization of smart city construction across the country, each large city generates a large amount of video monitoring data every day. However, in the actual use process, the video monitoring system is often large in deployment and control range and long in working time, so that the monitoring video is easily interfered by stripes. Meanwhile, the fringe interference types are very different (for example, horizontal stripes, column stripes, oblique stripes, thick stripes, thin stripes, and periodic stripes are common), and the causes of the fringe interference are often different (for example, the causes of power frequency interference, internal voltage imbalance, current imbalance, transmission, image sensor deviation, system noise or vibration, and the like). In actual use, the streak interference not only reduces the interpretability of the video, but also is prone to cause unpredictable failures. Therefore, it is particularly important for the streak detection of the monitoring system.
The first correlation technique is used for rapidly detecting the stripes of the monitoring video, and the first correlation technique is characterized in that the abnormal bright spots in the Fourier frequency spectrum of the image are used for periodic stripe detection, and because the information of the Fourier frequency spectrum is only used and the periodic characteristics of stripe interference are excessively depended, the detection rate of the video stripes in a real scene is low and the robustness is poor; the second related technology is digital holographic interference fringe detection, and the design key point is that hough transformation is used for detecting fuzzy straight lines, and Fourier transformation is combined to identify the overall characteristics of fringes with the same period.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a stripe detection method and device of a video image and a computer readable storage medium, which at least solve the technical problems of poor robustness and low efficiency of video image stripe detection in the related technology.
According to an aspect of the embodiments of the present invention, there is provided a method for detecting stripes in a video image, including: compressing a video texture map to obtain a mask image, wherein the video texture map is an image obtained by preprocessing a video image; carrying out quantization processing on the continuous smooth area in the mask image, and respectively determining the projection variances of the quantized image in different directions; counting abnormal bright spots in the image frequency spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots with frequency lower than a preset frequency; and determining the stripe detection result of the video image based on the projection variance and the abnormal bright point.
Optionally, the step of compressing the video texture map to obtain a mask image includes: performing binarization compression on the video texture map by using a first filter to obtain a video compressed image; and characterizing the video compression image as a mask image for extracting the continuous smooth area.
Optionally, counting abnormal bright spots in the image spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots with a frequency lower than a preset frequency, and the step includes: converting the continuous smooth area into a frequency domain to obtain a converted image spectrogram, wherein the image spectrogram presents a central symmetry point abnormal bright spot; enhancing the brightness intensity value of an abnormal bright point in the image spectrogram by adopting a second filter; and performing binarization processing on the brightness intensity values of the abnormal bright points to determine the abnormal bright points in the image frequency spectrum of the continuous smooth area.
Optionally, the step of performing quantization processing on continuous smooth areas in the mask image, and determining projection variances of the quantized image in different directions respectively includes: carrying out quantization processing on the continuous smooth area by adopting a preset quantization formula; respectively calculating a first gradient map of the quantized image in a first direction and a second gradient map in a second direction; and calculating a first gradient projection variance corresponding to a first direction and a second gradient projection variance corresponding to a second direction for the first gradient map and the second gradient map, wherein the first gradient projection variance and the second gradient projection variance are used for judging the stripe direction and the stripe intensity on the video image.
Optionally, before the video texture map is compressed to obtain the mask image, the streak detection method further includes: converting the video image into a gray image, and denoising the gray image by using Gaussian filtering to obtain a denoised gray image; calculating the gradient direction and gradient strength of the denoised gray level image; and performing non-maximum suppression processing on the de-noised gray level image based on the gradient direction and the gradient strength to obtain the video texture image.
Optionally, before the video texture map is compressed to obtain the mask image, the streak detection method further includes: extracting the chrominance components of the video image to obtain a chrominance component map; and determining an image spectrogram based on the color component map.
Optionally, after determining the projection variances of the quantized image in different directions respectively, the streak detection method further includes: establishing a video blank picture with the size consistent with that of the mask image, wherein the video blank picture is used for storing the dynamic change information of each pixel point in a preset monitoring video; confirming the total frame number of processed images in a preset monitoring video; and determining whether the pixel points are flicker points or not based on the dynamic change information and the total frame number of the image.
Optionally, the step of determining a streak detection result of the video image based on the projection variance and the abnormal bright point includes: calculating an abnormal bright point rate of the continuous smooth area based on the abnormal bright point in the image spectrum of the continuous smooth area; determining the continuous smooth subarea with the abnormal bright spot rate larger than a first preset threshold value as a stripe candidate area; screening the stripe candidate area based on the projection variances in different directions to obtain a target stripe area; determining a stripe direction in the target stripe region; determining the area with the number of the flicker points in the target stripe area larger than a second preset threshold value as a fast stripe area; and determining a stripe detection result for performing stripe detection on the video image based on the fast stripe region and the target stripe region.
According to another aspect of the embodiments of the present invention, there is also provided a streak detection apparatus for a video image, including: the device comprises a compression unit, a processing unit and a processing unit, wherein the compression unit is used for compressing a video texture map to obtain a mask image, and the video texture map is an image obtained by preprocessing the video image; the calculation unit is used for carrying out quantization processing on the continuous smooth area in the mask image and respectively determining the projection variances of the quantized image in different directions; the statistical unit is used for counting abnormal bright spots in the image frequency spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots lower than a preset frequency; a determining unit, configured to determine a streak detection result of the video image based on the projection variance and the abnormal bright point.
Optionally, the compression unit comprises: the first compression module is used for performing binarization compression on the video texture map by adopting a first filter to obtain a video compression image; and the first extraction module is used for representing the video compression image as a mask image for extracting the continuous smooth area.
Optionally, the statistical unit includes: the first conversion module is used for converting the continuous smooth area into a frequency domain to obtain a converted image spectrogram, wherein the image spectrogram presents a central symmetry point abnormal bright spot; the first enhancement module is used for enhancing the brightness intensity value of an abnormal bright point in the image spectrogram by adopting a second filter; and the first determining module is used for carrying out binarization processing on the brightness intensity values of the abnormal bright points so as to determine the abnormal bright points in the image frequency spectrum of the continuous smooth area.
