Video processing method and device, equipment, product and medium

Abstract

The invention discloses a video processing method and device, equipment, a product and a medium, and relates to the technical field of video processing, and the method comprises the steps: extracting video images from a to-be-processed video according to a preset frame rate, and obtaining a to-be-processed image sequence; judging whether two continuous to-be-processed images in the to-be-processed image sequence belong to the same scene or not; under the condition that the two continuous images to be processed are judged to belong to the same scene, combining the two continuous images to be processed; and cutting the to-be-processed image sequence by taking a middle point of the two continuous to-be-processed images as a cutting point under the condition of judging that the two continuous to-be-processed images do not belong to the same scene. The method and the device are used for solving the problems of poor accuracy and poor effect during picture deduplication in the prior art, and the accuracy of picture deduplication is improved, so that the accuracy of video segmentation and video analysis based on the deduplicated picture is ensured.

Description

Technical Field

[0001] The present application relates to the field of video processing technology, and in particular to a video processing method, device, equipment, product and medium. Background Art

[0002] In the field of video analysis, in order to quickly obtain video content, the existing technology uses the method of extracting frames from the video to reduce the video. The specific implementation is to extract pictures from the video at a fixed frame rate, and analyze the video content by analyzing the extracted picture sequence. In the process of extracting pictures at a fixed frame rate, in order to prevent content loss, a relatively dense extraction interval is often selected. However, this method will result in a large number of repeated or similar picture scenes, and it is necessary to perform picture deduplication operations.

[0003] In the prior art, the image similarity technology used for image deduplication operations is based on image pixel distribution judgment, and does not take into account other features of the video. The similarity calculation accuracy is low, resulting in poor deduplication effect, which in turn leads to poor accuracy in video segmentation and video content analysis using deduplicated images. Summary of the invention

[0004] In response to the above-mentioned problems and technical needs, the applicant has proposed a video processing method, device, equipment, product and medium to solve the problems of poor accuracy and poor effect in image deduplication in the prior art, thereby improving the accuracy of image deduplication to ensure the accuracy of video segmentation and video analysis based on deduplicated images.

[0005] The present application provides a video processing method, the method comprising: Get the video to be processed; Extracting video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed; Based on the sequence of timestamps, determining whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene, wherein the scene is used to characterize whether the two consecutive images to be processed indicate a picture movement; When it is determined that two consecutive images to be processed belong to the same scene, merging the two consecutive images to be processed; When it is determined that two consecutive images to be processed do not belong to the same scene, the sequence of images to be processed is cropped using the middle point of the two consecutive images to be processed as a cutting point.

[0006] According to the video processing method provided in the embodiment of the present application, determining whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene includes: Randomly determine N positions from a first image to be processed of two consecutive images to be processed, wherein N is an integer greater than 1, and the N positions do not overlap; Determine a first pixel matrix of S*M with the pixel point at each position in the first image to be processed as the center, wherein S is an integer greater than 1, and M is an integer greater than 1; In the second image to be processed of the two consecutive images to be processed, taking the pixel point at each position as the center, determining a second pixel matrix of P*Q, wherein P is an integer greater than 1, Q is an integer greater than 1, P is greater than S, P is greater than M, Q is greater than S, and Q is greater than M; For each position, the similarity between the first pixel matrix and the second pixel matrix is ​​determined, and based on the obtained determination result, it is judged whether two consecutive images to be processed belong to the same scene.

[0007] According to the video processing method provided in the embodiment of the present application, for each position, determining the similarity between the first pixel matrix and the second pixel matrix, and judging whether two consecutive images to be processed belong to the same scene based on the obtained determination result, includes: For each position, determining the similarity between the first pixel matrix and the second pixel matrix to determine whether the second pixel matrix includes a similar region similar to the first pixel matrix; When it is determined that the number of positions including the position of the similar area is greater than or equal to a preset value, determining that two consecutive images to be processed belong to the same scene; When it is determined that the number of positions including the position of the similar area is less than the preset value, it is determined that the two consecutive images to be processed do not belong to the same scene.

