Video coding method and device for privacy protection encryption, equipment and storage medium

Abstract

The invention discloses a privacy protection encryption video coding method and device, equipment and a storage medium, and relates to the technical field of video encryption coding, and the method comprises the steps: obtaining a monitoring video of a video collection equipment side for a target monitoring region, marking a region of interest in the monitoring video, converting the monitoring video into a video signal stream, and transmitting the video signal stream to a video server; the method comprises the following steps: cutting a video signal stream to obtain a general video signal stream and an interested video signal stream, performing two-dimensional mapping on the interested video signal stream to obtain a two-dimensional mapping coupling item of the interested video signal, performing component division on the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scrambling the plurality of coupling components to obtain a scrambled video signal stream; the method comprises the steps of obtaining a confused video signal stream, carrying out hybrid coding on the confused video signal stream and the general video signal stream according to an initial sequence to obtain a coded signal stream, realizing identification of privacy information in picture content in a monitoring video, carrying out encryption processing on the privacy information, and improving privacy data transmission security.

Description

Technical Field

[0001] The present application relates to the technical field of video encryption coding, and in particular to a privacy-preserving encrypted video coding method, apparatus, device and storage medium. Background Art

[0002] With the in-depth application of network communication, a large amount of data is exposed in the public network, which makes some private information leaked. Once the private information is leaked, both individuals and organizations will bear great risks. At present, the most common form of private information leakage is image information or video information leakage. Private information may be recorded during the shooting process. At present, the usual processing method for this problem is to encrypt the image or video information as a whole, such as encrypting the image or video information with a key, and transmitting it in the form of ciphertext during transmission. When the receiving end receives the ciphertext, it decodes it to obtain the plaintext, thereby ensuring the security of the data during transmission. However, the current privacy protection encryption method has the problems of long processing time and large ciphertext data packet size, which is not conducive to the rapid transmission of data. It also consumes a lot of computing power and reduces the transmission and processing efficiency of image or video information.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a privacy-preserving encrypted video encoding method, device, equipment and storage medium, aiming to solve the technical problem in the prior art that privacy information is easily leaked during video transmission.

[0005] To achieve the above object, the present application proposes a privacy-preserving encrypted video encoding method, which is applied to a video acquisition device side, and the privacy-preserving encrypted video encoding method includes: Acquire a monitoring video of the target monitoring area from the video acquisition device side, and mark the area of ​​interest in the monitoring video; Converting the monitoring video into a video signal stream, and cutting the video signal stream to obtain a general video signal stream and an interested video signal stream; Performing two-dimensional mapping on the video signal stream of interest to obtain a two-dimensional mapping coupling item of the video signal of interest; Segmenting the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scrambling the plurality of coupling components to obtain a chaotic video signal stream; The chaotic video signal stream and the general video signal stream are mixed and encoded in an original order to obtain an encoded signal stream.

[0006] In one embodiment, the step of obtaining a monitoring video of a target monitoring area from the video acquisition device and marking an area of ​​interest in the monitoring video includes: Acquire a monitoring video of a target monitoring area from the video acquisition device, perform edge detection on the monitoring video, and determine a plurality of scene partitions in the monitoring video; Performing content recognition on the scene partitions respectively to obtain content recognition results; Matching the content recognition result with a preset feature of interest to determine the similarity between the content recognition result and the preset region of interest; When the similarity is greater than an interest threshold, the content recognition result is marked as an interest region.

[0007] In one embodiment, the steps of converting the monitoring video into a video signal stream, cutting the video signal stream, and obtaining a general video signal stream and an interested video signal stream include: Convert the monitoring video into a video stream signal, perform frame-by-frame detection on the monitoring stream signal based on the timing sequence, and obtain a frame detection result and frame detection timing information; When the frame detection result is a marked frame, recording the position of the marked frame; Determine a marker signal stream according to the position of the marker frame, determine the start and end frame positions of the marker signal stream, and determine a first cutting point and a second cutting point of the video signal stream according to the start and end frame positions; Cutting the video signal stream into a plurality of general video signal stream segments and a plurality of interested video signal stream segments based on the first cutting point and the second cutting point; Based on the detection timing information, the plurality of general video signal stream segments and the plurality of interested video signal stream segments are respectively combined to obtain a general video signal stream and an interested video signal stream.

