A method for tracing the source of secretly filmed and recorded videos based on digital watermark

Abstract

The present application relates to the technical field of video tracing, and in particular to a method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks, the method comprising: performing an embedding strength analysis on the video data based on the video characteristics, determining the embedding strength information corresponding to the video data, and at the same time, sending the video data to the human visual system for simulated perception to determine the watermark embedding position. Further, a watermark is embedded based on the watermark information, the embedding strength information, and the watermark embedding position to obtain target video data carrying the watermark. When abnormal playback of the target video data is detected, the watermark is parsed based on the target video data to obtain video release information to complete the video tracing operation. The watermark embedding process takes into account the video characteristics of the video data and the selection of the embedding position, ensuring the robustness and concealment of the watermark information in the video data.

Description

Technical Field

[0001] The present application relates to the technical field of video tracing, and in particular to a method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks. Background Art

[0002] With the rapid development of modern technology, video voyeurism is becoming increasingly difficult to detect and prevent, infringing on personal privacy and information security. Traditional methods of tracing the source of voyeurism, such as physical detection and network monitoring, can work to a certain extent, but due to technical limitations and operational complexity, it is often difficult to achieve comprehensive and efficient tracing of voyeurism.

[0003] In recent years, the emergence of digital watermarking technology has provided an efficient processing method for video tracing. Digital watermarking technology is a technology that embeds specific information (such as copyright information, identity identification, etc.) into digital media (such as images, videos, etc.). By embedding specific digital watermark information in video data, the source of the video can be tracked and traced.

[0004] Therefore, how to ensure the invisibility and robustness of digital watermarks during the process of embedding them into videos is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0005] The purpose of this application is to provide a method for tracing the source of secretly filmed or recorded videos based on digital watermarks, so as to solve at least one of the above technical problems.

[0006] The above invention objectives of the present application are achieved through the following technical solutions:

[0007] In the first aspect, the present application provides a method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks, which adopts the following technical solutions:

[0008] A method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks, comprising:

[0009] Acquire video characteristics of video data, perform embedding strength analysis on the video data based on the video characteristics, and determine embedding strength information corresponding to the video data, wherein the video characteristics include: pixel variation and texture complexity;

[0010] Sending the video data to a human visual system for simulated perception to determine a watermark embedding position;

[0011] Acquire watermark information corresponding to the video data, and embed the watermark based on the watermark information, the embedding strength information and the watermark embedding position to obtain target video data carrying the watermark;

[0012] When abnormal playback of the target video data is detected, watermark analysis is performed based on the target video data to obtain video publishing information to complete the video tracing operation.

[0013] By adopting the above technical solution, the embedding strength of the video data is analyzed based on the video characteristics to determine the embedding strength information corresponding to the video data. At the same time, the video data is sent to the human visual system for simulated perception to determine the watermark embedding position. Then, the watermark is embedded based on the watermark information, the embedding strength information and the watermark embedding position to obtain the target video data carrying the watermark. When abnormal playback of the target video data is detected, the watermark is parsed based on the target video data to obtain the video release information to complete the video tracing operation. The watermark embedding process takes into account the video characteristics of the video data and the selection of the embedding position, ensuring the robustness and concealment of the watermark information in the video data.

[0014] In a preferred example, the present application may be further configured as follows: performing embedding strength analysis on the video data based on the video characteristics to determine embedding strength information corresponding to the video data includes:

[0015] Based on the pixel change and the texture complexity in the video characteristics, the video data is divided into video regions to determine a high-frequency region and a low-frequency region;

[0016] Performing embedding strength analysis on the first video data corresponding to the high-frequency area to obtain a first embedding strength;

[0017] An embedding strength analysis is performed on the second video data corresponding to the low-frequency area to obtain a second embedding strength, wherein the embedding strength information is used to characterize a corresponding relationship between different video areas in the video data and corresponding embedding strengths.

[0018] In a preferred example, the present application may be further configured as follows: sending the video data to a human visual system for simulated perception to determine a watermark embedding position includes:

[0019] Preprocessing the video data to obtain the video data to be simulated, wherein the preprocessing includes: color space conversion, noise reduction, and contrast enhancement;

[0020] The video data to be simulated is sent to a human visual system, and the human visual system is controlled to perform multi-dimensional simulation perception to determine a watermark embedding position, wherein the multi-dimensional simulation perception includes: frequency sensitivity simulation perception and brightness sensitivity simulation perception.

[0021] In a preferred example, the present application can be further configured as follows: when it is detected that the target video data is abnormally played, watermark parsing is performed based on the target video data to obtain video release information to complete the video source tracing operation, including:

[0022] During the target video playback process, video playback parameters are obtained, and a first abnormality detection is performed based on the video playback parameters to obtain a first abnormality detection result, wherein the video playback parameters include: video frame rate, resolution, and encoding quality;

[0023] Obtaining a video playback log, and performing a second anomaly detection based on the video playback log to obtain a second anomaly detection result, wherein the video playback log includes: playback time, playback position, and user behavior;

[0024] Using computer vision technology, performing video image analysis on the target video data to determine a third anomaly detection result;

[0025] The first abnormality detection result, the second abnormality detection result and the third abnormality detection result are combined to obtain the video playback status, wherein the video playback status includes: normal playback and abnormal playback.