Optionally, the computing unit comprises: the first quantization module is used for performing quantization processing on the continuous smooth area by adopting a preset quantization formula; the first calculation module is used for respectively calculating a first gradient map of the quantized image in a first direction and a second gradient map in a second direction; and the second calculation module is used for calculating a first gradient projection variance corresponding to a first direction and a second gradient projection variance corresponding to a second direction for the first gradient map and the second gradient map, wherein the first gradient projection variance and the second gradient projection variance are used for judging the stripe direction and the stripe intensity on the video image.
Optionally, the streak detection apparatus further comprises: the first denoising module is used for converting the video texture image into a gray image before the video texture image is compressed to obtain a mask image, and denoising the gray image by Gaussian filtering to obtain a denoised gray image; the third calculation module is used for calculating the gradient direction and the gradient strength of the denoised gray level image; and the first processing module is used for carrying out non-maximum suppression processing on the de-noised gray level image based on the gradient direction and the gradient strength to obtain the video texture image.
Optionally, the streak detection apparatus further comprises: the second extraction module is used for extracting the chrominance components of the video image to obtain a chrominance component map before the video texture map is compressed to obtain a mask image; and the second determination module is used for determining the image spectrogram based on the color component map.
Optionally, the streak detection apparatus further comprises: the first establishing module is used for establishing a video blank image with the size consistent with that of the mask image after respectively determining projection variances of the quantized image in different directions, wherein the video blank image is used for storing dynamic change information of each pixel point in a preset monitoring video; the third determining module is used for determining the total number of processed images in the preset monitoring video; and the fourth determining module is used for determining whether the pixel points are flicker points or not based on the dynamic change information and the total image frame number.
Optionally, the determining unit includes: the fourth calculation module is used for calculating the abnormal bright spot rate of the continuous smooth area based on the abnormal bright spots in the image frequency spectrum of the continuous smooth area; a fifth determining module, configured to determine the continuous smooth sub-area with the abnormal bright point rate greater than the first preset threshold as a stripe candidate area; the first screening module is used for screening the stripe candidate area based on the projection variances in different directions to obtain a target stripe area; a sixth determining module, configured to determine a stripe direction in the target stripe region; the first recording module is used for determining an area, in the target stripe area, of which the number of the flicker points is greater than a second preset threshold value, as a fast stripe area; and the seventh determining module is used for determining a stripe detection result for performing stripe detection on the video image based on the fast stripe area and the target stripe area.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the computer-readable storage medium controls the method for detecting the stripes in the video image according to any one of the above-mentioned apparatuses.
In the embodiment of the invention, a video texture map is compressed to obtain a mask image, wherein the video texture map is an image obtained by preprocessing the video image, then a continuous smooth area in the mask image is quantized, the projection variances of the quantized image in different directions are respectively determined, then abnormal bright spots in the image frequency spectrum of the continuous smooth area are counted, and finally the fringe detection result of the video image is determined based on the projection variances and the abnormal bright spots. In the embodiment, the video texture map is compressed, so that the influence of pixel point fluctuation on algorithm robustness and calculation efficiency can be eliminated, meanwhile, in order to improve the stripe detection efficiency, the video image is quantized, and the stripe detection result in the video image is determined through the projection variance after quantization and the abnormal bright points in the statistical image frequency spectrum, so that the technical problems of poor robustness and low efficiency of video image stripe detection in the related technology are solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of an alternative method of streak detection for video images in accordance with embodiments of the present invention;
FIG. 2 is a flow chart of an alternative method of streak detection for a video image according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a video image streak detection apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
To facilitate understanding of the invention by those skilled in the art, some terms or nouns referred to in the embodiments of the invention are explained below:
Two-Dimensional Discrete Fourier Transform (Two-Dimensional Discrete Fourier Transform), a method of digital transformation, is commonly applied to Transform an image from the spatial domain to the frequency domain.
Discrete Fourier Transform (DFT) is the most basic method of signal analysis.
canny texture detection can remarkably reduce the data size of the image under the condition of keeping the original image attribute.
The embodiment of the invention can be applied to the stripe detection of various video images, such as various monitoring video images (including but not limited to videos shot by various fixed cameras (such as cameras connected with a fill-in light, home entrance cameras, building entrance cameras and the like), videos shot by various mobile cameras (such as mobile terminals-mobile phones, tablets, IPADs and the like). The embodiment fully utilizes the typical characteristic that the fringe interference has periodicity, and combines with the analysis of a space domain and a frequency domain, thereby reducing the influence of various factors on the fringe detection to the maximum extent. In this embodiment, the chrominance components of the video image may be extracted first, the spectrum image of the video image may be obtained through discrete fourier transform, and an algorithm is designed to detect an abnormal bright point in the spectrum image and determine whether stripe noise/interference exists. In addition, the embodiment can also establish a global filtering model through texture features of the video image, can effectively alleviate the influence of complex textures in the video image on the stripe detection, then can calculate gradient projection variances of local areas in different directions in a blocking manner after extracting a smooth area, and is used for judging the direction of the stripe, and finally comprehensively evaluating the stripe interference degree of the video image through detection results of two stages.
In accordance with an embodiment of the present invention, there is provided an embodiment of a method for streak detection in a video image, it should be noted that the steps illustrated in the flowchart of the accompanying drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Example one
Fig. 1 is a flow chart of an alternative method for detecting streaks in a video image, according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
and S102, compressing the video texture map to obtain a mask image, wherein the video texture map is an image obtained by preprocessing the video image.
And step S104, performing quantization processing on the continuous smooth areas in the mask image, and respectively determining the projection variances of the quantized image in different directions.
Step S106, counting abnormal bright spots in the image frequency spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots with frequency lower than a preset frequency.
And step S108, determining the fringe detection result of the video image based on the projection variance and the abnormal bright spot.
