A video key frame secondary extraction method and system for transformer substation terminal blocks

Abstract

The present invention provides a method and system for secondary extraction of video key frames for converter station terminal blocks, and relates to the field of video processing. The method comprises: performing video acquisition on the converter station terminal block; performing feature extraction and grayscale processing on each frame of the video; subtracting the grayscale values ​​of the corresponding pixel points of two adjacent frames of images, and taking the absolute value thereof to obtain a differential value; comparing the differential value with a set differential threshold, and if the differential value is higher than the set differential threshold, extracting the frame as a key frame of the video, and establishing a preliminary picture set; solving the problems of a large number of pictures per frame, high similarity of pictures per frame, and uneven picture clarity in the terminal block video shot manually in the current converter station.

Description

Technical Field

[0001] The present invention relates to the technical field of video processing, and in particular to a method and system for secondary extraction of video key frames oriented to a terminal block of a converter station. Background Art

[0002] For videos, they are composed of many still pictures, which are called frames. Due to the large number of video frames and the high similarity between adjacent frames, it takes a lot of time for the computer to process the video. In order to effectively reduce the computer computing time, it is necessary to filter and extract the video frames. After extracting the video key frames that can contain effective information, the key frames can be processed, which can greatly reduce the computing time.

[0003] In the application scenario of the converter station, in order to improve the workload of data collection on the terminal block on site, it is mostly collected in the form of video. Due to the uncertainty of manual shooting clarity and the similarity of the shooting objects, the current video key frame extraction technology for terminal blocks still has great limitations, such as a large number of pictures, high similarity of each frame, and uneven picture clarity. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the shortcomings of the prior art, the present invention provides a method and system for secondary extraction of video key frames for terminal blocks in converter stations, which solves the problems of a large number of pictures per frame, high similarity of pictures per frame, and uneven picture clarity in the manually shot terminal block videos in current converter stations.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] On the one hand, a video key frame secondary extraction method for a transformer substation terminal block is provided, comprising:

[0009] Conduct video capture of the actual terminal block of the converter station;

[0010] Extract features and grayscale each frame in the video;

[0011] Subtract the grayscale values ​​of the corresponding pixels of two adjacent frames of images, and take their absolute values ​​to obtain the difference value;

[0012] The difference value is compared with a set difference threshold, and if the difference value is higher than the set difference threshold, the frame is extracted to become a key frame of the video, and a preliminary picture set is established;

[0013] Perform convolution operation on the grayscale value of the pixel point corresponding to each image in the preliminary image set through the Laplacian mask to obtain Conv;

[0014] Calculate the standard deviation between the grayscale values ​​of Conv and the corresponding pixels of each image, where the standard deviation represents the clarity of each image;

[0015] Set the clarity threshold, define the image whose clarity is lower than the clarity threshold as blurry, and define the image whose clarity is higher than the clarity threshold as clear.

[0016] Preferably, the video capture of the actual terminal block of the converter station is achieved by a high-definition camera, and the high-definition camera is installed in the converter station room where it can clearly capture the actual picture of the terminal block.

[0017] Preferably, the feature extraction and grayscale processing of each frame of the video specifically includes:

[0018] Assume that the nth frame and the n-1th frame images in the video sequence are f n and f n-1 , the grayscale values ​​of the corresponding pixels of the two frames of images after feature extraction and grayscale processing are recorded as f n (x,y) and f n-1 (x,y).

[0019] Preferably, the grayscale values ​​of corresponding pixels of two adjacent frames of images are subtracted and their absolute values ​​are taken to obtain the difference value. The specific implementation formula is:

[0020] D n (x, y) = |f n (x, y)-f n-1 (x, y)|

[0021] Among them, D n Indicates the difference value.