[0026] In a preferred example, the present application can be further configured as follows: performing watermark parsing based on the target video data to obtain video publishing information includes:

[0027] Extracting watermarks based on the target video data to obtain a watermark to be parsed, and parsing watermarks based on the watermark to be parsed to obtain a watermark to be matched;

[0028] Based on the matching operation between the watermark to be matched and the watermark database, the video release information is determined, wherein the watermark database is a database storing all watermark information embedded in the video, and the video release information includes: publisher information, release time, shooting time, and shooting location.

[0029] In a preferred example, the present application may be further configured as follows: after performing watermark analysis based on the target video data to obtain video release information, the following further includes:

[0030] Acquire transmission information of the target video, wherein the transmission information includes: playback carrier, sharing record, download record and forwarding record;

[0031] Performing propagation analysis based on the transmission information to determine a propagation path, and visually displaying the propagation path by constructing a propagation graph, wherein nodes in the propagation graph represent playback carriers and edges represent sharing, downloading or forwarding behaviors;

[0032] The playback data of the target video at each node in the propagation graph is obtained, and propagation analysis is performed based on the playback data of each node to obtain a target propagation graph marked with key nodes.

[0033] In a second aspect, the present application provides an electronic device, which adopts the following technical solution:

[0034] at least one processor;

[0035] Memory;

[0036] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned method for tracing the source of secretly photographed or secretly recorded videos based on digital watermarks.

[0037] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0038] A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the above-mentioned method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks.

[0039] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution:

[0040] A computer program product includes a computer program, which, when executed by a processor, implements the above-mentioned method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks.

[0041] In summary, the present application includes at least one of the following beneficial technical effects:

[0042] Based on the video characteristics, the embedding strength of the video data is analyzed to determine the embedding strength information corresponding to the video data. At the same time, the video data is sent to the human visual system for simulated perception to determine the watermark embedding position. Then, the watermark is embedded based on the watermark information, embedding strength information and watermark embedding position to obtain the target video data carrying the watermark. When abnormal playback of the target video data is detected, the watermark is parsed based on the target video data to obtain the video release information to complete the video traceability operation. The watermark embedding process takes into account the video characteristics of the video data and the selection of the embedding position, ensuring the robustness and concealment of the watermark information in the video data.

[0043] Based on the pixel changes and texture complexity in the video characteristics, the video data is divided into video regions to determine the high-frequency region and the low-frequency region. The embedding strength analysis is performed on the first video data corresponding to the high-frequency region to obtain the first embedding strength. At the same time, the embedding strength analysis is performed on the second video data corresponding to the low-frequency region to obtain the second embedding strength. By analyzing the characteristics of the pixel changes and texture complexity of the video data, the appropriate embedding strength is selected to improve the robustness of the watermark embedding. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flowchart of a method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks in one embodiment of the present application;

[0045] Figure 2 This is a schematic diagram of the structure of a video secretly filmed or secretly recorded source tracing device based on digital watermark in one embodiment of the present application;

[0046] Figure 3 It is a structural schematic diagram of an electronic device according to one embodiment of the present application. DETAILED DESCRIPTION

[0047] The following combination Figures 1 to 3 This application is described in further detail.

[0048] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.

[0049] In order to make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment 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 the field without creative work are within the scope of protection of the present application. It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the data related to the object is involved in the embodiment of the present application, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in accordance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiment, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained, and the embodiment also needs to be implemented with the authorization and consent of the object.

[0050] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0051] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0052] The embodiment of the present application provides a method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. Figure 1 As shown, the method includes step S101, step S102, step S103 and step S104, wherein:

[0053] Step S101: acquiring video characteristics of video data, performing embedding strength analysis on the video data based on the video characteristics, and determining embedding strength information corresponding to the video data, wherein the video characteristics include: pixel variation and texture complexity.

[0054] For the embodiment of the present application, the appropriate embedding strength is selected by analyzing the characteristics of the pixel change and texture complexity of the video data, thereby improving the robustness of the watermark embedding, so as to ensure that the video data undergoes certain changes or distortions during transmission or processing, and the embedded watermark information can still maintain a certain detectability and recognizability. Therefore, the video characteristics of the video data are obtained, that is, continuous frames are extracted from the video data, and the pixel differences between adjacent frames are calculated. The larger the pixel difference. Indicates that the pixel change is more obvious; the texture complexity is evaluated by analyzing the grayscale distribution, edge density, directionality and other information of the local area in the video frame. Specifically, the texture features of the video frame are extracted by gray level co-occurrence matrix (GLCM), Fourier transform or wavelet transform method, and the texture complexity is quantified. Then, the video data is embedded based on the video characteristics. Strength analysis is performed to determine the embedding strength information corresponding to the video data. There are many ways to analyze the embedding strength, which are no longer limited in the embodiment of the present application. In one feasible method, based on the pixel changes and texture complexity in the video characteristics, the video data is divided into video areas to determine the high-frequency area and the low-frequency area; the embedding strength analysis is performed on the first video data corresponding to the high-frequency area to obtain the first embedding strength; the embedding strength analysis is performed on the second video data corresponding to the low-frequency area to obtain the second embedding strength, wherein the embedding strength information is used to characterize the correspondence between different video areas in the video data and the corresponding embedding strengths, the first embedding strength is a stronger embedding strength to enhance the robustness of the watermark embedding, and the second embedding strength is a weaker embedding strength to ensure the invisibility of the watermark.