[0008] According to the video processing method provided by the embodiment of the present application, determining the similarity between the first pixel matrix and the second pixel matrix to determine whether the second pixel matrix includes a similar area similar to the first pixel matrix includes: For each position, performing vectorization processing on the first pixel matrix to obtain a first vector, and performing vectorization processing on the second pixel matrix to obtain a second vector; Calculating the distance between the first vector and the second vector; In a case where it is determined that the distance is less than a preset distance, determining that the second pixel matrix includes a similar region similar to the first pixel matrix; When it is determined that the distance is greater than or equal to the preset distance, it is determined that the second pixel matrix does not include a similar area similar to the first pixel matrix.

[0009] According to the video processing method provided by the embodiment of the present application, determining the similarity between the first pixel matrix and the second pixel matrix to determine whether the second pixel matrix includes a similar area similar to the first pixel matrix includes: For each pixel point in the second pixel matrix, determine an S*M candidate pixel matrix; Determining a similarity value between the candidate pixel matrix and the first pixel matrix; When it is determined that there is at least one candidate pixel matrix whose similarity value with the first pixel matrix is ​​greater than a preset similarity value, determining that the second pixel matrix includes a similar region similar to the first pixel matrix; When it is determined that there is no similarity value between the candidate pixel matrix and the first pixel matrix greater than the preset similarity value, it is determined that the second pixel matrix does not include a similar area similar to the first pixel matrix.

[0010] According to the video processing method provided in the embodiment of the present application, the method further includes: Based on the merged image to be processed and the multiple image subsequences obtained after cropping, the video content of the video to be processed is determined.

[0011] The embodiment of the present application also provides a video processing device, including: An acquisition module is used to acquire the video to be processed; An extraction module, used to extract video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed; A judgment module, used for judging whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene based on the order of the timestamps, wherein the scene is used to characterize whether the two consecutive images to be processed indicate a picture movement; A merging module, used for merging two consecutive images to be processed when it is determined that the two consecutive images to be processed belong to the same scene; The cropping module is used to crop the sequence of images to be processed using the middle point of the two consecutive images to be processed as a cutting point when it is determined that the two consecutive images to be processed do not belong to the same scene.

[0012] The embodiment of the present application further provides an electronic device, the electronic device comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The processor may call the logic instructions in the memory to execute the steps of the video processing method described in any of the above embodiments.

[0013] An embodiment of the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the steps of the video processing method described in any of the above embodiments.

[0014] An embodiment of the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the video processing method described in any of the above embodiments are implemented.

[0015] The video processing method, device, equipment, product and medium provided in the embodiments of the present application extract video images from the video to be processed at a preset frame rate to obtain a sequence of images to be processed; based on the order of timestamps, determine whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene, wherein the scene is used to characterize whether the two consecutive images to be processed indicate screen movement; when it is determined that the two consecutive images to be processed belong to the same scene, merge the two consecutive images to be processed; when it is determined that the two consecutive images to be processed do not belong to the same scene, crop the sequence of images to be processed with the middle point of the two consecutive images to be processed as the cutting point. It can be seen that the present application fully considers the characteristics of screen movement in the video, determines whether the two images to be processed belong to screen movement, and determines whether to merge the images or segment the images based on the determined results, which not only improves the accuracy of image deduplication but also improves the accuracy of video segmentation, and effectively solves the problems of poor accuracy and poor effect in image deduplication in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is one of the flow charts of the video processing method provided in the embodiment of the present application; Figure 2 This is the second flow chart of the video processing method provided in the embodiment of the present application; Figure 3 is a structural diagram of a video processing device provided in an embodiment of the present application; Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The embodiment of the present application provides a video processing method. The method can be applied to a smart terminal or a server. Some other descriptions in the embodiment of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application. They will not be described one by one. The specific implementation of the method is as follows: Figure 1 As shown: Step 101, obtaining a video to be processed.

[0020] Step 102: extracting video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed.

[0021] Step 103 : judging whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene based on the sequence of timestamps.

[0022] The scene is used to indicate whether two consecutive images to be processed indicate image movement.

[0023] Step 104: when it is determined that the two consecutive images to be processed belong to the same scene, the two consecutive images to be processed are merged.