[0022] Preferably, the step of comparing the difference value with a set difference threshold, and if the difference value is higher than the set difference threshold, extracting the frame to become a key frame of the video, and establishing a preliminary picture set, specifically includes:

[0023] The difference value is compared with the set difference threshold. The larger the difference value between two adjacent frames, the greater the difference between the two adjacent frames. A difference value threshold ζ between two adjacent frames is set. If the difference value between a frame and the adjacent previous frame is higher than the set threshold ζ, D is satisfied. n >ζ, then the frame is extracted to become the key frame of the video, the first video key frame extraction is realized, and the preliminary picture set Ω1 is established.

[0024] Preferably, performing a convolution operation on the grayscale value of a pixel point corresponding to each image in the preliminary picture set through a Laplace mask to obtain Conv specifically includes:

[0025] In the process of performing convolution operation on the grayscale value of the pixel point corresponding to each image in the preliminary image set through the Laplace mask, the grayscale value of the pixel point corresponding to each image in the set Ω1 is set to f(x, y), and the convolution operation is performed through the Laplace mask to obtain Conv, as shown in the following formula:

[0026]

[0027] in K should be selected so that each array element is an integer and the sum of all array elements is zero.

[0028] On the other hand, a video key frame secondary extraction system for a transformer substation terminal block is provided, the system comprising a multi-shot primary video key frame extraction unit considering frame difference correlation and a multi-shot secondary key frame extraction unit considering definition complementarity;

[0029] The multi-shot one-shot video key frame extraction unit considering frame difference correlation: extracting features and graying each frame in the video, then making a difference between the gray values ​​of two adjacent frames, comparing the difference value with a set difference threshold, realizing the first video key frame extraction, and establishing a preliminary picture set set Ω1;

[0030] The multi-lens secondary key frame extraction unit considering the complementarity of clarity includes performing a convolution operation on the grayscale values ​​of the pixels corresponding to each frame of the image in the set Ω1 through a Laplace mask to obtain Conv, and then calculating the standard deviation of Conv and the grayscale values ​​of the pixels corresponding to each frame of the image, and the obtained value represents the clarity of each frame of the image; setting a clarity threshold, filtering out clear images from the set Ω1, and realizing secondary extraction of video key frames for the terminal block of the converter station.

[0031] In another aspect, there is provided a device comprising:

[0032] one or more processors;

[0033] a memory for storing one or more programs,

[0034] When the one or more programs are executed by the one or more processors, the one or more processors execute the method for secondary extraction of video key frames for a converter station terminal block.

[0035] On the other hand, a computer-readable storage medium storing a computer program is provided, and when the program is executed by a processor, the method for secondary extraction of video key frames for a terminal block of a converter station is implemented.

[0036] (III) Beneficial effects

[0037] The present invention provides a method and system for secondary extraction of video key frames for terminal blocks of converter stations, which solves the problems of a large number of pictures per frame, high similarity of pictures per frame, and uneven picture clarity in terminal block videos shot manually in current converter stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The present invention is a flow chart of a method for secondary extraction of video key frames for a terminal block of a converter station. DETAILED DESCRIPTION

[0039] The following will be combined with the accompanying drawings of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Example

[0041] like Figure 1 As shown, an embodiment of the present invention provides, on the one hand, a method for secondary extraction of video key frames for a terminal block of a converter station, comprising:

[0042] Conduct video capture of the actual terminal block of the converter station;

[0043] Extract features and grayscale each frame in the video;

[0044] Subtract the grayscale values ​​of the corresponding pixels of two adjacent frames of images, and take their absolute values ​​to obtain the difference value;

[0045] The difference value is compared with a set difference threshold, and if the difference value is higher than the set difference threshold, the frame is extracted to become a key frame of the video, and a preliminary picture set is established;

[0046] Perform convolution operation on the grayscale value of the pixel point corresponding to each image in the preliminary image set through the Laplacian mask to obtain Conv;

[0047] Calculate the standard deviation between the grayscale values ​​of Conv and the corresponding pixels of each image, where the standard deviation represents the clarity of each image;

[0048] Set the clarity threshold, define the image whose clarity is lower than the clarity threshold as blurry, and define the image whose clarity is higher than the clarity threshold as clear.