[0055] Step S102: sending the video data to the human visual system for simulated perception to determine the watermark embedding position.

[0056] For the embodiment of the present application, in order to make the watermark more visually concealed and less easily perceived by human vision, by simulating the human visual system and performing visual saliency detection, the watermark embedding position can be determined more accurately, the efficiency and effect of watermark embedding can be improved, and the impact of watermark embedding on video quality can be reduced. Therefore, the video data is sent to the human visual system for simulated perception to determine the watermark embedding position. In an achievable manner, the video data is preprocessed to obtain the video data to be simulated, and the video data to be simulated is sent to the human visual system, and the human visual system is controlled to perform multi-dimensional simulated perception to determine the watermark embedding position, wherein the multi-dimensional simulated perception includes: frequency sensitivity simulated perception, brightness sensitivity simulated perception, and the watermark embedding position is an area with low visual saliency to ensure the concealment of the watermark.

[0057] Step S103: Acquire watermark information corresponding to the video data, and embed the watermark based on the watermark information, embedding strength information and watermark embedding position to obtain target video data carrying the watermark.

[0058] For the embodiments of the present application, by embedding watermark information in video data, the copyright of the video content can be effectively identified and protected. Even if the video data is illegally copied or disseminated, the copyright ownership can be tracked and confirmed by detecting the watermark information. At the same time, the watermark embedding process takes into account the video characteristics of the video data and the choice of embedding position, ensuring the robustness and concealment of the watermark information in the video data.

[0059] Specifically, the watermark information corresponding to the video data is obtained, and the watermark information includes but is not limited to: identification code (used to uniquely identify video data), shooting time, shooting location, publisher information, publishing time, equipment information, and digital signature, so that the copyright owner can trace and prove the original copyright of the video by extracting the watermark information. Then, the watermark is embedded based on the watermark information, embedding strength information, and watermark embedding position to obtain the target video data carrying the watermark, that is, for the video data, the frequency domain watermark technology can be used, such as the discrete cosine transform (DCT) domain and the discrete Fourier transform (DFT) domain, and appropriate frequency bands or coefficients are selected in these transform domains to embed the watermark information at the watermark embedding position, and in the watermark embedding process, the embedding strength needs to be controlled to ensure that the embedding strength of the watermark information in the video data is adjusted according to the embedding strength information. Finally, after the watermark embedding is completed, the video data with the embedded watermark is saved as a new video file, that is, the target video data carrying the watermark.

[0060] Step S104: When abnormal playback of the target video data is detected, watermark analysis is performed based on the target video data to obtain video publishing information to complete the video tracing operation.

[0061] For the embodiment of the present application, the electronic device will monitor the target video data in real time during the playback and dissemination process to determine the playback status of the target video data, wherein the dimensions of real-time monitoring include but are not limited to: playback quality monitoring, video dissemination monitoring, video screen content monitoring, and of course, real-time monitoring of other dimensions can also be included, and the embodiment of the present application is no longer limited to this. When it is detected that the target video data is abnormally played, it indicates that the target video may be disseminated or illegally uploaded without authorization. Therefore, watermark parsing is performed based on the target video data to obtain video release information to complete the video tracing operation, effectively protect the copyright of the video content, and prevent illegal copying and dissemination. There are many feasible ways to analyze watermarks. In one feasible way, watermark extraction is performed based on the target video data to obtain the watermark to be parsed, and watermark parsing is performed based on the watermark to be parsed to obtain the watermark to be matched; matching operation is performed based on the watermark to be matched and the watermark database to determine the video release information, wherein the watermark database is a database that stores all watermark information embedded in the video, and the video release information includes: publisher information, release time, shooting time, and shooting location.

[0062] It can be seen that in the embodiment of the present application, the embedding strength analysis of the video data is performed based on the video characteristics to determine the embedding strength information corresponding to the video data. At the same time, the video data is sent to the human visual system for simulated perception to determine the watermark embedding position. Then, the watermark is embedded based on the watermark information, the embedding strength information and the watermark embedding position to obtain the target video data carrying the watermark. When abnormal playback of the target video data is detected, the watermark is parsed based on the target video data to obtain the video release information to complete the video tracing operation. The watermark embedding process takes into account the video characteristics of the video data and the selection of the embedding position, ensuring the robustness and concealment of the watermark information in the video data.

