Detection Method and Device for Transcript Area in Courtroom Video Data

Abstract

The present application discloses a method and device for detecting a transcript area in court trial video data. The method includes: obtaining at least two video images at a preset time interval in the court trial video data; determining the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within a first change interval threshold, determining an actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image; when the actual proportion value is within a first proportion interval threshold, determining that there is a transcript area in the court trial video data; wherein, the transcript area refers to the position area corresponding to the real-time input court trial content displayed in the video image. The method for detecting a transcript area in the court trial video data provided by the present application can effectively improve the detection efficiency of the transcript area in the court trial video data, save labor costs, reduce the error rate, and thus improve the user experience.

Description

Technical Field

[0001] This application relates to the field of intelligent recognition technology, and in particular, to a method, device, storage medium, and electronic device for detecting a transcript area in court trial video data. Background Art

[0002] With the increasing emphasis on privacy in the trial process, the requirements for live court trials are also getting higher. Since the transcript content of publicly live-streamed court cases usually involves personal privacy, it is required not to directly display the transcript screen. However, with the increasing number of cases, the video content in the court trial video database is also increasing. How to quickly check whether the video images stored in the court trial video database contain the transcript screen has become the current focus of attention. The existing methods generally use artificial intelligence technology to detect video data to determine whether there is a transcript area. However, there are problems such as difficult sample collection, time-consuming and laborious model training and optimization, long development cycle, low accuracy, poor adaptability, high required computing performance, slow detection speed, and difficult expansion. Therefore, there is an urgent need for a method to quickly detect whether the screen contains a transcript area. With the diversification of the styles of the transcript area (the styles of the transcript area are different for different manufacturers, and the probability of update is very high with software upgrades and iterations), there are generally corresponding subtitles in the video, there are also character contents on the wall charts in the video, and the clarity of the transcript area in different videos is also different. The existing implementation methods of artificial intelligence algorithms need to collect a large number of samples for videos with different styles and different clarity. With the increase in styles, maintenance becomes more difficult and the adaptability is low. Therefore, how to provide a more effective detection scheme for the transcript area in court trial video data to improve the detection efficiency of the transcript area in court trial video data has become an urgent problem to be solved. Summary of the Invention

[0003] This application provides a method for detecting a transcript area in court trial video data to solve the defects of low efficiency and poor adaptability in the detection configuration process of the transcript area in court trial video data in the prior art.

[0004] This application provides a method for detecting a transcript area in court trial video data, including:

[0005] Obtain at least two video images at a preset time interval in the court trial video data;

[0006] Determine the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within the first change interval threshold, determine the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image; when the actual proportion value is within the first proportion interval threshold, determine that there is a transcript area in the court trial video data; wherein, the transcript area refers to the position area corresponding to the real-time input court trial content displayed in the video image.

[0007] Further, determining the degree of change in the number of characters between the video images specifically includes: identifying, by means of optical character recognition, the number of first characters included in the first video image, the number of second characters included in the second video image, and the number of repeated characters between the first video image and the second video image in the video images; wherein, in the trial video data, the first video image is located before the second video image.

[0008] Based on the number of first characters, the number of second characters, the number of repeated characters, and a preset character difference prediction model, the degree of change in the number of characters between the video images is obtained.

[0009] Further, after determining the degree of change in the number of characters between the video images, it further includes: when the degree of change in the number of characters is within the second change interval threshold, determining that there is a transcript area in the trial video data; wherein, the minimum value of the second change interval threshold is greater than or equal to the maximum value of the first change interval threshold.

[0010] Further, after determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, it further includes:

[0011] When the actual proportion value is within the second proportion interval threshold, determining that there is no transcript area in the trial video data; wherein, the minimum value of the second proportion interval threshold is greater than or equal to the maximum value of the first proportion interval threshold.

[0012] Further, the obtaining of at least two video images at a preset time interval in the trial video data specifically includes: converting the trial video data into corresponding multiple video frames, and extracting at least two video images from the multiple video frames according to the preset time interval.