[0024] Step 105 : when it is determined that the two consecutive images to be processed do not belong to the same scene, the image sequence to be processed is cropped using the middle point of the two consecutive images to be processed as a cutting point.

[0025] The video processing method provided in the embodiment of the present application extracts video images from the video to be processed at a preset frame rate to obtain a sequence of images to be processed; based on the order of timestamps, determines whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene, wherein the scene is used to characterize whether the two consecutive images to be processed indicate screen movement; when it is determined that the two consecutive images to be processed belong to the same scene, merges the two consecutive images to be processed; when it is determined that the two consecutive images to be processed do not belong to the same scene, crops the sequence of images to be processed with the middle point of the two consecutive images to be processed as the cutting point. It can be seen that the present application fully considers the characteristics of screen movement in the video, determines whether the two images to be processed belong to screen movement, and determines whether to merge the images or segment the images based on the determined results, which not only improves the accuracy of image deduplication but also improves the accuracy of video segmentation, and effectively solves the problems of poor accuracy and poor effect in image deduplication in the prior art.

[0026] In a specific embodiment, the specific implementation of determining whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene includes: Randomly determine N positions in a first image to be processed of two consecutive images to be processed; determine a first pixel matrix of S*M with the pixel point at each position as the center in the first image to be processed; determine a second pixel matrix of P*Q with the pixel point at each position as the center in the second image to be processed of the two consecutive images to be processed; for each position, determine the similarity between the first pixel matrix and the second pixel matrix, and based on the obtained determination result, determine whether the two consecutive images to be processed belong to the same scene.

[0027] Wherein, N is an integer greater than 1, and the N positions do not overlap.

[0028] Wherein, S is an integer greater than 1, and M is an integer greater than 1.

[0029] Among them, P is an integer greater than 1, Q is an integer greater than 1, P is greater than S, P is greater than M, Q is greater than S, and Q is greater than M.

[0030] Specifically, the two consecutive images to be processed are the first and second images, the second and third images, the third and fourth images, ..., and so on, in the sequence of images to be processed, until the last image.

[0031] In a specific embodiment, for each position, determining the similarity between the first pixel matrix and the second pixel matrix, and judging whether two consecutive images to be processed belong to the same scene based on the obtained determination result, specifically includes: For each position, determine the similarity between the first pixel matrix and the second pixel matrix to determine whether the second pixel matrix includes a similar area similar to the first pixel matrix; when it is determined that the number of positions including the similar area is greater than or equal to a preset value, determine that the two consecutive images to be processed belong to the same scene; when it is determined that the number of positions including the similar area is less than a preset value, determine that the two consecutive images to be processed do not belong to the same scene.

[0032] In a specific embodiment, determining the similarity between the first pixel matrix and the second pixel matrix and determining whether the second pixel matrix includes a similar region similar to the first pixel matrix includes: For each position, the first pixel matrix is ​​vectorized to obtain a first vector, and the second pixel matrix is ​​vectorized to obtain a second vector; the distance between the first vector and the second vector is calculated; when it is determined that the distance is less than a preset distance, it is determined that the second pixel matrix includes a similar area similar to the first pixel matrix; when it is determined that the distance is greater than or equal to the preset distance, it is determined that the second pixel matrix does not include a similar area similar to the first pixel matrix.

[0033] In a specific embodiment, determining the similarity between the first pixel matrix and the second pixel matrix and determining whether the second pixel matrix includes a similar region similar to the first pixel matrix includes: For each pixel point in the second pixel matrix, determine an S*M candidate pixel matrix; determine a similarity value between the candidate pixel matrix and the first pixel matrix; when it is determined that there is at least one candidate pixel matrix whose similarity value with the first pixel matrix is ​​greater than a preset similarity value, determine that the second pixel matrix includes a similar area similar to the first pixel matrix; when it is determined that there is no candidate pixel matrix whose similarity value with the first pixel matrix is ​​greater than the preset similarity value, determine that the second pixel matrix does not include a similar area similar to the first pixel matrix.

[0034] The calculation of the similarity value in this embodiment can also be obtained by calculating the vector distance.