Through the steps, the video texture map is compressed to obtain a mask image, wherein the video texture map is an image obtained by preprocessing the video image, then the continuous smooth area in the mask image is quantized, the projection variances of the quantized image in different directions are respectively determined, then the abnormal bright spots in the image frequency spectrum of the continuous smooth area are counted, and finally the fringe detection result of the video image is determined based on the projection variances and the abnormal bright spots. In the embodiment, the video texture map is compressed, so that the influence of pixel point fluctuation on algorithm robustness and calculation efficiency can be eliminated, meanwhile, in order to improve the stripe detection efficiency, the video image is quantized, and the stripe detection result in the video image is determined through the projection variance after quantization and the abnormal bright points in the statistical image frequency spectrum, so that the technical problems of poor robustness and low efficiency of video image stripe detection in the related technology are solved.
In this embodiment, for a surveillance video (for example, a road traffic surveillance video, a mall entrance surveillance video, a building entrance surveillance video, and the like) collected by a camera, video frame images corresponding to a plurality of time points are analyzed, which are referred to as video images for short. In this embodiment, an input image for video streak detection is each frame of video image, and after receiving the video image, texture detection is performed on the input video image on the one hand, so as to extract a continuous smooth region of the image, eliminate interference of image detail texture on streak detection, and calculate gradient projection variance in the smooth region to determine a streak direction. And on the other hand, the chrominance components of the input video image are extracted to calculate an image frequency spectrum, a proper abnormal bright point detection algorithm is designed, and the distribution rule of the abnormal bright points in the frequency spectrum image is counted. And finally, comprehensively evaluating the fringe interference by combining the results of the two.
The following describes embodiments of the present invention in detail with reference to the respective steps.
And S102, compressing the video texture map to obtain a mask image, wherein the video texture map is an image obtained by preprocessing the video image.
In the embodiment of the invention, after the canny texture detection operation and the dilation operation are carried out on the video image, a canny texture map and a canny dilation map can be obtained, if the texture degree of the video image is large (namely the texture of the video image is complex) and indicates that the video image has rich text, the canny texture map is selected as the video texture map to be compressed, otherwise, the canny dilation map is selected as the video texture map to be compressed.
Optionally, the step of compressing the video texture map to obtain a mask image includes: performing binarization compression on the video texture map by adopting a first filter to obtain a video compressed image; the video compressed image is characterized as a mask image that extracts a continuous smooth region.
Since the real texture in the video texture map has a large influence on the detection of the texture, the detection is performed in a smooth area as much as possible. In the embodiment of the invention, in order to obtain a proper smooth area, a compressed video texture map is considered to eliminate the influence of pixel point fluctuation on algorithm robustness and calculation efficiency. In this embodiment, a filter (i.e., the first filter, for example, a 5 × 5 filter) is designed to perform binarization compression on the video texture map, and when extracting the mask image, the design method is as follows: if the gray value of pixels with a certain number of blocks (for example, 8 blocks or more) in the 5 × 5 blocks is greater than the preset value (for example, 230), all the areas are set to be 1, otherwise, the areas are set to be 0, and the obtained video compressed image is used as a mask image for extracting a smooth area.
Optionally, before the video texture map is compressed to obtain the mask image, the streak detection method further includes: converting the video image into a gray image, and denoising the gray image by using Gaussian filtering to obtain a denoised gray image; calculating the gradient direction and gradient strength of the denoised gray level image; and performing non-maximum suppression processing on the denoised gray level image based on the gradient direction and the gradient strength to obtain a video texture image.
In the embodiment of the invention, a video image is converted into a gray image, initial denoising is carried out by Gaussian filtering, and then the gradient direction and the gradient strength of the denoised gray image are respectively calculated by using a formula (1) and a formula (2).
Wherein G is gradient strength, theta is gradient direction, Gx、gyRespectively obtaining gradients in the x direction and the y direction, then obtaining a canny texture map by using a non-maximum inhibition method and combining the gradient direction and the gradient strength, and finally obtaining a canny expansion map by using expansion operation.
In the embodiment of the present invention, the continuous smooth region is extracted by using the obtained mask image as a mask for extracting the smooth region.
And step S104, performing quantization processing on the continuous smooth areas in the mask image, and respectively determining the projection variances of the quantized image in different directions.
In the embodiment of the invention, the algorithm can be accelerated by carrying out quantization processing on the image, and meanwhile, the algorithm has the capability of detecting the direction of the stripes by adding the gradient direction projection variance calculation module, and the false detection can be reduced to a certain extent.
Optionally, the step of performing quantization processing on the continuous smooth region in the mask image, and determining the projection variances of the quantized image in different directions respectively includes: carrying out quantization processing on the continuous smooth area by adopting a preset quantization formula; respectively calculating a first gradient map of the quantized image in a first direction and a second gradient map in a second direction; and calculating a first gradient projection variance corresponding to the first direction and a second gradient projection variance corresponding to the second direction for the first gradient map and the second gradient map, wherein the first gradient projection variance and the second gradient projection variance are used for judging the stripe direction and the stripe intensity on the video image.
In the embodiment of the present invention, the continuous smooth region may be quantized by using formula (3),
wherein I (x, y) represents a pixel point, ImaxRepresenting the maximum pixel point value, IminRepresenting the minimum pixel point value. Then, gradient maps (i.e., a first gradient map in a first direction and a second gradient map in a second direction) in x (e.g., east-west direction of coordinate axes) and y (e.g., north-south direction of coordinate axes) are calculated for the quantized images, and then projection variances (i.e., a first gradient projection variance in the first direction and a second gradient projection variance in the second direction) in x and y directions are calculated for the two gradient maps, respectively, and recorded
Wherein the subscript of var represents the projection variance in different directions, the superscript represents the gradient in different directions, vx，vyAnd the direction and the strength of the stripes are judged.
Step S106, counting abnormal bright spots in the image frequency spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots with frequency lower than a preset frequency.
In the embodiment of the invention, the stripe interference can be analyzed by using a statistical method of abnormal bright spots in a frequency domain, the characteristic of periodicity can be utilized to the maximum extent, and the influence of noise and background on a detection algorithm is relieved.
Optionally, counting abnormal bright spots in the image spectrum of the continuous smooth area, where the abnormal bright spots are bright spots with a frequency lower than a preset frequency, and the step includes: converting the continuous smooth area into a frequency domain to obtain a converted image spectrogram, wherein the image spectrogram presents a central symmetry point abnormal bright spot; enhancing the brightness intensity value of an abnormal bright point in the image spectrogram by adopting a second filter; the luminance intensity values at the plurality of abnormal bright points are binarized to determine abnormal bright points in the image spectrum of the continuous smooth area.