[0013] Further, determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image specifically includes:

[0014] Determining the motion direction of the motion area in the video image through motion detection analysis, and determining the number of pixels with the motion direction being vertical and the total number of pixels in the corresponding video image;

[0015] Determining the proportion value of the number of pixels with the motion direction being vertical to the total number of pixels in the corresponding video image as the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image.

[0016] This application also provides a detection device for the transcript area in the trial video data, including:

[0017] A video image acquisition unit for acquiring at least two video images within a preset time interval from the trial video data;

[0018] A transcript area detection unit for determining the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within the first change interval threshold, determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, and when the actual proportion value is within the first proportion interval threshold, determining that there is a transcript area in the trial video data; wherein, the transcript area refers to the position area corresponding to the real-time input trial content displayed in the video image.

[0019] Further, the transcript area detection unit is specifically configured to:

[0020] Identifying, by means of optical character recognition, the number of first characters included in a first video image, the number of second characters included in a second video image, and the number of repeated characters between the first video image and the second video image in the video images; wherein, in the trial video data, the first video image is before the second video image;

[0021] Based on the number of first characters, the number of second characters, the number of repeated characters, and a preset character difference prediction model, obtaining the degree of change in the number of characters between the video images.

[0022] Further, after determining the degree of change in the number of characters between the video images, the transcript area detection unit is further configured to determine that there is a transcript area in the trial video data when the degree of change in the number of characters is within a second change interval threshold; wherein, the minimum value of the second change interval threshold is greater than or equal to the maximum value of the first change interval threshold.

[0023] Further, after determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, the transcript area detection unit is further configured to determine that there is no transcript area in the trial video data when the actual proportion value is within a second proportion interval threshold; wherein, the minimum value of the second proportion interval threshold is greater than or equal to the maximum value of the first proportion interval threshold.

[0024] Further, the video image acquisition unit is specifically configured to: convert the trial video data into corresponding multiple video frames, and extract at least two video images from the multiple video frames according to the preset time interval.

[0025] Further, the transcript area detection unit is specifically configured to:

[0026] Determine the motion direction of the motion area in the video image through motion detection analysis, and determine the number of pixels with a vertical motion direction and the total number of pixels of the corresponding video image;

[0027] Determine the ratio of the number of pixels with a vertical motion direction to the total number of pixels of the corresponding video image as the actual ratio of the number of pixels of the vertical motion area in the video image to the total number of pixels of the video image.

[0028] This application also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to execute and implement the detection method for the transcript area in the trial video data as described in any one of the above through the computer program.

[0029] This application also provides a computer-readable storage medium. The computer-readable storage medium includes a stored program, wherein the program executes and implements the detection method for the transcript area in the trial video data as described in any one of the above when running.

[0030] This application also provides a computer program product, including a computer program. The computer program implements the detection method for the transcript area in the trial video data as described in any one of the above when executed by a processor.

[0031] The detection method for the transcript area in the trial video data provided by this application obtains at least two video images at a preset time interval in the trial video data, determines the degree of change in the number of characters between the video images, and determines the actual ratio of the number of pixels of the vertical motion area in the video image to the total number of pixels of the video image when the degree of change in the number of characters is within the first change interval threshold; when the actual ratio is within the first ratio interval threshold, it is determined that there is a transcript area in the trial video data; it can effectively improve the detection efficiency of the transcript area in the trial video data, save labor costs, reduce the error rate, improve the adaptability of the application, and thus enhance the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0033] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0034] Figure 1It is a schematic flowchart of the method for detecting the transcript area in the court trial video data provided by this application;

[0035] Figure 2 It is a specific flowchart of the method for detecting the transcript area in the court trial video data provided by this application;

[0036] Figure 3 It is a schematic structural diagram of the device for detecting the transcript area in the court trial video data provided by this application;

[0037] Figure 4 It is a schematic structural diagram of the electronic device provided by this application. Detailed implementation manners

[0038] In order to enable those skilled in the art to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0039] It should be noted that the terms "first", "second", etc. in the specification of this application and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order different from those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0040] The following is a detailed description of the embodiments based on the method for detecting the transcript area in the court trial video data described in this application. As Figure 1 shown, it is a schematic flowchart of the method for detecting the transcript area in the court trial video data provided by this application, and the specific implementation process includes the following steps:

[0041] Step 101: Obtain at least two video images at a preset time interval in the court trial video data.