[0063] Furthermore, in order to improve the robustness of watermark embedding, in an embodiment of the present application, embedding strength analysis is performed on video data based on video characteristics to determine embedding strength information corresponding to the video data, including:

[0064] Based on the pixel changes and texture complexity in the video characteristics, the video data is divided into video regions to determine the high-frequency region and the low-frequency region;

[0065] Performing embedding strength analysis on the first video data corresponding to the high-frequency region to obtain a first embedding strength;

[0066] An embedding strength analysis is performed on the second video data corresponding to the low-frequency region to obtain a second embedding strength, wherein the embedding strength information is used to characterize a corresponding relationship between different video regions in the video data and corresponding embedding strengths.

[0067] For the embodiments of the present application, the appropriate embedding strength is selected by analyzing the characteristics of pixel changes and texture complexity of the video data, thereby improving the robustness of watermark embedding, to ensure that even if the video data undergoes certain changes or distortions during transmission or processing, the embedded watermark information can still maintain a certain degree of detectability and recognizability.

[0068] Specifically, based on the pixel changes and texture complexity in the video characteristics, the video data is divided into video regions to determine the high-frequency region and the low-frequency region. For the process of video region division, the video data can be converted from the spatial domain to the frequency domain using Fourier transform or discrete cosine transform, and the video frame is divided into high-frequency and low-frequency regions in the frequency domain. The high-frequency region refers to the region with drastic pixel changes and rich textures, such as edges, scenes with rich details or dynamic image parts. These regions can withstand stronger watermark embedding strengths without significantly affecting the visual quality of the video because they contain a lot of detail information; the low-frequency region refers to the region with gentle pixel changes and relatively simple textures, such as the smooth background or static image part of the video. These regions are more sensitive to visual perception, so weaker embedding strengths are required to ensure the invisibility of the watermark. Then, statistical analysis is performed on the pixel values ​​in the high-frequency region, for example, the variance and standard deviation of the pixel values ​​are calculated to evaluate the dynamic range and activity of the high-frequency region, and the first embedding strength is determined based on the corresponding relationship between the statistical characteristics and the preset embedding strength. A statistical analysis is performed on the pixel values ​​in the low-frequency area, and a second embedding strength is determined based on the correspondence between the statistical characteristics of the low-frequency area and the preset embedding strength, wherein the first embedding strength is higher than the second embedding strength. Finally, a mapping relationship is established between different areas (high-frequency area and low-frequency area) in the data video and the corresponding embedding strength, so that it can be quickly searched and referenced in the subsequent watermark embedding process, wherein the mapping relationship can be implemented through a data structure (e.g., a hash table, an array). In this way, a stronger first embedding strength is used in the first video data part corresponding to the high-frequency area, which can ensure that the digital watermark can still maintain high robustness when subjected to various processing and transformations. However, a weaker second embedding strength is used in the second video data part corresponding to the low-frequency area, which ensures that effective digital watermark embedding is achieved without almost changing the video appearance. The embedding strength analysis is performed by combining the high-frequency and low-frequency characteristics of the video data to achieve the best balance between watermark invisibility and robustness.

[0069] It can be seen that in the embodiment of the present application, based on the pixel change and texture complexity in the video characteristics, the video data is divided into video regions to determine the high-frequency region and the low-frequency region. The embedding strength analysis is performed on the first video data corresponding to the high-frequency region to obtain the first embedding strength. At the same time, the embedding strength analysis is performed on the second video data corresponding to the low-frequency region to obtain the second embedding strength. By analyzing the characteristics of the pixel change and texture complexity of the video data, the appropriate embedding strength is selected, thereby improving the robustness of the watermark embedding.

[0070] Furthermore, in order to ensure the concealment of the watermark, in the embodiment of the present application, the video data is sent to the human visual system for simulated perception to determine the watermark embedding position, including:

[0071] Preprocessing the video data to obtain the video data to be simulated, wherein the preprocessing includes: color space conversion, noise reduction, and contrast enhancement;

[0072] The video data to be simulated is sent to the human visual system, and the human visual system is controlled to perform multi-dimensional simulation perception to determine the watermark embedding position, wherein the multi-dimensional simulation perception includes: frequency sensitivity simulation perception and brightness sensitivity simulation perception.

[0073] For the embodiment of the present application, in order to improve the quality of video data and facilitate the subsequent embedding of digital watermarks, the video data is preferentially preprocessed to obtain the video data to be simulated, wherein the preprocessing includes: color space conversion, noise reduction, and contrast enhancement. The color space conversion is used to convert the original video data from one color space to another color space, which usually involves the calculation and mapping of pixel values; the video data is subjected to noise reduction processing to reduce the impact of noise on watermark embedding and subsequent simulation perception; and contrast enhancement is used to improve the clarity and recognizability of the video image. Then, the preprocessed video data is sent to the simulated human visual system through the system association interface, and the human visual system is controlled to perform multi-dimensional simulation perception, wherein the multi-dimensional simulation perception includes: frequency sensitivity simulation perception, brightness sensitivity simulation perception, contrast masking simulation perception, and edge characteristic simulation perception. Since the human visual system has different sensitivities to low-frequency components and high-frequency components, it will affect the effect of digital watermark embedding to a certain extent. Therefore, frequency sensitivity simulation perception is used to simulate the sensitivity of human vision to different frequency components, and the area with weak human visual sensitivity is marked as the embedding position to be verified. Under different brightness conditions, the human visual system will perceive the video content differently. The brightness sensitivity simulation perception is used to simulate the sensitivity of human vision to light, and the area with weak human visual sensitivity is marked as the embedding position to be verified. Finally, the overlapping part of the two embedding positions to be verified is selected as the watermark embedding position, and the watermark embedding position is an area with low visual significance to ensure the concealment of the watermark.

