CN112653885B - Video repetition degree acquisition method, electronic equipment and storage medium - Google Patents

Abstract

The present disclosure discloses a video repetition acquisition method, an electronic device and a storage medium. The method may include: extracting M frames of video images from the first video, where M is a positive integer greater than one and less than or equal to the number included in the first video. The total number of frames, for each frame of extracted video image, the corresponding reverse sequence image is obtained respectively; N frames of video images are extracted from the second video, N is a positive integer greater than one, and is less than or equal to the second video included in The total number of frames, for each frame of the extracted video image, the similarity between the video image and each reverse sequence image is obtained respectively; based on the obtained similarity, the degree of repetition between the first video and the second video is determined . Applying the solution described in this disclosure can save computing resources and time costs, and improve processing efficiency.

Description

Video repetition acquisition method, electronic device and storage medium

Technical field

The present disclosure relates to video recognition technology, and in particular to video repetition acquisition methods, electronic devices and storage media.

Background technique

In practical applications, in many scenarios it is necessary to obtain the degree of repetition between one video and another video. Existing video repeatability acquisition methods are often complex, requiring various complex calculations, which consume more computing resources and take a long time.

Contents of the invention

The present disclosure provides a video repeatability acquisition method, electronic device, and storage medium.

A method for obtaining video repetition, including:

Extract M frames of video images from the first video, where M is a positive integer greater than one and less than or equal to the total number of frames included in the first video. For each frame of video image extracted, the corresponding reverse sequence is obtained. image;

Extract N frames of video images from the second video, where N is a positive integer greater than one and less than or equal to the total number of frames included in the second video. For each frame of the extracted video image, obtain the video image respectively. Similarity with each reverse sequence image;

The degree of duplication between the first video and the second video is determined based on the obtained similarity.

An electronic device including:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method as described above.

A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method described above.

A computer program product includes a computer program that implements the above-described method when executed by a processor.

One embodiment in the above disclosure has the following advantages or beneficial effects: video image extraction can be performed on the first video and the second video respectively, and the reverse sequence image of each video image extracted from the first video can be obtained, and the reverse sequence image of each video image extracted from the first video can be obtained. The similarity between each video image extracted from the second video and each reverse sequence image can then be used to determine the degree of repetition between the two videos based on the obtained similarity. The whole process is fast and easy to implement, saving computing resources. and time costs, and improve processing efficiency, etc.

It should be understood that what is described in this section is not intended to identify key or important features of the embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of the drawings

The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. in:

Figure 1 is a flow chart of an embodiment of a video repetition acquisition method according to the present disclosure;

Figure 2 is a schematic diagram of the optimal continuous path according to the present disclosure;

Figure 3 is a schematic diagram of the overall implementation process of the video repetition acquisition method according to the present disclosure;

4 illustrates a schematic block diagram of an example electronic device 400 that may be used to implement embodiments of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the present disclosure are included to facilitate understanding and should be considered to be exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

In addition, it should be understood that the term "and/or" in this article is only an association relationship describing related objects, indicating that three relationships can exist. For example, A and/or B can mean: A exists alone, and A exists simultaneously and B, there are three cases of B alone. In addition, the character "/" in this article generally indicates that the related objects are an "or" relationship.

Figure 1 is a flow chart of an embodiment of the video repetition obtaining method according to the present disclosure. As shown in Figure 1, it includes the following specific implementation methods.

In step 101, M frames of video images are extracted from the first video, where M is a positive integer greater than one and less than or equal to the total number of frames included in the first video. For each frame of the extracted video image, the corresponding reverse sequence image.

In step 102, N frames of video images are extracted from the second video, where N is a positive integer greater than one and less than or equal to the total number of frames included in the second video. For each frame of the extracted video image, the The similarity between the video image and each reverse sequence image.

In step 103, the degree of duplication between the first video and the second video is determined based on the obtained similarity.