[0042] In this step, first convert the court trial video data into corresponding multiple video frames, and extract at least two video images from the multiple video frames according to the preset time interval.

[0043] For example, when the preset time interval is 1 minute, within 1 minute after the start of the court trial video data, as the content of the court record increases, the characters in the court record area will change significantly. Therefore, here, the first video image A at the very beginning of the court trial video data and the second video image B after 1 minute can be selected, that is, the time point corresponding to the first frame of video image A and the time point corresponding to the second video image B are separated by 1 minute. It should be noted that in the specific implementation process, the video object includes, but is not limited to, court trial video data, and can also be other types of video data, which will not be repeated here. The obtained video images include, but are not limited to, the first video image A and the second video image B separated by 1 minute.

[0044] Step 102: Determine the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within the first change interval threshold, determine the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image; when the actual proportion value is within the first proportion interval threshold, determine that there is a court record area in the court trial video data; wherein, the court record area refers to the position area corresponding to the real-time input court trial content displayed in the video image.

[0045] In this step, to determine the degree of change in the number of characters between the video images, the corresponding implementation process may include: identifying the number of first characters included in the first video image, the number of second characters included in the second video image, and the number of repeated characters between the first video image and the second video image in the video images through optical character recognition; wherein, in the court trial video data, the first video image is before the second video image; based on the number of first characters, the number of second characters, the number of repeated characters, and a preset character difference prediction model, obtain the degree of change in the number of characters between the video images. Among them, the optical character recognition method can be implemented through OCR (optical character recognition) technology, which refers to the process of analyzing and processing image files to obtain character and layout information.

[0046] In the implementation process, after determining the degree of change in the number of characters between the video images, it further includes: when the degree of change in the number of characters is within the second change interval threshold, determine that there is a court record area in the court trial video data. Among them, the minimum value of the second change interval threshold is greater than or equal to the maximum value of the first change interval threshold.

[0047] In addition, to determine the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, the corresponding implementation process includes: determining the motion direction of the motion area in the video image through motion detection analysis, determining the number of pixels with the motion direction being vertical, and the total number of pixels in the corresponding video image; and determining the proportion value of the number of pixels with the motion direction being vertical to the total number of pixels in the corresponding video image as the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image.

[0048] Further, after determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, it further includes: when the actual proportion value is within the second proportion interval threshold, determining that there is no transcript area in the court trial video data. Wherein, the minimum value of the second proportion interval threshold is greater than or equal to the maximum value of the first proportion interval threshold.

[0049] For example, OCR recognition can be performed on the first video image A and the second video image B respectively, the number of recognized characters is compared, and the degree of change in the number of characters between the video images (i.e., the ratio of the difference in character content) is calculated and denoted as X. Based on the number of characters M recognized by OCR in the first video image A and the number of characters N recognized by OCR in the second video image B, and the number of repeated characters C, when judging whether there is repetition, not only the character content but also the order of appearance can be considered synchronously to avoid deviation in the calculation result. The calculation formula for the degree of change in the number of characters X is as follows:

[0050] X = 1 - 2 * C / (M + N) (1)

[0051] If M ≠ 0 and N ≠ 0 and X is within the second change interval threshold [10%, 100%], then report the result: there is a transcript area in the court trial video data; if M = 0 or N = 0 or X is within the first change interval threshold [0, 10%), it indicates that the video image is not clear and the OCR effect is not good. At this time, it is still impossible to judge whether there is a transcript area, so the next judgment is entered, that is, to judge whether the actual proportion value is within the first proportion interval threshold. When the actual proportion value is within the first proportion interval threshold, it is determined that there is a transcript area in the court trial video data. Wherein, the transcript area refers to the position area corresponding to the real-time input court trial content displayed in the video image. In addition, the preset time interval, change interval threshold, or proportion interval threshold can also be fine-tuned according to the actual situation to improve the effect, which will not be elaborated in detail here. The change interval threshold includes the first change interval threshold and the second change interval threshold. The proportion interval threshold includes the first proportion interval threshold and the second proportion interval threshold.