[0074] It can be seen that in the embodiment of the present application, in order to improve the quality of video data, the video data is preprocessed to obtain the video data to be simulated. Then, the video data to be simulated is sent to the human visual system, and the human visual system is controlled to perform multi-dimensional simulation perception to determine the watermark embedding position, and the watermark embedding position is an area with low visual significance to ensure the concealment of the watermark.

[0075] Further, in order to improve the accuracy of anomaly detection, in an embodiment of the present application, when abnormal playback of target video data is detected, watermark parsing is performed based on the target video data to obtain video release information to complete the video tracing operation, including:

[0076] During the target video playback process, video playback parameters are obtained, and a first abnormality detection is performed based on the video playback parameters to obtain a first abnormality detection result, wherein the video playback parameters include: video frame rate, resolution, and encoding quality;

[0077] Obtaining a video playback log, and performing a second anomaly detection based on the video playback log to obtain a second anomaly detection result, wherein the video playback log includes: playback time, playback position, and user behavior;

[0078] Using computer vision technology, perform video image analysis on the target video data to determine the third anomaly detection result;

[0079] The first abnormality detection result, the second abnormality detection result and the third abnormality detection result are combined to obtain the video playback status, wherein the video playback status includes: normal playback and abnormal playback.

[0080] For the embodiments of the present application, during the target video playback process, anomaly detection is performed in multiple dimensions, which can capture abnormal situations more comprehensively, reduce false alarms that may be generated by a single detection method, and improve the accuracy of anomaly detection. Specifically, the video playback parameters such as the video frame rate, resolution, and encoding quality of the target video are obtained through a video player or a related API, and the playback parameter threshold in the electronic device is obtained, that is, the playback parameter threshold specifies the normal range of each video playback parameter, so the video playback parameters are compared with the pre-stored playback parameter threshold for a first anomaly detection. When any parameter is abnormal, the first anomaly detection result is determined to be abnormal; otherwise, the first anomaly detection result is determined to be normal. At the same time, the video playback log is obtained through the player, server or related log recording tool, wherein the video playback log includes but is not limited to: playback time, playback position (progress bar position) and user behavior (for example, pause, fast forward, fast rewind, etc.), and then the second abnormality detection is performed on the video playback log to detect whether the target video has abnormal behavior, such as a large number of repeated playbacks in a short period of time, skipping of specific parts or abnormal user operations, and the abnormal features corresponding to the abnormal behavior are pre-stored in the electronic device. When the abnormal features are detected, the second abnormality detection result is determined to be abnormal, otherwise, the second abnormality detection result is determined to be normal. At the same time, a specific segment is captured from the video data, and the specific segment is analyzed using computer solution technology to detect whether the specific segment has abnormal content or mode. The abnormality includes but is not limited to: color abnormality, motion abnormality, object recognition abnormality, etc. When the abnormality is detected, the third abnormality detection result is determined to be abnormal, otherwise, the third abnormality detection result is determined to be normal. Finally, the first abnormality detection result, the second abnormality detection result and the third abnormality detection result are combined to obtain the video playback situation, wherein only when the three abnormality detection results are normal, the video playback situation is determined to be normal playback, otherwise, the video playback situation is determined to be abnormal playback.

[0081] It can be seen that in an embodiment of the present application, during the playback of the target video, the video playback parameters are obtained, and a first anomaly detection is performed based on the video playback parameters to obtain a first anomaly detection result. At the same time, a second anomaly detection is performed based on the video playback log to obtain a second anomaly detection result, and computer vision technology is used to perform video screen analysis on the target video data to determine a third anomaly detection result. Finally, the video playback situation is obtained by combining the first anomaly detection result, the second anomaly detection result, and the third anomaly detection result. During the playback of the target video, anomaly detection is performed in multiple dimensions to more comprehensively capture abnormal situations, reduce false alarms that may be caused by a single detection method, and improve the accuracy of anomaly detection.

[0082] Furthermore, in order to effectively prevent the video from being tampered with or forged, in an embodiment of the present application, watermark parsing is performed based on the target video data to obtain video release information, including:

[0083] Extracting watermarks based on target video data to obtain watermarks to be parsed, and parsing watermarks based on the watermarks to be parsed to obtain watermarks to be matched;

[0084] Based on the matching operation between the watermark to be matched and the watermark database, the video release information is determined, wherein the watermark database is a database storing all the watermark information embedded in the video, and the video release information includes: publisher information, release time, shooting time, and shooting location.