It can be seen that in the solution described in the above method embodiment, video image extraction can be performed on the first video and the second video respectively, and the reverse sequence image of each video image extracted from the first video can be obtained, as well as the reverse sequence image of each video image extracted from the first video can be obtained. The similarity between each video image extracted from the two videos and each reverse sequence image can then be used to determine the degree of repetition between the two videos based on the obtained similarity. The whole process is fast and easy to implement, saving computing resources and time cost, and improve processing efficiency, etc.

In the solution described in the present disclosure, there is no limit on how to extract video images from the first video. For example, it may include but is not limited to: using each frame in the first video as an extracted video image, or, every L frame interval, Then a frame of video image is extracted from the first video, L is a positive integer, and the specific value can be determined according to actual needs.

Assume that the first video contains a total of 100 frames, then these 100 frames can be used as extracted video images, or, assuming that the value of L is 1, then one frame can be extracted from the first video every 1 frame. Video images, thereby extracting a total of 50 frames of video images, etc.

Similarly, the method of extracting video images from the second video may include but is not limited to: using each frame in the second video as an extracted video image, or extracting video images from the second video every L frames. A frame of video image.

Generally speaking, the way to extract video images from the first video is the same as the way to extract the video images from the second video. For example, each frame in the first video can be used as an extracted video image, and each frame in the second video can be used as an extracted video image, or, every frame is separated from the first video. Extract one frame of video image, and, every other frame, extract one frame of video image from the second video.

For the method of treating each frame in the video as an extracted video image, more video images can be extracted, thereby improving the accuracy of subsequent processing results, etc. For the method of interval extraction, the number of extracted video images will be reduced, and accordingly, the workload of subsequent processing can be reduced, thereby improving processing efficiency, etc. The specific method used can be determined according to actual needs.

As described in step 101, after M frames of video images are extracted from the first video, the corresponding reverse sequence image can be obtained for each frame of the extracted video image. Specifically, for each frame of the extracted video image, the value of each pixel in the video image can be inverted, thereby obtaining a reverse sequence image corresponding to the video image.

Assume that 50 frames of video images are extracted from the first video, respectively numbered video image 1 - video image 50, then the reverse sequence image corresponding to video image 1, the reverse sequence image corresponding to video image 2, and video image 3 can be obtained respectively. The corresponding reverse-sequence images, ..., and the corresponding reverse-sequence images of the video image 50, etc., so that a total of 50 reverse-sequence images can be obtained.

The extracted video image is usually a bitmap (BMP, Bitmap) image, and the extracted video image is stored in the memory in BMP format. For image storage, 256-bit original images are usually used, and one byte represents the value of one pixel.

Correspondingly, for each frame of video image extracted from the first video, the Byte value of each pixel in the video image can be inverted, thereby obtaining a reverse sequence image corresponding to the video image.

In practical applications, after each frame of video image is extracted from the first video, the reverse sequence image corresponding to the video image can be obtained, or after all M frames of video images are extracted, each frame of video image can be extracted. For video images, the corresponding reverse sequence images are obtained respectively. The specific method used can be determined according to actual needs.

As described in step 102, N frames of video images can be extracted from the second video, and for each frame of the extracted video image, the similarity between the video image and each reverse sequence image can be obtained respectively.

Assume that 50 frames of video images are extracted from the second video, numbered respectively as video image 101-video image 150, and assuming that there are 50 reverse sequence images in total, then for video image 101, video image 101 and each reverse sequence image can be obtained respectively. The similarity between sequence images can be obtained, so that 50 similarities can be obtained. For the video image 102, the similarity between the video image 102 and each reverse sequence image can be obtained respectively, and 50 similarities can be obtained, and so on.

In practical applications, after each frame of video image is extracted from the second video, the similarity between the video image and each reverse sequence image can be obtained, or all N frames of video images can be extracted. Finally, for each video image, the similarity with each reverse sequence image is obtained. The specific method used can be determined according to actual needs.