[0008] In one embodiment, the step of performing two-dimensional mapping on the video signal stream of interest to obtain a two-dimensional mapping coupling item of the video signal of interest comprises: Channel-separating the video signal stream of interest to obtain a plurality of non-overlapping video signal sub-streams of interest of preset sizes; respectively determining the frame sequence of the video signal substream of interest; Perform frame-by-frame two-dimensional mapping on the frame sequence to determine a two-dimensional mapping coupling item of the video signal of interest.

[0009] In one embodiment, the step of dividing the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scrambling the plurality of coupling components to obtain a chaotic video signal stream comprises: The two-dimensional mapping coupling item is divided into components based on the interested video signal substream of a preset size to obtain a plurality of coupling components; Determine a two-dimensional configuration of the coupling component, and determine a row component and a column component of the coupling component in the two-dimensional configuration; The row components and column components are scrambled according to a preset scrambling strategy, and the row components and column components are scrambled and shifted to obtain a scrambled video signal stream.

[0010] In one embodiment, after the step of scrambling the row components and the column components according to a preset scrambling strategy and scrambling and shifting the row components and the column components to obtain a scrambled video signal stream, the step further includes: Determine the start and end frame positions of the chaotic video signal stream, and determine the index position according to the start and end frame positions; generating an index code, and extracting an interference video stream from a data interference database based on the index code; Determine the start and end frame positions of the interference video stream, match the start and end frame positions of the interference video stream with the index position, use the interference video stream as an explicit chaotic video signal stream, use the chaotic video signal stream as an implicit chaotic video signal stream, and the explicit chaotic video signal stream corresponds to the implicit chaotic video signal stream.

[0011] In one embodiment, the step of mixing and encoding the chaotic video signal stream and the general video signal stream in an initial order to obtain the encoded signal stream comprises: Arranging the chaotic video signal stream and the general video signal stream in an initial order to obtain a video stream sequence to be encoded; Replacing the corresponding chaotic video signal stream in the to-be-encoded video stream sequence with an explicit chaotic video signal stream, converting the chaotic video signal stream into an implicit chaotic video signal stream, and determining a matching index based on the explicit chaotic video signal stream and the implicit chaotic video signal stream; The to-be-encoded video stream sequence and the matching index are mixed and encoded to obtain an encoded signal stream.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a privacy-preserving encrypted video encoding device, the privacy-preserving encrypted video encoding device comprising: An area locking module is used to obtain a monitoring video of a target monitoring area from the video acquisition device side and mark an area of ​​interest in the monitoring video; A video processing module, used for converting the monitoring video into a video signal stream, cutting the video signal stream to obtain a general video signal stream and an interested video signal stream; A signal mapping module, used for performing two-dimensional mapping on the video signal stream of interest to obtain a two-dimensional mapping coupling item of the video signal of interest; A component scrambling module, used for scrambling the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scrambling the plurality of coupling components to obtain a chaotic video signal stream; The signal encoding module is used to perform mixed encoding on the chaotic video signal stream and the general video signal stream in an initial order to obtain an encoded signal stream.

[0013] In addition, to achieve the above-mentioned objectives, the present application also proposes a privacy-preserving encrypted video encoding device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the privacy-preserving encrypted video encoding method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the privacy-preserving encrypted video encoding method as described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the privacy-preserving encrypted video encoding method as described above are implemented.