In the embodiment of the present invention, a continuous smooth region is converted into a frequency domain by using a two-dimensional discrete fourier transform, due to a periodic characteristic represented by a part of stripes, a centrosymmetric abnormal bright point appears in a discrete fourier transform spectrum, for a characteristic of a fourier spectrum image, the whole spectrum image can be divided into a central region and an outer region based on a preset weight, and due to an obvious abnormal bright point existing in the central region, only the abnormal bright point in the outer region is considered, and then a filter (i.e., the above-mentioned second filter, for example, a 3 × 3 filter) is designed to enhance an intensity value of the abnormal bright point, and binarization is performed, i.e., if the intensity value is greater than a preset threshold, the abnormal bright point is determined.
And step S108, determining the fringe detection result of the video image based on the projection variance and the abnormal bright spot.
Optionally, before the video texture map is compressed to obtain the mask image, the streak detection method further includes: extracting the chrominance components of the video image to obtain a chrominance component map; and determining an image spectrogram based on the chroma component map.
In the embodiment of the invention, the chrominance components of the video image can be extracted, then the image spectrogram is obtained based on the chrominance components, and then the distribution rule of the abnormal bright points in the spectrogram is counted by establishing a proper abnormal bright point detection algorithm.
Alternatively, after determining the projection variances of the quantized image in different directions, the streak detection method further includes: establishing a video blank picture with the size consistent with that of the mask picture, wherein the video blank picture is used for storing the dynamic change information of each pixel point in a preset monitoring video; confirming the total frame number of processed images in a preset monitoring video; and determining whether the pixel points are flash points or not based on the dynamic change information and the total frame number of the image.
In the embodiment of the invention, firstly, an empty map S (x, y) with the same size as the mask image is established for storing the dynamic change information of each pixel point in the preset monitoring video, meanwhile, the total frame number T processed at present is tracked and stored, and the conversion times of each pixel point are obtained by using a formula (4).
Wherein, F (x, y) and F (x, y) are respectively expressed as compressed binary images of a current frame and a previous frame. In the algorithm, a calculation is made
And (3) recording the pixel points which are larger than a preset value (for example, 0.6) in the obtained values as flicker points, and recording the number of the flicker points.
Optionally, the step of determining a streak detection result of the video image based on the projection variance and the abnormal bright spot includes: calculating the abnormal bright point rate of the continuous smooth area based on the abnormal bright points in the image frequency spectrum of the continuous smooth area; determining a continuous smooth sub-area with the abnormal bright spot rate larger than a first preset threshold value as a stripe candidate area; screening a stripe candidate area based on projection variances in different directions to obtain a target stripe area; determining a stripe direction in a target stripe region; determining an area with the number of the flicker points in the target stripe area larger than a second preset threshold value as a fast stripe area; and determining a stripe detection result for performing stripe detection on the video image based on the fast stripe region and the target stripe region.
In the embodiment of the invention, the video fringe degree is jointly evaluated based on the detection results of the projection variance, the abnormal bright spots and the flicker spots. Setting the area with the abnormal bright point rate larger than the set threshold as a stripe candidate area, discarding other areas which do not meet the conditions, then recording the area with the projection variance larger than the set threshold (for example, 3) in the stripe candidate area as a stripe area, recording the direction of the stripe area, then recording the area with the number of the flicker points larger than the threshold in the stripe area as a fast stripe area, and finally updating the stripe detection result of the video to obtain a comprehensive video stripe evaluation.
The stripe detection method of the video image provided by the embodiment of the invention uses the binary compression characteristic as the basic characteristic of the stripe detection algorithm, so that the algorithm has stronger robustness, meanwhile, the flicker degree of the pixel is evaluated by utilizing the statistical characteristic of the pixel level, so that the algorithm has the capability of detecting the dynamic change degree of the video, and the algorithm can utilize the characteristic of periodicity to the maximum extent by analyzing the stripe interference in the frequency domain, simultaneously relieve the influence of noise and background on the algorithm, and has the capability of detecting the stripe direction by calculating the projection variance in the gradient direction, and simultaneously can reduce false detection.
Example two
In the embodiment of the invention, the typical characteristic that the fringe interference has periodicity is fully utilized, and the spatial domain and frequency domain analysis is combined, so that the influence of various factors on the fringe detection is reduced to the maximum extent. Firstly, extracting chrominance components of a video frame image, obtaining a frequency spectrum image of the video frame image through discrete Fourier transform, detecting abnormal points in the frequency spectrum image through a design algorithm for judging whether stripe interference exists, then establishing a global filtering model through texture characteristics of a picture, relieving the influence of complex textures of the image on stripe detection as much as possible, obtaining a smooth stripe estimation region, calculating gradient projection variances of a local region in the x and y directions in a blocking mode for judging the direction of the stripe, and then comprehensively evaluating the stripe interference degree and the mode of the image through detection results of two stages.
Fig. 2 is a flow chart of another alternative method for detecting streaks in a video image according to an embodiment of the present invention, as shown in fig. 2, firstly, an input of video streaks detection is a current frame image, on one hand, texture detection is performed on the current frame image to obtain a canny map and a canny expansion map, one of the canny map and the canny expansion map is selected as a canny texture map based on a texture degree of the current frame image, a smooth region of the image is extracted by using the canny texture map to eliminate interference of image detail textures on the streak detection, and a gradient projection variance is calculated in the smooth region to determine a direction of the streaks. And on the other hand, extracting the chrominance components of the current frame image to be used for calculating the DFT frequency spectrum image, designing a proper abnormal bright point detection algorithm to detect abnormal bright points, and counting the distribution rule of the abnormal bright points in the frequency spectrum image. And finally, comprehensively evaluating the stripes by combining the results of the two. The method comprises the following specific steps:
the method comprises the following steps: and performing canny texture detection operation and dilation operation on the current frame image. Firstly, converting a current image into a gray image, carrying out primary denoising by using Gaussian filtering, and then calculating the gradient direction and the intensity of the current image according to the following formula:
wherein G is the gradient strength; theta is the gradient direction; gx、gyGradients in the x and y directions, respectively; and then, acquiring a canny image by using a non-maximum value inhibition method and combining the gradient direction, and finally acquiring a canny expansion image by using an expansion operation.