[0085] For the embodiment of the present application, the target video data is decoded by using a video codec library, and converted from a compressed format to an original frame sequence, the algorithm used when the watermark is embedded is obtained, and a corresponding extraction algorithm is selected to extract the watermark to be parsed from the video frame. The watermark extraction involves frequency domain analysis, spatial domain analysis, or other complex image processing. The watermark to be parsed is usually a binary sequence or a string. Then, according to the encoding method used when the watermark is embedded, a corresponding parsing algorithm is selected, and the watermark to be parsed is parsed according to the parsing algorithm to obtain a watermark to be matched, wherein the watermark to be matched is usually a string or a readable text format. Preferably, when performing watermark parsing, the parsed watermark information can be verified to ensure the integrity and correctness of the watermark information. If the verification fails, it indicates that the watermark has been erroneous or damaged during the extraction or parsing process. A watermark database is pre-set in the electronic device. The watermark database is a database that stores all watermark information embedded in the video. Therefore, the watermark to be matched is used as a query condition to search for watermark records matching it in the watermark database. In the process of searching and matching, a suitable matching algorithm can be selected according to the specific form of the watermark to be matched, that is, for simple strings or binary sequences, an exact matching algorithm can be used; for more complex watermark information, fuzzy matching or feature-based matching algorithms may need to be used. Preferably, in order to improve the matching efficiency, optimization measures such as indexing technology and caching mechanism can be used to improve the matching efficiency. Finally, the corresponding video release information is extracted based on the successfully matched watermark information, wherein the video release information includes: release person information, release time, shooting time, and shooting location. Through watermark extraction and matching, the copyright of the video can be verified. If the video is illegally disseminated or abused, the original release person and release time of the video can be traced back through the watermark information, and the video can be prevented from being tampered with or forged.

[0086] It can be seen that in the embodiment of the present application, watermark extraction is performed based on the target video data to obtain the watermark to be parsed, and watermark parsing is performed based on the watermark to be parsed to obtain the watermark to be matched. Then, a matching operation is performed based on the watermark to be matched and the watermark database to determine the video release information. Through watermark extraction and matching, the copyright ownership of the video can be verified. If the video is illegally disseminated or abused, the original publisher and release time of the video can be traced back through the watermark information, and the video can be effectively prevented from being tampered with or forged.

[0087] Further, in order to enhance the copyright protection of the video, in the embodiment of the present application, after performing watermark analysis based on the target video data and obtaining the video release information, the following steps are further included:

[0088] Obtaining transmission information of the target video, wherein the transmission information includes: playback carrier, sharing record, download record and forwarding record;

[0089] Perform propagation analysis based on transmission information to determine the propagation path, and visualize the propagation path by constructing a propagation graph, where nodes represent playback carriers and edges represent sharing, downloading, or forwarding behaviors;

[0090] The playback data of the target video at each node in the propagation graph is obtained, and propagation analysis is performed based on the playback data of each node to obtain a target propagation graph marked with key nodes.

[0091] For the embodiment of the present application, after obtaining the video release information, by constructing a propagation map and visually displaying the propagation path, it is possible to intuitively see the propagation of the target video between different playback carriers, which helps the video publisher to quickly trace the illegal dissemination of the video and enhance the copyright protection of the video.

[0092] Specifically, the transmission information of the target video is obtained, and the transmission information includes: playback carrier, sharing record, download record and forwarding record, wherein the playback carrier is used to characterize on which platforms, devices or applications the target video is played; the sharing record is the record of the target video being shared by the user, including but not limited to: sharing time, sharing source and sharing target; the download record includes but is not limited to: download time, download volume, etc.; the forwarding record includes but is not limited to: forwarding time, forwarder information, forwarding volume, etc. Then, the propagation analysis is performed based on the transmission information of the target video to determine the propagation path, that is, based on the sharing record, download record and forwarding record, the playback carrier that plays a key role in the propagation process of the target video is identified, and the propagation path is determined by tracking the propagation trajectory of the target video between different playback carriers. Then, a visualization tool is used to generate a propagation map, and interactive functions are added to the propagation map, such as zooming, dragging, and clicking nodes to view detailed information, etc., to improve the user experience. Obtain the propagation data of each node of the target video in the propagation graph, including but not limited to: number of views, viewing time, audience distribution, etc., and perform propagation analysis based on the playback data of each node to obtain a target propagation graph marked with key nodes, where key nodes are playback carriers with many views, long viewing time, and wide audience distribution. Of course, key nodes can also be nodes that occupy important positions in the propagation graph, such as bridge nodes (nodes connecting different propagation paths) and central nodes (nodes with high influence in the propagation graph). Finally, visually annotate the identified key nodes in the propagation graph, for example, use different colors, sizes, or shapes to represent key nodes, so as to obtain a target propagation graph marked with key nodes.

[0093] It can be seen that in the embodiment of the present application, the transmission information of the target video is obtained, the propagation analysis is performed based on the transmission information, the propagation path is determined, and the propagation path is visually displayed by constructing a propagation graph. Then, the propagation analysis is performed based on the playback data of each node to obtain a target propagation graph marked with key nodes. The target propagation graph helps video publishers to quickly trace the source of video theft and enhance the copyright protection of the video.