[0016] One or more technical solutions proposed in the present application have at least the following technical effects: obtaining a monitoring video of a target monitoring area from a video acquisition device, marking an area of ​​interest in the monitoring video, converting the monitoring video into a video signal stream, cutting the video signal stream to obtain a general video signal stream and an interested video signal stream, two-dimensionally mapping the interested video signal stream to obtain a two-dimensional mapped coupling item of the interested video signal, componentizing the two-dimensional mapped coupling item to obtain a plurality of coupled components, and scrambling the plurality of coupled components to obtain a chaotic video signal stream, mixing and encoding the chaotic video signal stream and the general video signal stream in an initial order to obtain a coded signal stream, realizing identification of privacy information in the picture content in the monitoring video, encrypting the privacy information, and improving the security of privacy data transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A flowchart of the first embodiment of the video encoding method for privacy protection encryption provided in this application; Figure 2 A schematic diagram of region marking provided for an embodiment of a video encoding method for privacy protection encryption of the present application; Figure 3 A flow chart of cutting a region of interest provided in accordance with an embodiment of a method for video encoding with privacy protection encryption of the present application; Figure 4 A schematic diagram of scrambled encryption movement rules provided in an embodiment of a privacy protection encrypted video encoding method of the present application; Figure 5 A signal flow replacement schematic diagram provided for an embodiment of a privacy protection encrypted video encoding method of the present application; Figure 6 A schematic diagram of the module structure of a privacy-preserving encrypted video encoding device according to an embodiment of the present application; Figure 7 A schematic diagram of the device structure of the hardware operating environment involved in the privacy-preserving encrypted video encoding method in an embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: obtain the monitoring video of the target monitoring area from the video acquisition device side, and mark the area of ​​interest in the monitoring video; convert the monitoring video into a video signal stream, cut the video signal stream to obtain a general video signal stream and an interested video signal stream; perform two-dimensional mapping on the interested video signal stream to obtain a two-dimensional mapped coupling item of the interested video signal; perform component division on the two-dimensional mapped coupling item to obtain multiple coupled components, and scramble the multiple coupled components to obtain a chaotic video signal stream; mix and encode the chaotic video signal stream and the general video signal stream in an initial order to obtain a coded signal stream.

[0024] In this embodiment, for ease of description, the following description is made by taking a video encoding device for identifying privacy-preserving encryption as the execution subject.

[0025] The conventional encryption processing method in the prior art is to encrypt the image or video information as a whole, such as encrypting the image or video information with a key, and transmitting it in the form of ciphertext during transmission. When the receiving end receives the ciphertext, it decodes it to obtain the plaintext, thereby ensuring the security of the data during transmission. However, the current privacy protection encryption method has the problems of long processing time and large ciphertext data packets, which is not conducive to the rapid transmission of data, and also consumes a lot of computing power, reducing the transmission and processing efficiency of image or video information.

[0026] The present application provides a solution that can encrypt the privacy information in the video information without increasing the data packet size too much. Compared with the privacy data protection method of the prior art, it has faster processability and facilitates data transmission and processing while ensuring privacy information.

[0027] It can be seen from the above embodiments that the present application obtains a monitoring video of a target monitoring area on the video acquisition device side, marks an area of ​​interest in the monitoring video, converts the monitoring video into a video signal stream, cuts the video signal stream to obtain a general video signal stream and an interested video signal stream, performs two-dimensional mapping on the interested video signal stream to obtain a two-dimensional mapping coupling item of the interested video signal, performs component analysis on the two-dimensional mapping coupling item to obtain a plurality of coupling components, scrambles the plurality of coupling components to obtain a chaotic video signal stream, mix-encodes the chaotic video signal stream and the general video signal stream in an initial order to obtain a coded signal stream, thereby realizing the identification of privacy information in the picture content in the monitoring video, encrypting the privacy information, and improving the security of privacy data transmission.

[0028] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a privacy-preserving encrypted video encoding device, etc. The following takes a privacy-preserving encrypted video encoding device as an example to illustrate this embodiment and the following embodiments.

[0029] Based on this, the embodiment of the present application provides a privacy-preserving encrypted video encoding method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the privacy protection encrypted video encoding method of the present application.

[0030] In this embodiment, the privacy-preserving encrypted video encoding method includes steps S10 to S40: Step S10: acquiring a monitoring video of a target monitoring area from the video acquisition device, and marking an area of ​​interest in the monitoring video.

[0031] It should be noted that the video acquisition device side refers to the device that obtains video information, which is the data sending end in the data transmission link. The video acquisition device can process the data to a certain extent before data transmission, such as encrypting and encoding the video information. The target detection area refers to the monitorable area of ​​the video acquisition device. The target detection area is determined by the installation conditions such as the installation position and installation angle of the video acquisition device; the monitoring video refers to the monitoring video of the target monitoring area collected by the video acquisition device during operation. The area of ​​interest refers to the video area in the target detection area where there is high privacy information.