Step two: a suitable base feature is selected. The canny image or the canny expansion image is selected based on the texture degree, the texture degree is large, the image is complex in texture and rich in text, and therefore the canny image can be used as a basic feature (namely the canny texture image), and otherwise, the canny expansion image is selected.
Step three: and extracting a smooth area. Since the real texture of the image has a large influence on the detection of the streak, the detection is performed in a smooth area as much as possible. In order to obtain a proper smooth area, the canny texture map can be compressed to eliminate the influence of pixel point fluctuation on algorithm robustness and computational efficiency. In order to initially fill the foreground region, the canny texture map is first reduced, and then a 5 × 5 filter is designed to perform binarization compression on the canny texture map, in such a way that if the gray value of 8 or more pixels in a 5 × 5 block is greater than 230, the region is set to be 1, and otherwise, the region is set to be 0. The image obtained at this time is used as a mask (mask) for extracting a smooth region.
Step four: and counting abnormal bright spots in the DFT spectrum of the smooth area. After a continuous smooth region is extracted by using the mask obtained in the third step, the smooth region is converted into a frequency domain by using two-dimensional discrete Fourier transform:
where F (x, y) represents a gray distribution function with x, y as variables in the spatial domain, F (u, v) represents a frequency distribution function with u, v as variables in the frequency domain, and i represents an imaginary part (i.e., i21). Due to the periodic characteristic reflected by partial stripes, the DFT frequency spectrum can present centrosymmetric abnormal bright spots, aiming at the characteristic of a Fourier frequency spectrum image, the whole frequency spectrum image is divided into a central area and an outer area based on the weight omega, a 3 x 3 filter is designed to enhance the intensity value of the abnormal bright spots, binarization is carried out, if the intensity value is larger than a threshold value, the abnormal bright spots are determined, and finally the abnormal bright spot rate psi is calculated.
Step five: the gradient direction projection variance is calculated. After the smooth area is extracted by the mask obtained in the third step, the area is quantized according to the following formula:
then, gradient images in the x and y directions are respectively calculated for the quantized images, then, the projection variances in the x and y directions are calculated for the two gradient images and are recorded
V hereinx，vyAnd the direction and the strength of the stripes are judged.
Step six: pixel level statistical features. Firstly, establishing an empty map S (x, y) with the size consistent with that of a compressed canny texture map for storing the dynamic change information of each pixel point in a section of video. Meanwhile, the total frame number T processed at present is tracked and stored, the transformation times of each pixel point are calculated by the following formula,
wherein, F (x, y) and F (x, y) are compressed binary images of the current frame and the previous frame, respectively. In this algorithm, will
And marking the pixel points with the middle size larger than 0.6 as flicker points, and marking the number of the pixel points as K.
Step seven: and (5) detecting stripes. And performing joint evaluation on the video fringe degree based on the detection results of the fourth step, the fifth step and the sixth step. Regarding the result of the step four, setting the area with the abnormal bright point rate larger than the set threshold as a stripe candidate area, and discarding other areas which do not meet the condition; for the result of step five, v in the stripe candidate area is dividedxOr vyThe area above the set threshold (e.g. 3) is marked as a stripe area and its direction is recorded; and regarding the result in the sixth step, recording the area with the number of the flicker points larger than the threshold value in the stripe area as a fast stripe area, and thus obtaining a comprehensive evaluation on the stripe condition of the video.
Step eight: and (5) post-processing of video fringe detection. And selectively filtering false alarms caused by certain special conditions.
The stripe detection algorithm provided by the embodiment of the invention has the following beneficial effects:
(1) the canny texture binary compression feature is used as a basic feature, so that the algorithm has stronger robustness;
(2) the flicker degree of the pixels is evaluated by utilizing the statistical characteristics of the pixel level, so that the algorithm has the capability of detecting the dynamic change degree of the video;
(3) the characteristic of periodicity of the interference can be utilized to the maximum extent by analyzing the interference of the stripes in the frequency domain, and meanwhile, the influence of noise and background on a detection algorithm is relieved;
(4) by calculating the gradient direction projection variance, the algorithm has the capability of detecting the direction of the stripes, and meanwhile, the false detection can be reduced.
EXAMPLE III
The streak detection device for video images provided in this embodiment includes a plurality of implementation units, and each implementation unit corresponds to each implementation step in the first embodiment.
Fig. 3 is a schematic diagram of a video image streak detection apparatus according to an embodiment of the present invention, as shown in fig. 3, the detection apparatus may include: a compression unit 30, a calculation unit 32, a statistics unit 34, a determination unit 36, wherein,
the compression unit 30 is configured to compress the video texture map to obtain a mask image, where the video texture map is an image obtained by preprocessing the video image;
a calculating unit 32, configured to perform quantization processing on the continuous smooth regions in the mask image, and determine projection variances of the quantized image in different directions respectively;
a counting unit 34, configured to count an abnormal bright spot in the image spectrum of the continuous smooth area, where the abnormal bright spot is a bright spot lower than a preset frequency;
and a determining unit 36 for determining a streak detection result of the video image based on the projection variance and the abnormal bright point.
The above fringe detection device can compress the video texture map through the compression unit 30 to obtain the mask image, wherein the video texture map is an image obtained by preprocessing the video image, then quantize the continuous smooth area in the mask image through the calculation unit 32, respectively determine the projection variances of the quantized image in different directions, then count the abnormal bright spots in the image spectrum of the continuous smooth area through the counting unit 34, wherein the abnormal bright spots are bright spots lower than the preset frequency, and finally determine the fringe detection result of the video image through the determination unit 36 based on the projection variances and the abnormal bright spots. In the embodiment, the video texture map is compressed, so that the influence of pixel point fluctuation on algorithm robustness and calculation efficiency can be eliminated, meanwhile, in order to improve the stripe detection efficiency, the video image is quantized, and the stripe detection result in the video image is determined through the projection variance after quantization and the abnormal bright points in the statistical image frequency spectrum, so that the technical problems of poor robustness and low efficiency of video image stripe detection in the related technology are solved.