[0052] In the process of judging the pixel proportion and movement direction of the moving areas of the first video image A and the second video image B, the movement direction (vertical and horizontal) and the number of pixels in the moving areas of the two video images (i.e., the first video image A and the second video image B) can be obtained through the motion detection and analysis method in the prior art. At the same time, the number of pixels with a vertical movement direction can be calculated, and the proportion of the number of pixels (vertical) V in the moving area to the total number of pixels W is calculated, that is, the proportion value of the number of pixels with a vertical movement direction to the total number of pixels of the corresponding video image. Here, the actual proportion value of the number of pixels in the vertical moving area of the video image to the total number of pixels of the video image is represented by Y, and the calculation formula of Y is:

[0053] Y = V / W (2)

[0054] The judgment criterion is: if Y falls within the second proportion interval threshold [0%, 6), the result is reported: there is no notarized area in the picture; if Y falls within the first proportion interval threshold [6%, 100], the result is reported: there is a notarized area in the picture. It should be noted that the interval here can also be adjusted according to the actual situation to improve the effect.

[0055] As Figure 2 shown, in one embodiment, first, the trial video data can be converted into two video images. The first video image A and the second video image B one minute later are selected, and OCR recognition is performed. The OCR character results and the number of characters of the two video images are respectively recorded. The number of characters recognized from the video image A through OCR is M, and the number of characters recognized from the video image B through OCR is N. The number of repeated characters is C, and the proportion of character difference (i.e., the degree of change in the number of characters), X = 1 - 2*C / (M + N).

[0056] Furthermore, the values of M, N, and X are judged. The judgment is made: if M≠0 and N≠0 and X is within the second change interval threshold [10%, 100%], the result is reported: there is a notarized area in the trial video data; if M = 0 or N = 0 or X is within the first change interval threshold [0, 10%), it means that the video image is not clear and the OCR recognition effect is not good. At this time, it is still impossible to judge whether there is a notarized area, so the next judgment is entered.

[0057] The number of pixels in the motion area (vertically) is denoted as V, the total number of pixels in the video image is denoted as W, and the calculation formula for the proportion Y (i.e., the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image) is: Y = V / W. Calculate the value of Y. Determine whether Y is within the range of the first proportion interval threshold [6%, 100]. If so, report the result: There is a transcript area in the court trial video data; if not, report the result: There is no transcript area in the court trial video data, and the process ends. The present invention converts the problem of transcript area detection into problems of OCR character number calculation, motion area pixel, and motion direction calculation, and combines the actual test data to improve the processing efficiency and accuracy and reduce the algorithm performance occupancy. In addition, by converting the video data into video images, selecting video images at a certain time interval, performing OCR recognition respectively, according to the degree of change of the recognized character content (such as the number of characters), and at the same time performing pixel change judgment to determine whether the pixels in a region are changing vertically, to comprehensively determine whether there is a transcript area, which enhances the application adaptability, adapts to a variety of different scenarios, has good adaptability, and both the time interval and the interval threshold can be freely adjusted to adapt to different on-site environments.

[0058] The method for detecting a transcript area in court trial video data provided by this application, by obtaining at least two video images at a preset time interval in the court trial video data, determining the degree of change in the number of characters between the video images, and when the degree of change in the number of characters is within the first change interval threshold, determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image; when the actual proportion value is within the first proportion interval threshold, determining that there is a transcript area in the court trial video data; it can effectively improve the detection efficiency of the transcript area in court trial video data, save labor costs, reduce the error rate, improve the application adaptability, and thus enhance the user experience.

[0059] The detection device for the transcript area in court trial video data provided by this application will be described below. The detection device for the transcript area in court trial video data described below can be mutually corresponding and referred to the detection method for the transcript area in court trial video data described above.

[0060] Reference Figure 3 As shown, it is a schematic structural diagram of the detection device for the transcript area in court trial video data provided by this application.