Specifically, for each frame of video image extracted from the second video, the following processing can be performed: perform a coupling operation on the video image and each reverse sequence image to obtain M coupling result images, the video image, the reverse sequence image and The sizes of the coupling result images are the same. For each coupling result image, the number of pixels with non-zero values in the coupling result image can be counted separately, and the statistical results are used as the inverse sequence corresponding to the video image and the coupling result image. The similarity between images, where for any pixel in the coupling result image, if the value of the corresponding pixel of the pixel in the video image is the same as the value of the corresponding pixel of the pixel in the reverse sequence image If the values are the same, the value of the pixel can be set to zero. Otherwise, if it is not zero, the corresponding pixel is the pixel at the same position.

The extracted video image may be of any size. In the solution of the present disclosure, the extracted video image can also be preprocessed first, that is, adjusted to a predetermined size. After adjustment, whether it is from the first video The size of the extracted video image, the video image extracted from the second video, the reverse sequence image or the coupling result image are all the same, that is, they are all the predetermined size. The specific value of the predetermined size can be determined according to actual needs.

For each frame of video image extracted from the second video, it can be coupled with M reverse sequence images respectively, thereby obtaining M coupling result images. For example, for each reverse-sequence image, the corresponding pixels in the video image and the reverse-sequence image can be separately ANDed by Byte to obtain the coupling result image corresponding to the reverse-sequence image, and the coupling result image can be counted The number of pixels with non-zero values in , and the statistical result is used as the similarity between the video image and the reverse sequence image.

When a certain video image is coupled to a certain reverse sequence image, that is, when the corresponding pixel points in the video image and the reverse sequence image are operated by Byte, the coordinate position in the obtained coupling result image is (10, Taking the pixel point of 10) as an example, assuming that the value of the pixel point at the coordinate position (10,10) in the video image is the same as the value of the pixel point at the coordinate position (10,10) in the reverse sequence image, then Then the pixel point with the coordinate position (10,10) in the coupling result image can be set to 0, otherwise, it can be set to 1, and the number of pixel points with a value other than 0 in the coupling result image can be counted, The statistical result is used as the similarity between the video image and the reverse sequence image.

In this way, for each frame of video image extracted from the second video, the following result set can be obtained:

A1 A2 A3…

B1 19 5 10…

Among them, B1 represents a frame of video image extracted from the second video, A1, A2 and A3 respectively represent each frame of video image extracted from the first video, 19 represents the inverse of the corresponding video image B1 and video image A1. The similarity between sequence images, 5 represents the similarity between the reverse sequence images corresponding to video image B1 and video image A2, and so on.

According to the result set corresponding to each video image extracted from the second video, a result matrix with N rows and M columns can be generated.

The i-th row in the result matrix corresponds to the i-th frame of video image extracted from the second video, 1≤i≤N, and the i-th frame of video image represents the sequence of the i-th video image extracted from the second video in order of extraction time. The extracted N frames of video images are sorted to the i-th video image. The j-th column in the result matrix corresponds to the j-th frame of video image extracted from the first video, 1≤j≤M, j-th frame The video image represents the j-th video image after sorting the M frames of video images extracted from the first video in the order of extraction time. Each element in the result matrix represents the video image corresponding to the row. The similarity between the reverse sequence images of the video image corresponding to the column.

The resulting matrix can look like this:

Among them, B1, B2 and B3 respectively represent each frame of video image extracted from the second video, A1, A2 and A3 respectively represent each frame of video image extracted from the first video. In addition, A1 is the first The video image extracted from the first video is followed by A2, and so on. Similarly, B1 is the video image extracted from the second video first, followed by B2, and so on.

The degree of duplication between the first video and the second video can be determined according to the result matrix. Specifically, under the principle that the path length is as long as possible and the sum of each element on the path is as small as possible, the two factors of path length and the sum of each element on the path can be balanced, and an optimal path can be determined from the result matrix. Optimal continuous path, each element on the optimal continuous path is in a different row, and each element is in a different column. According to the path length of the optimal continuous path, the sum of each element on the optimal continuous path, M And the number of pixels included in the video image determines the degree of repetition between the first video and the second video.