Optionally, the compression unit includes: the first compression module is used for performing binarization compression on the video texture map by adopting a first filter to obtain a video compression image; and the first extraction module is used for representing the video compression image as a mask image for extracting a continuous smooth area.
Optionally, the statistical unit includes: the first conversion module is used for converting the continuous smooth area into a frequency domain to obtain a converted image spectrogram, wherein the image spectrogram presents a central symmetry point abnormal bright spot; the first enhancement module is used for enhancing the brightness intensity value of an abnormal bright point in the image spectrogram by adopting a second filter; the first determining module is used for carrying out binarization processing on the brightness intensity values of the abnormal bright points so as to determine the abnormal bright points in the image frequency spectrum of the continuous smooth area.
Optionally, the computing unit includes: the first quantization module is used for performing quantization processing on the continuous smooth area by adopting a preset quantization formula; the first calculation module is used for respectively calculating a first gradient map of the quantized image in a first direction and a second gradient map in a second direction; and the second calculation module is used for calculating a first gradient projection variance corresponding to the first direction and a second gradient projection variance corresponding to the second direction for the first gradient map and the second gradient map, wherein the first gradient projection variance and the second gradient projection variance are used for judging the stripe direction and the stripe intensity on the video image.
Optionally, the streak detection apparatus further includes: the first denoising module is used for converting the video texture image into a gray image before the video texture image is compressed to obtain a mask image, and denoising the gray image by using Gaussian filtering to obtain a denoised gray image; the third calculation module is used for calculating the gradient direction and the gradient strength of the denoised gray level image; and the first processing module is used for carrying out non-maximum suppression processing on the denoised gray level image based on the gradient direction and the gradient strength to obtain a video texture image.
Optionally, the streak detection apparatus further includes: the second extraction module is used for extracting the chrominance components of the video image to obtain a chrominance component map before the video texture map is compressed to obtain a mask image; and the second determination module is used for determining the image spectrogram based on the color component map.
Optionally, the streak detection apparatus further includes: the first establishing module is used for establishing a video blank consistent with the mask image in size after determining the projection variances of the quantized image in different directions respectively, wherein the video blank is used for storing the dynamic change information of each pixel point in a preset monitoring video; the third determining module is used for determining the total number of processed images in the preset monitoring video; and the fourth determining module is used for determining whether the pixel points are flicker points or not based on the dynamic change information and the total frame number of the image.
Optionally, the determining unit includes: the fourth calculation module is used for calculating the abnormal bright spot rate of the continuous smooth area based on the abnormal bright spots in the image frequency spectrum of the continuous smooth area; the fifth determining module is used for determining the continuous smooth subarea with the abnormal bright spot rate larger than the first preset threshold value as a stripe candidate area; the first screening module is used for screening the stripe candidate area based on the projection variances in different directions to obtain a target stripe area; a sixth determining module, configured to determine a stripe direction in the target stripe region; the first recording module is used for determining an area with the number of the flashing points in the target stripe area larger than a second preset threshold value as a fast stripe area; and the seventh determining module is used for determining a stripe detection result for performing stripe detection on the video image based on the fast stripe area and the target stripe area.
The above-mentioned streak detection apparatus may further include a processor and a memory, and the above-mentioned compressing unit 30, the calculating unit 32, the counting unit 34, the determining unit 36, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to implement the corresponding functions.
The processor comprises a kernel, and the kernel calls a corresponding program unit from the memory. The kernel can be set to be one or more, and the streak detection result of the video image is determined by adjusting the kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: compressing the video texture map to obtain a mask image; carrying out quantization processing on continuous smooth areas in the mask image, and respectively determining projection variances of the quantized image in different directions; counting abnormal bright spots in the image frequency spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots with frequency lower than a preset frequency; and determining the fringe detection result of the video image based on the projection variance and the abnormal bright spots.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and the computer program controls, when running, the method for detecting the stripes in the video image in any one of the above-mentioned apparatuses where the computer-readable storage medium is located.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units 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 units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for detecting streaks in a video image, comprising:
compressing a video texture map to obtain a mask image, wherein the video texture map is an image obtained by preprocessing a video image;
carrying out quantization processing on the continuous smooth area in the mask image, and respectively determining the projection variances of the quantized image in different directions;
counting abnormal bright spots in the image frequency spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots with frequency lower than a preset frequency;
and determining the stripe detection result of the video image based on the projection variance and the abnormal bright point.
2. The streak detection method according to claim 1, wherein the step of compressing the video texture map to obtain the mask image comprises:
performing binarization compression on the video texture map by using a first filter to obtain a video compressed image;
and characterizing the video compression image as a mask image for extracting the continuous smooth area.
3. The streak detection method according to claim 1, wherein the step of counting the abnormal bright spots in the image spectrum of the continuous smooth area comprises:
converting the continuous smooth area into a frequency domain to obtain a converted image spectrogram, wherein the image spectrogram presents a central symmetry point abnormal bright spot;
enhancing the brightness intensity value of an abnormal bright point in the image spectrogram by adopting a second filter;
and performing binarization processing on the brightness intensity values of the abnormal bright points to determine the abnormal bright points in the image frequency spectrum of the continuous smooth area.
4. The streak detection method according to claim 1, wherein the step of quantizing the continuous smooth regions in the mask image and determining the projection variances of the quantized image in different directions, respectively, comprises:
carrying out quantization processing on the continuous smooth area by adopting a preset quantization formula;
respectively calculating a first gradient map of the quantized image in a first direction and a second gradient map in a second direction;
and calculating a first gradient projection variance corresponding to a first direction and a second gradient projection variance corresponding to a second direction for the first gradient map and the second gradient map, wherein the first gradient projection variance and the second gradient projection variance are used for judging the stripe direction and the stripe intensity on the video image.