[0035] In a specific embodiment, after the image sequence to be processed is merged and cropped, the video content of the video to be processed is determined based on the merged image to be processed and the multiple image subsequences obtained after cropping.

[0036] The specific implementation of the present application is described below through a specific embodiment (the description of the quantity involved in this embodiment is only an example and is not intended to limit the scope of protection of the present application). For details, please refer to Figure 2 : Step 201: extracting images of a video to be processed at a preset frame rate.

[0037] For example, extract every 10 frames.

[0038] Step 202, sorting the extracted pictures in extraction order, arranging them from front to back according to video time, to obtain a sequence of images to be processed.

[0039] Step 203, select two consecutive pictures in sequence, randomly select 5 positions from the previous picture, and ensure that these 5 positions are not within 20% of the edge of the picture.

[0040] Step 204, taking the pixel points at the above five positions as the center, select a 3*3 pixel matrix respectively, for a total of five 3*3 matrices, each matrix corresponding to one position.

[0041] Step 205, in the second picture, with the above 5 positions as the center and within a range of 50 pixels, search for a 3*3 matrix with a similar pixel distribution to the 3*3 matrix at the corresponding positions.

[0042] For example, each position coordinate (x, y) is centered in a square area with a side length of 100, centered at four points: (x-50, y-50), (x-50, y+50), (x+50, y-50), and (x+50, y+50).

[0043] Step 206, the distribution similarity is calculated by tiling the 3*3 matrix into a vector of length 9, calculating the Euclidean distance between two vectors, tiling the pixel gradient in the matrix into a vector to calculate the Euclidean distance, and summing the two distances to obtain a similarity evaluation.

[0044] Among them, the smaller the distance and the more similar they are.

[0045] Step 207, the minimum distance of the five positions obtained in step 205 and the position of the minimum distance. When more than three minimum distances are less than the preset threshold, and the change directions and distances of the matrix centers found are close, the two pictures are considered to belong to the same scene, and only the lens is moved.

[0046] Step 208, returning to step 203, until the relationship between all pictures is determined, the video is cut into multiple segments between two pictures determined as lens switching.

[0047] Specifically, since the movement of the picture is a relatively continuous and slow change, the scene is relatively similar during the whole movement process. For example, when shooting a mountain range by moving the camera, although the shape of the mountain is different, the meaning represented is similar and can be merged. The present application can effectively distinguish whether the video screen is a shot switch or a picture movement, realize the accurate merging and cutting of pictures, so that the video content of the original video can be obtained more accurately using the final video.

[0048] The application embodiment also provides a video processing device. The specific implementation of the device can refer to the description of the video processing method based on approximate personalized delivery, and the repeated parts will not be repeated. Figure 3 As shown, the device comprises: An acquisition module 301 is used to acquire a video to be processed; An extraction module 302 is used to extract video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed; A judgment module 303 is used to judge whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene based on the order of the timestamps, wherein the scene is used to indicate whether the two consecutive images to be processed indicate a picture movement; A merging module 304 is used to merge the two consecutive images to be processed when it is determined that the two consecutive images to be processed belong to the same scene; The cropping module 305 is used to crop the sequence of images to be processed using the middle point of the two consecutive images to be processed as a cutting point when it is determined that the two consecutive images to be processed do not belong to the same scene.

[0049] In a specific embodiment, the judgment module 303 is used to randomly determine N positions from the first image to be processed of two consecutive images to be processed, wherein N is an integer greater than 1 and the N positions do not overlap; in the first image to be processed, with the pixel point at each position as the center, determine a first pixel matrix of S*M, wherein S is an integer greater than 1, and M is an integer greater than 1; in the second image to be processed of the two consecutive images to be processed, with the pixel point at each position as the center, determine a second pixel matrix of P*Q, wherein P is an integer greater than 1, Q is an integer greater than 1, P is greater than S, P is greater than M, Q is greater than S, and Q is greater than M; for each position, determine the similarity between the first pixel matrix and the second pixel matrix, and based on the obtained determination result, determine whether the two consecutive images to be processed belong to the same scene.