[0061] The detection device for the transcript area in court trial video data described in this application specifically includes the following parts:

[0062] A video image acquisition unit 301, configured to acquire at least two video images at a preset time interval in the court trial video data;

[0063] The transcript area detection unit 302 is used to determine the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within the first change interval threshold, determine the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, and when the actual proportion value is within the first proportion interval threshold, determine that there is a transcript area in the trial video data; wherein, the transcript area refers to the position area corresponding to the real-time input trial content displayed in the video image.

[0064] Further, the transcript area detection unit is specifically used for:

[0065] Identify the number of first characters included in the first video image, the number of second characters included in the second video image, and the number of repeated characters between the first video image and the second video image in the video image by means of optical character recognition; wherein, in the trial video data, the first video image is located before the second video image.

[0066] Based on the number of first characters, the number of second characters, the number of repeated characters, and a preset character difference prediction model, obtain the degree of change in the number of characters between the video images.

[0067] Further, after determining the degree of change in the number of characters between the video images, the transcript area detection unit is further used to determine that there is a transcript area in the trial video data when the degree of change in the number of characters is within the second change interval threshold; wherein, the minimum value of the second change interval threshold is greater than or equal to the maximum value of the first change interval threshold.

[0068] Further, after determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, the transcript area detection unit is further used to determine that there is no transcript area in the trial video data when the actual proportion value is within the second proportion interval threshold; wherein, the minimum value of the second proportion interval threshold is greater than or equal to the maximum value of the first proportion interval threshold.

[0069] Further, the video image acquisition unit is specifically used for: converting the trial video data into corresponding multiple video frames, and extracting at least two video images from the multiple video frames at the preset time interval.

[0070] Further, the transcript area detection unit is specifically used for:

[0071] Determine the motion direction of the motion area in the video image through motion detection analysis, and determine the number of pixels with the motion direction being vertical and the total number of pixels of the corresponding video image.

[0072] Determine the ratio value of the number of pixels with the longitudinal movement direction to the total number of pixels of the corresponding video image as the actual ratio value of the number of pixels of the longitudinal movement area in the video image to the total number of pixels of the video image.

[0073] The detection device for the transcript area in the trial video data provided by this application obtains at least two video images at a preset time interval in the trial video data, determines the degree of change in the number of characters between the video images, and when the degree of change in the number of characters is within the first change interval threshold, determines the actual ratio value of the number of pixels of the longitudinal movement area in the video image to the total number of pixels of the video image; when the actual ratio value is within the first ratio interval threshold, determines that there is a transcript area in the trial video data; it can effectively improve the detection efficiency of the transcript area in the trial video data, save labor costs, reduce the error rate, improve the adaptability of the application, and thus enhance the user experience.

[0074] Figure 4 Illustrates a schematic physical structure diagram of an electronic device. As Figure 4 shown, the electronic device may include: a processor 401, a communications interface 404, a memory 402, and a communication bus 403. Among them, the processor 401, the communications interface 404, and the memory 402 complete mutual communication through the communication bus 403. The processor 401 can call the logical instructions in the memory 402 to execute the method for detecting the transcript area in the trial video data, and the method includes: obtaining at least two video images at a preset time interval in the trial video data; determining the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within the first change interval threshold, determining the actual ratio value of the number of pixels of the longitudinal movement area in the video image to the total number of pixels of the video image; when the actual ratio value is within the first ratio interval threshold, determining that there is a transcript area in the trial video data; where the transcript area refers to the position area corresponding to the real-time recorded trial content in the video image.

[0075] In addition, when the logical instructions in the above-mentioned memory 402 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0076] On the other hand, the present application also provides a computer program product. The computer program product includes a computer program that can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for detecting the transcript area in the trial video data provided by the above-mentioned various methods. The method includes: obtaining at least two video images at a preset time interval in the trial video data; determining the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within the first change interval threshold, determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image; when the actual proportion value is within the first proportion interval threshold, determining that there is a transcript area in the trial video data; where the transcript area refers to the position area corresponding to the real-time input trial content displayed in the video image.