5. The streak detection method according to claim 1, wherein before the compressing the video texture map to obtain the mask image, the streak detection method further comprises:
converting the video image into a gray image, and denoising the gray image by using Gaussian filtering to obtain a denoised gray image;
calculating the gradient direction and gradient strength of the denoised gray level image;
and performing non-maximum suppression processing on the de-noised gray level image based on the gradient direction and the gradient strength to obtain the video texture image.
6. The streak detection method according to claim 1, wherein before the compressing the video texture map to obtain the mask image, the streak detection method further comprises:
extracting the chrominance components of the video image to obtain a chrominance component map;
and determining an image spectrogram based on the color component map.
7. The streak detection method according to claim 1, wherein after the projection variances of the quantized image in different directions are respectively determined, the streak detection method further comprises:
establishing a video blank picture with the size consistent with that of the mask image, wherein the video blank picture is used for storing the dynamic change information of each pixel point in a preset monitoring video;
confirming the total frame number of processed images in a preset monitoring video;
and determining whether the pixel points are flicker points or not based on the dynamic change information and the total frame number of the image.
8. The streak detection method according to claim 1, wherein the step of determining a streak detection result of the video image based on the projection variance and the anomalous bright spots comprises:
calculating an abnormal bright point rate of the continuous smooth area based on the abnormal bright point in the image spectrum of the continuous smooth area;
determining the continuous smooth subarea with the abnormal bright spot rate larger than a first preset threshold value as a stripe candidate area;
screening the stripe candidate area based on the projection variances in different directions to obtain a target stripe area;
determining a stripe direction in the target stripe region;
determining the area with the number of the flicker points in the target stripe area larger than a second preset threshold value as a fast stripe area;
and determining a stripe detection result for performing stripe detection on the video image based on the fast stripe region and the target stripe region.
9. A streak detection apparatus for a video image, comprising:
the device comprises a compression unit, a processing unit and a processing unit, wherein the compression unit is used for compressing a video texture map to obtain a mask image, and the video texture map is an image obtained by preprocessing the video image;
the calculation unit is used for carrying out quantization processing on the continuous smooth area in the mask image and respectively determining the projection variances of the quantized image in different directions;
the statistical unit is used for counting abnormal bright spots in the image frequency spectrum of the continuous smooth area, wherein the abnormal bright spots are bright spots lower than a preset frequency;
a determining unit, configured to determine a streak detection result of the video image based on the projection variance and the abnormal bright point.
10. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium controls an apparatus to execute the method for detecting the streaks in the video image according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110839815.9A CN113569713A (en) | 2021-07-23 | 2021-07-23 | Stripe detection method and device for video image and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110839815.9A CN113569713A (en) | 2021-07-23 | 2021-07-23 | Stripe detection method and device for video image and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113569713A true CN113569713A (en) | 2021-10-29 |
Family
ID=78167039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110839815.9A Pending CN113569713A (en) | 2021-07-23 | 2021-07-23 | Stripe detection method and device for video image and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113569713A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549843A (en) * | 2022-04-22 | 2022-05-27 | 珠海视熙科技有限公司 | Stroboscopic stripe detection and elimination method and device, camera equipment and storage medium |
| CN116184407A (en) * | 2023-02-22 | 2023-05-30 | 北京东方至远科技股份有限公司 | Automatic marking method, device and equipment for SAR image radiation quality problem |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005061929A (en) * | 2003-08-08 | 2005-03-10 | Ricoh Co Ltd | Defect inspection method |
| JP2005345290A (en) * | 2004-06-03 | 2005-12-15 | Seiko Epson Corp | Streak-like flaw detecting method and streak-like flaw detector |
| CN101622859A (en) * | 2007-03-05 | 2010-01-06 | 恩益禧电子股份有限公司 | Imaging device and flicker detection method |
| WO2011000226A1 (en) * | 2009-07-03 | 2011-01-06 | 深圳泰山在线科技有限公司 | Target detecting method and device and used image collecting apparatus thereof |
| CN103530644A (en) * | 2013-10-25 | 2014-01-22 | 天津工业大学 | Automatic identification method for weave structures of striped fabric |
| CN103971406A (en) * | 2014-05-09 | 2014-08-06 | 青岛大学 | Underwater target three-dimensional reconstruction method based on line structured light |
| CN104427210A (en) * | 2013-08-23 | 2015-03-18 | 浙江大华技术股份有限公司 | A method and device for detecting a random abnormal blinking dot |
| CN105263018A (en) * | 2015-10-12 | 2016-01-20 | 浙江宇视科技有限公司 | Method and device for detecting superposed stripe in video image |
| JP2016063529A (en) * | 2014-09-22 | 2016-04-25 | リコーイメージング株式会社 | Image processing system |
| CN106127759A (en) * | 2016-06-22 | 2016-11-16 | 成都市晶林科技有限公司 | The detection method of infrared image fringes noise |
| CN106303158A (en) * | 2016-09-30 | 2017-01-04 | 杭州电子科技大学 | A kind of striped method for detecting abnormality in video image |
| CN109712107A (en) * | 2017-10-26 | 2019-05-03 | 北京航天长峰科技工业集团有限公司 | A kind of monitor video striped rapid detection method |
| CN109816663A (en) * | 2018-10-15 | 2019-05-28 | 华为技术有限公司 | A kind of image processing method, device and equipment |
| CN111685782A (en) * | 2019-03-12 | 2020-09-22 | 佳能株式会社 | Radiation imaging apparatus, image processing apparatus and method, and storage medium |