[0032] In a specific implementation, the video acquisition device can perform video monitoring of the working environment according to the work arrangement. For each video acquisition device, it has a unique monitoring area, which is the target monitoring area of ​​the current video acquisition device. When the video acquisition device is working, it can generate monitoring videos in real time and identify the content of the monitoring videos. Specifically, the content in the content monitoring device can be classified, and tags can be added to the content according to the classification results. Based on the tags, it can be determined whether it is an area of ​​interest. Since there may be many similarities in content-based classification, in order to avoid misjudgment of privacy content, the area corresponding to the identified tag that meets the area of ​​interest can be determined as the area of ​​interest.

[0033] In a feasible implementation manner, the step of acquiring a monitoring video of a target monitoring area from the video acquisition device side and marking an area of ​​interest in the monitoring video includes: Acquire a monitoring video of a target monitoring area from the video acquisition device, perform edge detection on the monitoring video, and determine a plurality of scene partitions in the monitoring video; Performing content recognition on the scene partitions respectively to obtain content recognition results; Matching the content recognition result with a preset feature of interest to determine the similarity between the content recognition result and the preset region of interest; When the similarity is greater than an interest threshold, the content recognition result is marked as an interest region.

[0034] It should be noted that when processing the monitoring video, the monitoring video can be edge detected based on the screen content, and the monitoring video can be divided into multiple scene partitions, where at least one scene partition exists, that is, all the content in the current monitoring area is private content. Similarity refers to the degree of similarity between the preset interest areas of the scene partition, and the preset interest area is a collection of privacy information determined based on historical experience.

[0035] In a specific implementation, after obtaining the monitoring video of the target monitoring area on the video acquisition device side, the monitoring video can be preprocessed, the monitoring video can be grayed, and edge detection can be performed on the monitoring video. The scene in the monitoring video can be identified. When performing edge detection, the Sobel operator can be used to perform coarse edge detection, and the edge can be detected according to the spatial gradient of the brightness of the image. The edge detection formula is: ,

[0036] The magnitude of the gradient is:

[0037] The direction of the gradient is:

[0038] in, and is the gradient of the image in the x and y directions, is the magnitude of the gradient, is the direction of the gradient.

[0039] After edge detection, you can select the edge and the identified detection result. Figure 2 As shown, Figure 2The figure is a schematic diagram of region marking. Each marked region can be regarded as a scene partition, and then the scene partition is subjected to content recognition to obtain the content recognition result, the subject information in the seven-degree malignant scene partition, and the subject information is categorized. Then the content recognition result is matched with the preset feature of interest to determine the similarity between the content recognition result and the preset feature of interest. When the similarity is greater than the threshold of interest, the content recognition result can be marked as a region of interest (ROI).

[0040] Step S20: convert the monitoring video into a video signal stream, and cut the video signal stream to obtain a general video signal stream and an interested video signal stream.

[0041] It should be noted that the video signal stream refers to a temporally continuous sequence of images that constitutes a dynamic image on a one-dimensional time axis. The video signal stream of interest is an image sequence corresponding to the image sequence of the area of ​​interest on the time axis. The general video signal stream is an image sequence other than the video signal stream of interest.

[0042] In a specific implementation, the monitoring video is converted into a video signal stream, and the video signal stream is cut to cut the monitoring video into two types of signal streams, namely a general video signal stream and an interested video signal stream. The specific implementation method is: convert the monitoring video into a video stream signal, perform frame-by-frame detection on the monitoring stream signal based on timing, and obtain a frame detection result and frame detection timing information; when the frame detection result is a marked frame, record the position of the marked frame; determine the marked signal stream according to the position of the marked frame, determine the start and end frame positions of the marked signal stream, and determine the first cutting point and the second cutting point of the video signal stream according to the start and end frame positions; cut the video signal stream into multiple general video signal stream segments and multiple interested video signal stream segments based on the first cutting point and the second cutting point; combine multiple general video signal stream segments and multiple interested video signal stream segments based on the detection timing information to obtain a general video signal stream and an interested video signal stream.