When determining the optimal continuous path from the result matrix, we hope that the path length is as long as possible, and the sum of the elements on the path is as small as possible. The smaller the sum, the higher the similarity, and the longer the path length, the greater the number of similar frames. However, the path length and the sum of the elements on the path are two factors that influence each other. For example, an increase in the path length may cause the sum of the elements on the path to also increase, so it is necessary to balance these two factors. Factors, based on the temporal continuity of frames, the optimal result of comprehensive evaluation is selected, that is, the optimal continuous path. Or it can also be understood that for the factor of path length, the larger the value, the higher the score. For the factor of the sum of the elements on the path, the smaller the value, the higher the score. The higher the score of one of the factors, the higher the score. At the same time, the score of another factor may be reduced, so it is necessary to balance the two factors and select the optimal continuous path with the highest comprehensive score.

As shown in Figure 2, Figure 2 is a schematic diagram of the optimal continuous path according to the present disclosure. There is no restriction on how to determine the optimal continuous path from the result matrix. For example, various existing mature algorithms can be used.

The degree of repetition between the first video and the second video can be determined based on the path length of the optimal continuous path, the sum of the elements on the optimal continuous path, M, and the number of pixels included in the video image. .

For example, you can calculate the quotient of the sum of each element on the optimal continuous path and the number of pixels included in the video image, and calculate the quotient of the path length of the optimal continuous path and M, and then calculate the quotient of the two quotients. Product, take the product as the degree of repetition between the first video and the second video.

That is: Result=(P/W)*(MaxLength/M); (1)

Among them, P represents the sum of the elements on the optimal continuous path, W represents the number of pixels included in the video image, MaxLength represents the path length of the optimal continuous path, and M represents the extraction from the first video. The number of video images, Result represents the degree of repetition.

Based on the above introduction, it can be seen that Figure 3 is a schematic diagram of the overall implementation process of the video repetition acquisition method according to the present disclosure. For specific implementation, please refer to the aforementioned relevant descriptions and will not be described again.

In addition, it should be noted that the foregoing method embodiments are expressed as a series of action combinations for simple description, but those skilled in the art should know that the present disclosure is not limited by the described action sequence, because Certain steps may be performed in other orders or simultaneously in accordance with the present disclosure. Secondly, those skilled in the art should also know that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily necessary for the present disclosure.

In short, using the solution described in this disclosure, the distance between the first video and the second video can be determined through video image extraction, reverse sequence image generation, coupling operation, result matrix generation, optimal continuous path determination, and repetition calculation. The whole process is fast and easy to implement, saves computing resources and time costs, and improves processing efficiency. It is suitable for use in high-concurrency projects. In addition, it can be applied to videos of any type, duration, etc., and has wide applicability.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

4 illustrates a schematic block diagram of an example electronic device 400 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to refer to various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are examples only and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 4 , the device 400 includes a computing unit 401 that can execute according to a computer program stored in a read-only memory (ROM) 402 or loaded from a storage unit 408 into a random access memory (RAM) 403 Various appropriate actions and treatments. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. Computing unit 401, ROM 402 and RAM 403 are connected to each other via bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

Multiple components in the device 400 are connected to the I/O interface 405, including: input unit 406, such as a keyboard, mouse, etc.; output unit 407, such as various types of displays, speakers, etc.; storage unit 408, such as a magnetic disk, optical disk, etc. ; and communication unit 409, such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information/data with other devices through computer networks such as the Internet and/or various telecommunications networks.

Computing unit 401 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any appropriate processor, controller, microcontroller, etc. Computing unit 401 performs various methods and processes described above, such as the methods described in this disclosure. For example, in some embodiments, the methods described in the present disclosure may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 400 via ROM 402 and/or communication unit 409. When a computer program is loaded into RAM 403 and executed by computing unit 401, one or more steps of the method described in this disclosure may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the methods described in this disclosure in any other suitable manner (eg, by means of firmware).