[0049] Preferably, the video capture of the actual terminal block of the converter station is achieved by a high-definition camera, and the high-definition camera is installed in the converter station room where it can clearly capture the actual picture of the terminal block.

[0050] Preferably, the feature extraction and grayscale processing of each frame of the video specifically includes:

[0051] Assume that the nth frame and the n-1th frame images in the video sequence are f n and f n-1 , the grayscale values ​​of the corresponding pixels of the two frames of images after feature extraction and grayscale processing are recorded as f n (x,y) and f n-1 (x,y).

[0052] Preferably, the grayscale values ​​of corresponding pixels of two adjacent frames of images are subtracted and their absolute values ​​are taken to obtain the difference value. The specific implementation formula is:

[0053] D n (x, y) = |F n (x, y)-F n-1 (x, y)|

[0054] Among them, D n Indicates the difference value.

[0055] Preferably, the step of comparing the difference value with a set difference threshold, and if the difference value is higher than the set difference threshold, extracting the frame to become a key frame of the video, and establishing a preliminary picture set, specifically includes:

[0056] The difference value is compared with the set difference threshold. The larger the difference value between two adjacent frames, the greater the difference between the two adjacent frames. A difference value threshold ζ between two adjacent frames is set. If the difference value between a frame and the adjacent previous frame is higher than the set threshold ζ, D is satisfied. n >ζ, then the frame is extracted to become the key frame of the video, the first video key frame extraction is realized, and the preliminary picture set Ω1 is established.

[0057] Preferably, performing a convolution operation on the grayscale value of a pixel point corresponding to each image in the preliminary picture set through a Laplace mask to obtain Conv specifically includes:

[0058] In the process of performing convolution operation on the grayscale value of the pixel point corresponding to each image in the preliminary image set through the Laplace mask, the grayscale value of the pixel point corresponding to each image in the set Ω1 is set to f(x, y), and the convolution operation is performed through the Laplace mask to obtain Conv, as shown in the following formula:

[0059]

[0060] in K should be selected so that each array element is an integer and the sum of all array elements is zero.

[0061] As another embodiment of the present invention, a video key frame secondary extraction system for a converter station terminal block is provided, the system comprising a multi-shot primary video key frame extraction unit considering frame difference correlation and a multi-shot secondary key frame extraction unit considering definition complementarity;

[0062] The multi-shot one-shot video key frame extraction unit considering frame difference correlation: extracting features and graying each frame in the video, then making a difference between the gray values ​​of two adjacent frames, comparing the difference value with a set difference threshold, realizing the first video key frame extraction, and establishing a preliminary picture set set Ω1;

[0063] The multi-lens secondary key frame extraction unit considering the complementarity of clarity includes performing a convolution operation on the grayscale values ​​of the pixels corresponding to each frame of the image in the set Ω1 through a Laplace mask to obtain Conv, and then calculating the standard deviation of Conv and the grayscale values ​​of the pixels corresponding to each frame of the image, and the obtained value represents the clarity of each frame of the image; setting a clarity threshold, filtering out clear images from the set Ω1, and realizing secondary extraction of video key frames for the terminal block of the converter station.

[0064] As another embodiment of the present invention, there is provided a device, comprising:

[0065] one or more processors;

[0066] a memory for storing one or more programs,

[0067] When the one or more programs are executed by the one or more processors, the one or more processors execute a video key frame secondary extraction method for a converter station terminal block in the above embodiment.

[0068] As another embodiment of the present invention, a computer-readable storage medium storing a computer program is provided. When the program is executed by a processor, a video key frame secondary extraction method for a converter station terminal block in the above embodiment is implemented.