[0043] Reference Figure 3 , Figure 3The flowchart for cutting the region of interest. First, the image of the region of interest in the signal stream of the monitoring video can be channel-separated, and separated according to the Y channel, Cb channel, and Cr channel to obtain multiple image blocks, and each block is subjected to DCT transformation to obtain a general video signal stream and a video signal stream of interest. When segmenting, frame-by-frame detection can be performed according to the timing information to determine the frame detection results and detection timing information obtained when performing frame detection. The frame detection results include marked frames and unmarked frames. The marked frames correspond to the region of interest. When the marked frames are obtained, the position of the current marked frame can be recorded, and the marked signal stream is located with the position of the marked frame, and the start and end frame positions of the marked signal stream are determined, indicating the start frame position and the end frame position of the marked signal stream, and the start and end frame positions are used as cutting points. The start frame position corresponds to the first cutting point, and the end frame position is the second cutting point. Therefore, based on the first cutting point and the second cutting point, the video signal stream is cut into multiple general video signal stream segments and multiple video signal stream segments of interest. Based on the detection timing information, the plurality of general video signal stream segments and the plurality of interested video signal stream segments are respectively combined to obtain a general video signal stream and an interested video signal stream.

[0044] Step S30: Perform two-dimensional mapping on the video signal stream of interest to obtain a two-dimensional mapping coupling item of the video signal of interest.

[0045] It should be noted that the two-dimensional mapping coupling term refers to mapping the video signal stream of interest from the time sequence to the time-space dimension to form a two-dimensional mapping of time and space. In the video signal, the time dimension represents the frame sequence, while the space dimension represents the pixel position within a single frame. By mapping the video signal to the time-space plane, motion information, scene changes, etc. in the video content can be analyzed.

[0046] In a specific implementation, the step of performing two-dimensional mapping on the video signal stream of interest to obtain the two-dimensional mapping coupling items of the video signal of interest includes: performing channel separation on the video signal stream of interest to obtain multiple non-overlapping substreams of the video signal of interest of preset size; determining the frame sequence of the substream of interest for each substream of the video signal of interest; performing frame-by-frame two-dimensional mapping on the frame sequence to determine the two-dimensional mapping coupling items of the video signal of interest. Specifically, the chaotic system is combined with the region of interest for encryption, and due to the unpredictability of the pseudo-random sequence generated by the chaotic system, a good encryption system can be formed. When performing two-dimensional mapping, a two-dimensional Logistic mapping can be used, and the two-dimensional Logistic dynamics equation is:

[0047] in, and is the coupling term, where and The first coupling term of .

[0048] The two-dimensional Logistic mapping equation is:

[0049] in, These are the control parameters of the system, usually , It is the initial value of the system, which will affect the output result.

[0050] Step S40: Component the two-dimensional mapped coupling item to obtain a plurality of coupling components, and scramble the plurality of coupling components to obtain a chaotic video signal stream.

[0051] It should be noted that the chaotic video signal stream refers to the video signal stream obtained after scrambling the signal stream of the region of interest, and the frame data in the chaotic video signal stream is disrupted, so that the arranged frame data does not have the privacy data represented by the original frame data.

[0052] In a specific implementation, there is a large correlation between different image blocks. Therefore, in order to process the privacy data of the area of ​​interest, it is necessary to scramble the position of the image blocks, and divide the two-dimensional mapping coupling items into components based on the video signal substream of interest of a preset size to obtain multiple coupling components; determine the two-dimensional configuration of the coupling components, and determine the row components and column components of the coupling components in the two-dimensional configuration; scramble the row components and column components according to the preset scrambling strategy, scramble the row components and column components, and obtain a chaotic video signal stream. For example, the two-dimensional mapping coupling image is based on a preset 8×8 image block, and each row and column block is cyclically shifted to the right and downward respectively, and the generated chaotic sequence is used to control the shift rounds, and multiple rounds of shifts are performed to achieve the purpose of encrypting the image block position. Assume that the width and height of the image to be encrypted are respectively and , then the number of rows after block division is , the number of rows after block division is , the chaotic sequences generated according to the key are recorded as and Since the chaotic sequence value is not an integer that meets the requirements, it is necessary to amplify the sequence value and then take the remainder. The moving distance of the row and column elements is:

[0053]

[0054] in, , , Indicates The distance the row moves to the right, The value range is , Indicates The distance the column is moved down, The value range is The mobile rules of scrambled encryption are based on The value of The entire row is moved to the right by a corresponding distance. When it moves to the last digit, it moves the last digit to the first digit of the row. Column, move this column down When moving to the last position, move the last position to the first position in the column. After several rounds of alternating moves, the image block position can be effectively encrypted. Figure 4 , Figure 4 This is a schematic diagram of the scrambled encryption movement rules. Figure 4 (a) is an 8×8 image block. The block movement at Figure 4 (b) is an 8×8 image block. Based on this scrambling method, the signal frames in the video stream in the area of ​​interest can be disrupted to obtain a chaotic video signal stream.