Various implementations of the systems and techniques described above may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip implemented in a system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or a combination thereof. These various embodiments may include implementation in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor The processor, which may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device. An output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions specified in the flowcharts and/or block diagrams/ The operation is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be provided in any form, including Acoustic input, voice input or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., A user's computer having a graphical user interface or web browser through which the user can interact with implementations of the systems and technologies described herein), or including such backend components, middleware components, or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communications network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

Computer systems may include clients and servers. Clients and servers are generally remote from each other and typically interact over a communications network. The relationship of client and server is created by computer programs running on corresponding computers and having a client-server relationship with each other.

It should be understood that various forms of the process shown above may be used, with steps reordered, added or deleted. For example, each step described in the present disclosure can be executed in parallel, sequentially, or in a different order. As long as the desired results of the technical solution disclosed in the present disclosure can be achieved, there is no limitation here.

The above-mentioned specific embodiments do not constitute a limitation on the scope of the present disclosure. It will be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions are possible depending on design requirements and other factors. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this disclosure shall be included in the protection scope of this disclosure.

Claims (6)

1. A video repetition rate obtaining method, comprising:

extracting M frames of video images from a first video, wherein M is a positive integer greater than one and less than or equal to the total frame number included in the first video, and respectively acquiring corresponding reverse sequence images for each extracted frame of video image, including: for each extracted video image, respectively inverting the values of all pixel points in the video image to obtain an inverted sequence image corresponding to the video image;

extracting N frames of video images from a second video, where N is a positive integer greater than one and less than or equal to a total frame number included in the second video, and for each extracted frame of video image, respectively obtaining a similarity between the video image and each reverse sequence image, including: respectively carrying out coupling operation on the video image and each reverse sequence image to obtain M coupling result images, wherein the sizes of the video image, the reverse sequence image and the coupling result images are the same, respectively counting the number of pixel points with non-zero values in the coupling result images aiming at each coupling result image, and taking the counting result as the similarity between the video image and the reverse sequence image corresponding to the coupling result image;

determining the repeatability between the first video and the second video according to the acquired similarity comprises the following steps: generating N rows and M columns of result matrixes according to the acquired similarity; the ith row in the result matrix corresponds to an ith frame of video image extracted from the second video, i is more than or equal to 1 and less than or equal to N, the jth column in the result matrix corresponds to a jth frame of video image extracted from the first video, j is more than or equal to 1 and less than or equal to M, and each element in the result matrix represents the similarity between the video image corresponding to the row and the reverse sequence image of the video image corresponding to the column; and under the principle that the path length is as long as possible and the sum of elements on the path is as small as possible, balancing the path length and the sum of elements on the path, determining an optimal continuous path from the result matrix, wherein the rows of the elements on the optimal continuous path are different, the columns of the elements are different, calculating the quotient of the sum of elements on the optimal continuous path and the number of pixel points included in the video image, calculating the quotient of the path length of the optimal continuous path and the M, calculating the product of the two quotients, and taking the product as the repeatability between the first video and the second video.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

the extracting M frames of video images from the first video includes: each frame in the first video is used as an extracted video image, or each interval L frames, one frame of video image is extracted from the first video, and L is a positive integer;

the extracting N frames of video images from the second video includes: and taking each frame in the second video as the extracted video image, or extracting one frame of video image from the second video every interval L frames.

3. The method of claim 1, wherein the step of determining the position of the substrate comprises,

and for any pixel point in the coupling result image, if the value of the corresponding pixel point in the video image of the pixel point is the same as the value of the corresponding pixel point in the reverse sequence image of the pixel point, setting the value of the pixel point to be zero, otherwise, setting the value of the pixel point to be not zero, and setting the corresponding pixel point to be the pixel point at the same position.

4. The method of claim 1, wherein the step of determining the position of the substrate comprises,

the video image includes: a bitmap image;

the inverting the value of each pixel point in the video image comprises: inverting Byte values of all pixel points in the video image;

the step of coupling the video image with each reverse sequence image to obtain M coupling result images comprises the following steps: and aiming at each reverse sequence image, respectively performing Byte and operation on the video image and corresponding pixel points in the reverse sequence image to obtain a coupling result image corresponding to the reverse sequence image.

5. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

6. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-4.