[0050] In a specific embodiment, the judgment module 303 is used to determine the similarity between the first pixel matrix and the second pixel matrix for each position to determine whether the second pixel matrix includes a similar area similar to the first pixel matrix; when it is determined that the number of positions including the similar area is greater than or equal to a preset value, it is determined that the two consecutive images to be processed belong to the same scene; when it is determined that the number of positions including the similar area is less than a preset value, it is determined that the two consecutive images to be processed do not belong to the same scene.

[0051] In a specific embodiment, the judgment module 303 is used to perform vectorization processing on the first pixel matrix for each position to obtain a first vector, and to perform vectorization processing on the second pixel matrix to obtain a second vector; calculate the distance between the first vector and the second vector; when it is determined that the distance is less than a preset distance, determine that the second pixel matrix includes a similar area similar to the first pixel matrix; when it is determined that the distance is greater than or equal to the preset distance, determine that the second pixel matrix does not include a similar area similar to the first pixel matrix.

[0052] In a specific embodiment, the judgment module 303 is used to determine an S*M candidate pixel matrix for each pixel point in the second pixel matrix; determine the similarity value between the candidate pixel matrix and the first pixel matrix; when it is determined that there is at least one candidate pixel matrix whose similarity value with the first pixel matrix is ​​greater than a preset similarity value, determine that the second pixel matrix includes a similar area similar to the first pixel matrix; when it is determined that there is no candidate pixel matrix whose similarity value with the first pixel matrix is ​​greater than the preset similarity value, determine that the second pixel matrix does not include a similar area similar to the first pixel matrix.

[0053] In a specific embodiment, the device further includes a determination module, which is used to determine the video content of the video to be processed based on the merged image to be processed and the multiple image subsequences obtained after cropping.

[0054] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 401, a communication interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communication interface 402 and the memory 403 communicate with each other through the communication bus 404. The processor 401 may call the logic instructions in the memory 403 to execute the video processing method, which includes: obtaining a video to be processed; extracting video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed; judging whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene based on the order of timestamps, wherein the scene is used to characterize whether two consecutive images to be processed indicate that the screen moves; if it is determined that the two consecutive images to be processed belong to the same scene, merging the two consecutive images to be processed; if it is determined that the two consecutive images to be processed do not belong to the same scene, cropping the sequence of images to be processed with the middle point of the two consecutive images to be processed as the cutting point.

[0055] In addition, the logic instructions in the above-mentioned memory 403 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0056] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the video processing method provided by the above-mentioned methods, and the method includes: obtaining a video to be processed; extracting video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed; based on the sequence of timestamps, determining whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene, wherein the scene is used to characterize whether two consecutive images to be processed indicate movement of the screen; when it is determined that two consecutive images to be processed belong to the same scene, merging the two consecutive images to be processed; when it is determined that two consecutive images to be processed do not belong to the same scene, cropping the sequence of images to be processed with the middle point of the two consecutive images to be processed as the cutting point.

[0057] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the video processing method provided by the above-mentioned embodiments, the method comprising: obtaining a video to be processed; extracting video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed; based on the order of timestamps, determining whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene, wherein the scene is used to characterize whether two consecutive images to be processed indicate movement of the screen; when it is determined that two consecutive images to be processed belong to the same scene, merging the two consecutive images to be processed; when it is determined that two consecutive images to be processed do not belong to the same scene, cropping the sequence of images to be processed with the midpoint of the two consecutive images to be processed as the cutting point.

[0058] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0059] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0060] Finally, it should be noted that the above is only the preferred implementation of the present application, and the present application is not limited to the above embodiments. It is understood that other improvements and changes directly derived or associated by those skilled in the art without departing from the spirit and concept of the present application should be considered to be included in the scope of protection of the present application.

Claims

1. A video processing method, characterized in that: The method comprises: Get the video to be processed; Extracting video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed; Based on the sequence of timestamps, determining whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene, wherein the scene is used to characterize whether the two consecutive images to be processed indicate a picture movement; When it is determined that two consecutive images to be processed belong to the same scene, merging the two consecutive images to be processed; When it is determined that two consecutive images to be processed do not belong to the same scene, the sequence of images to be processed is cropped using the middle point of the two consecutive images to be processed as a cutting point.