[0094] The above-mentioned embodiment introduces a method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks from the perspective of method flow. The following embodiment introduces a device for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks from the perspective of a virtual module or a virtual unit. Please refer to the following embodiments for details.

[0095] The embodiment of the present application provides a video secretly filmed or secretly recorded source tracing device based on digital watermark, such as Figure 2 As shown, the video secretly filmed or secretly recorded source tracing device based on digital watermark may specifically include:

[0096] The embedding strength analysis module 210 is used to obtain video characteristics of the video data, perform embedding strength analysis on the video data based on the video characteristics, and determine embedding strength information corresponding to the video data, wherein the video characteristics include: pixel variation and texture complexity;

[0097] The simulation perception module 220 is used to send the video data to the human visual system for simulation perception to determine the watermark embedding position;

[0098] The watermark embedding module 230 is used to obtain watermark information corresponding to the video data, and embed the watermark based on the watermark information, embedding strength information and watermark embedding position to obtain target video data carrying the watermark;

[0099] The video tracing module 240 is used to perform watermark analysis based on the target video data to obtain video release information to complete the video tracing operation when abnormal playback of the target video data is detected.

[0100] For the embodiment of the present application, the embedding strength analysis of the video data is performed based on the video characteristics to determine the embedding strength information corresponding to the video data. At the same time, the video data is sent to the human visual system for simulated perception to determine the watermark embedding position. Then, the watermark is embedded based on the watermark information, the embedding strength information and the watermark embedding position to obtain the target video data carrying the watermark. When abnormal playback of the target video data is detected, the watermark is parsed based on the target video data to obtain the video release information to complete the video tracing operation. The watermark embedding process takes into account the video characteristics of the video data and the selection of the embedding position, ensuring the robustness and concealment of the watermark information in the video data.

[0101] In a possible implementation of the embodiment of the present application, when the embedding strength analysis module 210 performs embedding strength analysis on video data based on video characteristics to determine embedding strength information corresponding to the video data, it is used to:

[0102] Based on the pixel changes and texture complexity in the video characteristics, the video data is divided into video regions to determine the high-frequency region and the low-frequency region;

[0103] Performing embedding strength analysis on the first video data corresponding to the high-frequency region to obtain a first embedding strength;

[0104] An embedding strength analysis is performed on the second video data corresponding to the low-frequency region to obtain a second embedding strength, wherein the embedding strength information is used to characterize a corresponding relationship between different video regions in the video data and corresponding embedding strengths.

[0105] In a possible implementation of the embodiment of the present application, when the simulation perception module 220 sends the video data to the human visual system for simulation perception and determines the watermark embedding position, it is used to:

[0106] Preprocessing the video data to obtain the video data to be simulated, wherein the preprocessing includes: color space conversion, noise reduction, and contrast enhancement;

[0107] The video data to be simulated is sent to the human visual system, and the human visual system is controlled to perform multi-dimensional simulation perception to determine the watermark embedding position, wherein the multi-dimensional simulation perception includes: frequency sensitivity simulation perception and brightness sensitivity simulation perception.

[0108] A possible implementation of the embodiment of the present application is a device for tracing the source of secretly photographed or secretly recorded video based on digital watermarks, further comprising:

[0109] The anomaly detection module is used to obtain video playback parameters during the target video playback process, and perform a first anomaly detection based on the video playback parameters to obtain a first anomaly detection result, wherein the video playback parameters include: video frame rate, resolution, and encoding quality;

[0110] Obtaining a video playback log, and performing a second anomaly detection based on the video playback log to obtain a second anomaly detection result, wherein the video playback log includes: playback time, playback position, and user behavior;

[0111] Using computer vision technology, perform video image analysis on the target video data to determine the third anomaly detection result;

[0112] The first abnormality detection result, the second abnormality detection result and the third abnormality detection result are combined to obtain the video playback status, wherein the video playback status includes: normal playback and abnormal playback.

[0113] In a possible implementation of the embodiment of the present application, when the video source tracing module 240 performs watermark parsing based on the target video data to obtain the video release information, it is used to:

[0114] Extracting watermarks based on target video data to obtain watermarks to be parsed, and parsing watermarks based on the watermarks to be parsed to obtain watermarks to be matched;

[0115] Based on the matching operation between the watermark to be matched and the watermark database, the video release information is determined, wherein the watermark database is a database storing all the watermark information embedded in the video, and the video release information includes: publisher information, release time, shooting time, and shooting location.