[0069] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A video key frame secondary extraction method for a transformer substation terminal block, characterized in that: include: Conduct video capture of the actual terminal block of the converter station; Extract features and grayscale each frame in the video; Subtract the grayscale values ​​of the corresponding pixels of two adjacent frames of images, and take their absolute values ​​to obtain the difference value; The difference value is compared with a set difference threshold, and if the difference value is higher than the set difference threshold, the frame is extracted to become a key frame of the video, and a preliminary picture set is established; Perform convolution operation on the grayscale value of the pixel point corresponding to each image in the preliminary image set through the Laplacian mask to obtain Conv; Calculate the standard deviation between the grayscale values ​​of Conv and the corresponding pixels of each image, where the standard deviation represents the clarity of each image; Set the clarity threshold, define the image whose clarity is lower than the clarity threshold as blurry, and define the image whose clarity is higher than the clarity threshold as clear; The feature extraction and grayscale processing of each frame of the video specifically includes: Assume that the nth frame and the n-1th frame images in the video sequence are f n and f n-1 , the grayscale values ​​of the corresponding pixels of the two frames of images after feature extraction and grayscale processing are recorded as f n (x,y) and f n-1 (x,y); The grayscale values ​​of the corresponding pixels of two adjacent frames of images are subtracted, and the absolute value is taken to obtain the difference value. The specific implementation formula is: D n (x,y)=|f n (x,y)-f n-1 (x,y)| Among them, D n represents the difference value; The step of comparing the difference value with a set difference threshold value, and if the difference value is higher than the set difference threshold value, extracting the frame as a key frame of the video, and establishing a preliminary picture set, specifically includes: The difference value is compared with the set difference threshold. The larger the difference value between two adjacent frames, the greater the difference between the two adjacent frames. A difference value threshold ζ between two adjacent frames is set. If the difference value between a frame and the adjacent previous frame is higher than the set threshold ζ, D is satisfied. n >ζ, then the frame is extracted as the key frame of the video, the first video key frame extraction is realized, and the primary picture set Ω1 is established; The step of performing a convolution operation on the grayscale value of a pixel point corresponding to each image in the preliminary image set through a Laplace mask to obtain Conv specifically includes: In the process of performing convolution operation on the grayscale value of the pixel point corresponding to each image in the preliminary image set through the Laplace mask, the grayscale value of the pixel point corresponding to each image in the set Ω1 is set to f(x, y), and the convolution operation is performed through the Laplace mask to obtain Conv, as shown in the following formula: in K should be selected so that each array element is an integer and the sum of all array elements is zero.

2. According to claim 1, a method for secondary extraction of video key frames for converter station terminal blocks is characterized in that: The video acquisition of the actual terminal block of the converter station is achieved by a high-definition camera, and the high-definition camera is installed in the converter station room where it can clearly capture the actual picture of the terminal block.

3. A video key frame secondary extraction system for a converter station terminal row, applied to a video key frame secondary extraction method for a converter station terminal row according to any one of claims 1-2, characterized in that: The system comprises a multi-shot primary video key frame extraction unit considering frame difference correlation and a multi-shot secondary key frame extraction unit considering definition complementarity; The multi-shot one-shot video key frame extraction unit considering frame difference correlation: extracting features and graying each frame in the video, then making a difference between the gray values ​​of two adjacent frames, comparing the difference value with a set difference threshold, realizing the first video key frame extraction, and establishing a preliminary picture set set Ω1; The multi-shot secondary key frame extraction unit considering the complementarity of definition includes performing a convolution operation on the grayscale value of the pixel point corresponding to each frame of the image in the set Ω1 through a Laplace mask to obtain Conv, and then calculating the standard deviation of Conv and the grayscale value of the pixel point corresponding to each frame of the image, and the obtained value represents the definition of each frame of the image; The clarity threshold is set, and clear images are selected from the set Ω1 to realize the secondary extraction of video key frames for the terminal block of the transformer station.

4. A device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors execute the video key frame secondary extraction method for a converter station terminal block as described in any one of claims 1-2.

5. A computer-readable storage medium storing a computer program, characterized in that: When the program is executed by a processor, a video key frame secondary extraction method for a converter station terminal block as described in any one of claims 1 to 2 is implemented.

Images