2. The video processing method according to claim 1, characterized in that: Determining whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene includes: Randomly determine N positions from a first image to be processed of two consecutive images to be processed, wherein N is an integer greater than 1, and the N positions do not overlap; Determine a first pixel matrix of S*M with the pixel point at each position in the first image to be processed as the center, wherein S is an integer greater than 1, and M is an integer greater than 1; In the second image to be processed of the two consecutive images to be processed, taking the pixel point at each position as the center, determining a second pixel matrix of P*Q, wherein P is an integer greater than 1, Q is an integer greater than 1, P is greater than S, P is greater than M, Q is greater than S, and Q is greater than M; For each position, the similarity between the first pixel matrix and the second pixel matrix is ​​determined, and based on the obtained determination result, it is judged whether two consecutive images to be processed belong to the same scene.

3. The video processing method according to claim 2, characterized in that: For each position, determining the similarity between the first pixel matrix and the second pixel matrix, and judging whether two consecutive images to be processed belong to the same scene based on the obtained determination result, including: For each position, determining the similarity between the first pixel matrix and the second pixel matrix to determine whether the second pixel matrix includes a similar region similar to the first pixel matrix; When it is determined that the number of positions including the position of the similar area is greater than or equal to a preset value, determining that two consecutive images to be processed belong to the same scene; When it is determined that the number of positions including the position of the similar area is less than the preset value, it is determined that the two consecutive images to be processed do not belong to the same scene.

4. The video processing method according to claim 3, characterized in that: Determining the similarity between the first pixel matrix and the second pixel matrix to determine whether the second pixel matrix includes a similar area similar to the first pixel matrix includes: For each position, performing vectorization processing on the first pixel matrix to obtain a first vector, and performing vectorization processing on the second pixel matrix to obtain a second vector; Calculating the distance between the first vector and the second vector; In a case where it is determined that the distance is less than a preset distance, determining that the second pixel matrix includes a similar region similar to the first pixel matrix; When it is determined that the distance is greater than or equal to the preset distance, it is determined that the second pixel matrix does not include a similar area similar to the first pixel matrix.

5. The video processing method according to claim 3, characterized in that: Determining the similarity between the first pixel matrix and the second pixel matrix to determine whether the second pixel matrix includes a similar area similar to the first pixel matrix includes: For each pixel point in the second pixel matrix, determine an S*M candidate pixel matrix; Determining a similarity value between the candidate pixel matrix and the first pixel matrix; When it is determined that there is at least one candidate pixel matrix whose similarity value with the first pixel matrix is ​​greater than a preset similarity value, determining that the second pixel matrix includes a similar region similar to the first pixel matrix; When it is determined that there is no similarity value between the candidate pixel matrix and the first pixel matrix greater than the preset similarity value, it is determined that the second pixel matrix does not include a similar area similar to the first pixel matrix.

6. The video processing method according to any one of claims 1 to 5, characterized in that: The method further comprises: Based on the merged image to be processed and the multiple image subsequences obtained after cropping, the video content of the video to be processed is determined.

7. A video processing device, characterized in that: include: An acquisition module is used to acquire the video to be processed; An extraction module, used to extract video images from the video to be processed according to a preset frame rate to obtain a sequence of images to be processed; A judgment module, used for judging whether two consecutive images to be processed in the sequence of images to be processed belong to the same scene based on the order of the timestamps, wherein the scene is used to characterize whether the two consecutive images to be processed indicate a picture movement; A merging module, used for merging two consecutive images to be processed when it is determined that the two consecutive images to be processed belong to the same scene; The cropping module is used to crop the sequence of images to be processed using the middle point of the two consecutive images to be processed as a cutting point when it is determined that the two consecutive images to be processed do not belong to the same scene.

8. An electronic device, characterized in that: The electronic device comprises: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The processor can call the logic instructions in the memory to execute the steps of the video processing method described in any one of claims 1-6.

9. A computer program product, characterized in that The computer program product comprises a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions. When the program instructions are executed by a computer, the computer can execute the steps of the video processing method according to any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the video processing method according to any one of claims 1 to 6 are implemented.

Images