[0077] On another aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium includes a stored program. When the program runs, it executes the method for detecting the transcript area in the trial video data provided by the above-mentioned various methods. The method includes: obtaining at least two video images at a preset time interval in the trial video data; determining the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within the first change interval threshold, determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image; when the actual proportion value is within the first proportion interval threshold, determining that there is a transcript area in the trial video data; where the transcript area refers to the position area corresponding to the real-time input trial content displayed in the video image.

[0078] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0079] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing 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.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting the transcript area in court trial video data, characterized in that Including: Obtaining at least two video images within a preset time interval from the trial video data; Determining the degree of change in the number of characters between the video images; when the degree of change in the number of characters is within the first change interval threshold, determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image; when the actual proportion value is within the first proportion interval threshold, determining that there is a transcript area in the trial video data; that is, comprehensively judging whether there is a transcript area based on the degree of change in the number of characters and the degree of vertical pixel change; wherein, the transcript area refers to the position area corresponding to the real-time input trial content in the video image.

2. The method for detecting the transcript area in the court trial video data according to claim 1, wherein Determining the degree of change in the number of characters between the video images specifically includes: Identifying the number of first characters included in the first video image, the number of second characters included in the second video image, and the number of repeated characters between the first video image and the second video image in the video image by means of optical character recognition; wherein, in the trial video data, the first video image is before the second video image. Based on the number of first characters, the number of second characters, the number of repeated characters, and a preset character difference prediction model, obtaining the degree of change in the number of characters between the video images.

3. The method for detecting the transcript area in the trial video data according to claim 1, wherein After determining the degree of change in the number of characters between the video images, it further includes: when the degree of change in the number of characters is within the second change interval threshold, determining that there is a transcript area in the trial video data; wherein, the minimum value of the second change interval threshold is greater than or equal to the maximum value of the first change interval threshold.

4. The method for detecting the transcript area in the trial video data according to claim 1, wherein After determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, it further includes: When the actual proportion value is within the second proportion interval threshold, determining that there is no transcript area in the trial video data; wherein, the minimum value of the second proportion interval threshold is greater than or equal to the maximum value of the first proportion interval threshold.

5. The method for detecting the transcript area in the court trial video data according to claim 1, wherein The obtaining at least two video images within a preset time interval from the trial video data specifically includes: converting the trial video data into corresponding multiple video frames, and extracting at least two video images from the multiple video frames according to the preset time interval.

6. The method for detecting a transcript area in courtroom trial video data according to claim 1, wherein Determining the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image specifically includes: Determining the motion direction of the motion area in the video image through motion detection analysis, and determining the number of pixels with the motion direction being vertical and the total number of pixels in the corresponding video image; Determining the proportion value of the number of pixels with the motion direction being vertical to the total number of pixels in the corresponding video image as the actual proportion value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image.

7. A detection device for the transcript area in court trial video data, characterized in that, Including: A video image acquisition unit for obtaining at least two video images within a preset time interval from the trial video data; A transcript area detection unit, configured to determine the degree of change in the number of characters between the video images; in a case where the degree of change in the number of characters is within a first change interval threshold, determine an actual ratio value of the number of pixels in the vertical motion area in the video image to the total number of pixels in the video image, and when the actual ratio value is within a first ratio interval threshold, determine that there is a transcript area in the trial video data; that is, comprehensively judge whether there is a transcript area based on the degree of change in the number of characters and the degree of vertical change in pixels; wherein, the transcript area refers to the position area corresponding to the real-time input trial content displayed in the video image.

8. The detection device for the transcript area in the trial video data according to claim 7, wherein The transcript area detection unit is specifically configured to: Identify, by means of optical character recognition, the number of first characters included in a first video image, the number of second characters included in a second video image, and the number of repeated characters between the first video image and the second video image in the video image; wherein, in the trial video data, the first video image is located before the second video image; Based on the number of first characters, the number of second characters, the number of repeated characters, and a preset character difference prediction model, obtain the degree of change in the number of characters between the video images.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when running, executes the method for detecting a transcript area in trial video data according to any one of claims 1 to 6.

10. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method for detecting a transcript area in trial video data according to any one of claims 1 to 6 through the computer program.

Images