[0116] A possible implementation of the embodiment of the present application is a device for tracing the source of secretly photographed or secretly recorded video based on digital watermarks, further comprising:

[0117] A communication analysis module is used to obtain the transmission information of the target video, wherein the transmission information includes: playback carrier, sharing record, download record and forwarding record;

[0118] Perform propagation analysis based on transmission information to determine the propagation path, and visualize the propagation path by constructing a propagation graph, where nodes represent playback carriers and edges represent sharing, downloading, or forwarding behaviors;

[0119] The playback data of the target video at each node in the propagation graph is obtained, and propagation analysis is performed based on the playback data of each node to obtain a target propagation graph marked with key nodes.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the video tracing device based on digital watermark described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0121] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0122] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0123] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0124] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0125] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0126] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0127] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0128] An embodiment of the present application provides a computer program product, which includes a computer program, which implements a method as described in any of the above embodiments when executed by a processor. Compared with the related art, the embodiment of the present application performs an embedding strength analysis on the video data based on the video characteristics to determine the embedding strength information corresponding to the video data. At the same time, the video data is sent to the human visual system for simulated perception to determine the watermark embedding position. Then, a watermark is embedded based on the watermark information, the embedding strength information and the watermark embedding position to obtain the target video data carrying the watermark. When abnormal playback of the target video data is detected, the watermark is parsed based on the target video data to obtain the video release information to complete the video tracing operation. The watermark embedding process takes into account the video characteristics of the video data and the selection of the embedding position, ensuring the robustness and concealment of the watermark information in the video data.

[0129] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0130] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks, characterized in that: include: Acquire video characteristics of video data, perform embedding strength analysis on the video data based on the video characteristics, and determine embedding strength information corresponding to the video data, wherein the video characteristics include: pixel variation and texture complexity; Sending the video data to a human visual system for simulated perception to determine a watermark embedding position; Acquire watermark information corresponding to the video data, and embed the watermark based on the watermark information, the embedding strength information and the watermark embedding position to obtain target video data carrying the watermark; When it is detected that the target video data is abnormally played, watermark analysis is performed based on the target video data to obtain video release information to complete the video source tracing operation; The step of sending the video data to a human visual system for simulated perception and determining a watermark embedding position includes: Preprocessing the video data to obtain the video data to be simulated, wherein the preprocessing includes: color space conversion, noise reduction, and contrast enhancement; Sending the video data to be simulated to a human visual system, and controlling the human visual system to perform multi-dimensional simulation perception to determine a watermark embedding position, wherein the multi-dimensional simulation perception includes: frequency sensitivity simulation perception and brightness sensitivity simulation perception; The step of performing watermark analysis based on the target video data to obtain video publishing information includes: Extracting watermarks based on the target video data to obtain a watermark to be parsed, and parsing watermarks based on the watermark to be parsed to obtain a watermark to be matched; Based on the matching operation between the watermark to be matched and the watermark database, the video release information is determined, wherein the watermark database is a database storing all watermark information embedded in the video, and the video release information includes: information of the publisher, release time, shooting time, and shooting location; After performing watermark analysis based on the target video data to obtain video release information, the method further includes: Acquire transmission information of the target video, wherein the transmission information includes: playback carrier, sharing record, download record and forwarding record; Performing propagation analysis based on the transmission information to determine a propagation path, and visually displaying the propagation path by constructing a propagation graph, wherein nodes in the propagation graph represent playback carriers and edges represent sharing, downloading or forwarding behaviors; The playback data of the target video at each node in the propagation graph is obtained, and propagation analysis is performed based on the playback data of each node to obtain a target propagation graph marked with key nodes.

2. The method for tracing the source of secretly filmed or secretly recorded videos based on digital watermark according to claim 1 is characterized in that: The performing embedding strength analysis on the video data based on the video characteristics to determine embedding strength information corresponding to the video data includes: Based on the pixel change and the texture complexity in the video characteristics, the video data is divided into video regions to determine a high-frequency region and a low-frequency region; Performing embedding strength analysis on the first video data corresponding to the high-frequency area to obtain a first embedding strength; An embedding strength analysis is performed on the second video data corresponding to the low-frequency area to obtain a second embedding strength, wherein the embedding strength information is used to characterize a corresponding relationship between different video areas in the video data and corresponding embedding strengths.

3. The method for tracing the source of secretly filmed or secretly recorded videos based on digital watermark according to claim 1 is characterized in that: When it is detected that the target video data is abnormally played, watermark parsing is performed based on the target video data to obtain video release information to complete the video source tracing operation, including: During the target video playback process, video playback parameters are obtained, and a first abnormality detection is performed based on the video playback parameters to obtain a first abnormality detection result, wherein the video playback parameters include: video frame rate, resolution, and encoding quality; Obtaining a video playback log, and performing a second anomaly detection based on the video playback log to obtain a second anomaly detection result, wherein the video playback log includes: playback time, playback position, and user behavior; Using computer vision technology, performing video image analysis on the target video data to determine a third anomaly detection result; The first abnormality detection result, the second abnormality detection result and the third abnormality detection result are combined to obtain the video playback status, wherein the video playback status includes: normal playback and abnormal playback.

4. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the video secretly filmed or recorded secretly method based on digital watermark as described in any one of claims 1 to 3.

5. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks as described in any one of claims 1 to 3.

6. A computer program product, characterized in that The method comprises a computer program, wherein the computer program is executed by a processor to execute the method for tracing the source of secretly filmed or secretly recorded videos based on digital watermarks as described in any one of claims 1 to 3.

Images