| CN111741186A (en) * | 2020-06-11 | 2020-10-02 | 浙江大华技术股份有限公司 | Video jitter detection method, device and system |
| CN111815578A (en) * | 2020-06-23 | 2020-10-23 | 浙江大华技术股份有限公司 | Image stripe detection method, video monitoring system and related device |
| CN112291551A (en) * | 2020-06-23 | 2021-01-29 | 广州红贝科技有限公司 | Video quality detection method based on image processing, storage device and mobile terminal |
| CN112752093A (en) * | 2020-12-25 | 2021-05-04 | 浙江大华技术股份有限公司 | Video fringe detection method and device, storage medium and electronic device |
-
2021
- 2021-07-23 CN CN202110839815.9A patent/CN113569713A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005061929A (en) * | 2003-08-08 | 2005-03-10 | Ricoh Co Ltd | Defect inspection method |
| JP2005345290A (en) * | 2004-06-03 | 2005-12-15 | Seiko Epson Corp | Streak-like flaw detecting method and streak-like flaw detector |
| CN101622859A (en) * | 2007-03-05 | 2010-01-06 | 恩益禧电子股份有限公司 | Imaging device and flicker detection method |
| WO2011000226A1 (en) * | 2009-07-03 | 2011-01-06 | 深圳泰山在线科技有限公司 | Target detecting method and device and used image collecting apparatus thereof |
| CN104427210A (en) * | 2013-08-23 | 2015-03-18 | 浙江大华技术股份有限公司 | A method and device for detecting a random abnormal blinking dot |
| CN103530644A (en) * | 2013-10-25 | 2014-01-22 | 天津工业大学 | Automatic identification method for weave structures of striped fabric |
| CN103971406A (en) * | 2014-05-09 | 2014-08-06 | 青岛大学 | Underwater target three-dimensional reconstruction method based on line structured light |
| JP2016063529A (en) * | 2014-09-22 | 2016-04-25 | リコーイメージング株式会社 | Image processing system |
| CN105263018A (en) * | 2015-10-12 | 2016-01-20 | 浙江宇视科技有限公司 | Method and device for detecting superposed stripe in video image |
| CN106127759A (en) * | 2016-06-22 | 2016-11-16 | 成都市晶林科技有限公司 | The detection method of infrared image fringes noise |
| CN106303158A (en) * | 2016-09-30 | 2017-01-04 | 杭州电子科技大学 | A kind of striped method for detecting abnormality in video image |
| CN109712107A (en) * | 2017-10-26 | 2019-05-03 | 北京航天长峰科技工业集团有限公司 | A kind of monitor video striped rapid detection method |
| CN109816663A (en) * | 2018-10-15 | 2019-05-28 | 华为技术有限公司 | A kind of image processing method, device and equipment |
| CN111685782A (en) * | 2019-03-12 | 2020-09-22 | 佳能株式会社 | Radiation imaging apparatus, image processing apparatus and method, and storage medium |
| CN111741186A (en) * | 2020-06-11 | 2020-10-02 | 浙江大华技术股份有限公司 | Video jitter detection method, device and system |
| CN111815578A (en) * | 2020-06-23 | 2020-10-23 | 浙江大华技术股份有限公司 | Image stripe detection method, video monitoring system and related device |
| CN112291551A (en) * | 2020-06-23 | 2021-01-29 | 广州红贝科技有限公司 | Video quality detection method based on image processing, storage device and mobile terminal |
| CN112752093A (en) * | 2020-12-25 | 2021-05-04 | 浙江大华技术股份有限公司 | Video fringe detection method and device, storage medium and electronic device |
Non-Patent Citations (4)
| Title |
|---|
| XU-HUA LIU ET AL: "On study of a method for detecting micro-deformation defects of steel plate surface", 《PROC. OF SPIE》, 31 December 2020 (2020-12-31), pages 1 - 10 * |
| 王珩等: "一种视频监控图像条纹噪声的快速检测方法", 《微型机与应用》, vol. 30, no. 17, 31 December 2011 (2011-12-31), pages 36 - 39 * |
| 邹媛媛: "《基于结构光视觉的激光拼焊焊缝测量方法》", 30 September 2020, pages: 69 - 71 * |
| 陈捷等: "SAR图像海洋内波参数自动提取方法", 《海洋技术学报》, vol. 33, no. 6, 31 December 2014 (2014-12-31), pages 20 - 27 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549843A (en) * | 2022-04-22 | 2022-05-27 | 珠海视熙科技有限公司 | Stroboscopic stripe detection and elimination method and device, camera equipment and storage medium |
| CN116184407A (en) * | 2023-02-22 | 2023-05-30 | 北京东方至远科技股份有限公司 | Automatic marking method, device and equipment for SAR image radiation quality problem |
| CN116184407B (en) * | 2023-02-22 | 2023-08-22 | 北京东方至远科技股份有限公司 | Automatic marking method, device and equipment for SAR image radiation quality problem |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106780392B (en) | Image fusion method and device | |
| Lin et al. | Preprocessing reference sensor pattern noise via spectrum equalization | |
| CN108549874B (en) | Target detection method, target detection equipment and computer-readable storage medium | |
| CN110366001B (en) | Method and device for determining video definition, storage medium and electronic device | |
| CN109064504B (en) | Image processing method, apparatus and computer storage medium | |
| CN113569713A (en) | Stripe detection method and device for video image and computer readable storage medium | |
| US10769478B2 (en) | Convolutional neutral network identification efficiency increasing method and related convolutional neutral network identification efficiency increasing device | |
| CN111784605A (en) | Image denoising method based on region guidance, computer device and computer readable storage medium | |
| CN110717922A (en) | Image definition evaluation method and device | |
| CN109903265B (en) | Method and system for setting detection threshold value of image change area and electronic device thereof | |
| CN108961209B (en) | Pedestrian image quality evaluation method, electronic device and computer readable medium | |
| CN113052754B (en) | Method and device for blurring picture background | |
| CN112862753A (en) | Noise intensity estimation method and device and electronic equipment | |
| CN115131714A (en) | Intelligent detection and analysis method and system for video image | |
| CN115131229A (en) | Image noise reduction and filtering data processing method and device and computer equipment | |
| CN112204957A (en) | White balance processing method and device, movable platform and camera | |
| CN112435182B (en) | Image noise reduction method and device | |
| CN113592801A (en) | Method and device for detecting stripe interference of video image | |
| CN112541853A (en) | Data processing method, device and equipment | |
| CN116228712A (en) | Multi-scale slope disaster monitoring method, system and device | |
| CN116129195A (en) | Image quality evaluation device, image quality evaluation method, electronic device, and storage medium | |
| CN111147693B (en) | Noise reduction method and device for full-size photographed image | |
| Sonawane et al. | Image quality assessment techniques: An overview | |
| CN112329572B (en) | Rapid static living body detection method and device based on frame and flash point | |
| CN114359183A (en) | Image quality evaluation method and device, and lens occlusion determination method |
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 |