[0055] In a feasible implementation manner, after the step of scrambling the row components and the column components according to a preset scrambling strategy and scrambling and shifting the row components and the column components to obtain a scrambled video signal stream, the step further includes: Determine the start and end frame positions of the chaotic video signal stream, and determine the index position according to the start and end frame positions; generating an index code, and extracting an interference video stream from a data interference database based on the index code; Determine the start and end frame positions of the interference video stream, match the start and end frame positions of the interference video stream with the index position, use the interference video stream as an explicit chaotic video signal stream, use the chaotic video signal stream as an implicit chaotic video signal stream, and the explicit chaotic video signal stream corresponds to the implicit chaotic video signal stream.

[0056] It should be noted that the explicit chaotic video signal stream and the implicit chaotic video signal stream are video signal streams with the same frame length. The explicit chaotic video signal stream will replace the video signal stream of the region of interest for encoding and transmission, while the implicit chaotic video signal stream is the chaotic video signal stream after scrambling processing.

[0057] In a specific implementation, the start and end frame positions of the chaotic video signal stream can be determined, and the index position can be determined according to the start and end frame positions. The index position can determine the replacement position of the signal stream, and an index code is generated according to the index position. The interference video stream is extracted from the data interference database based on the index code. The data interference database stores preset interference videos, such as mosaics, stickers and other interference video streams. Figure 5 , Figure 5 The figure is a schematic diagram of signal stream replacement. The black area represents the explicit chaotic video signal stream, the gray area represents the implicit chaotic video signal stream, and the white area is the general video signal stream. When performing signal stream replacement, the original chaotic video signal stream can be determined as the implicit chaotic video signal stream, and then an explicit chaotic video signal stream with the same start and end frames replaces the original chaotic video signal stream position, that is, the original video signal stream is changed with an unrelated video signal stream, so the privacy and security of the data can be guaranteed. At the same time, in order to transmit the data, based on the index code and index position, the part of the content can be carried in the transmitted video signal stream. Since it is chaotic, the position of the frame sequence is not in the original position during data transmission, so the final video image is also chaotic.

[0058] Step S50: Mix and encode the chaotic video signal stream and the general video signal stream in an initial order to obtain an encoded signal stream.

[0059] It should be noted that the coded signal stream refers to a video signal stream that can be transmitted over a network and is obtained after a series of processing is performed on the monitoring video and the privacy data in the monitoring video is encrypted.

[0060] In a specific implementation, the chaotic video signal stream and the general video signal stream are arranged in an initial order to obtain a video stream sequence to be encoded; the corresponding chaotic video signal stream in the video stream sequence to be encoded is replaced with an explicit chaotic video signal stream, the chaotic video signal stream is converted into an implicit video signal stream, and a matching index is determined based on the explicit chaotic video signal stream and the implicit video signal stream; the video stream sequence to be encoded and the matching index are mixed and encoded to obtain a coded signal stream. Specifically, the chaotic video signal stream and the general video signal stream are arranged in an initial order, and the basis of the arrangement is the timing information of the frame data to obtain a video stream sequence to be encoded. When encoding, the chaotic video signal stream contained in the video signal stream to be encoded can be replaced with an explicit chaotic video signal stream. The explicit chaotic video signal stream and the chaotic video signal stream have no content association, so the privacy and security of the data can be protected. On the other hand, the chaotic video signal stream is converted into an implicit video signal stream, and the encrypted data is co-encoded with the original coded video, which can cause huge interference to the direct hard decoding of the data and seriously distort the original video content information. In order to facilitate subsequent decoding operations, a matching index can be determined based on an explicit chaotic video signal stream and an implicit video signal stream; when encoding, the video stream sequence to be encoded can be directly mixed and encoded with the matching index to obtain a coded signal stream. This encoding method, on the one hand, directly changes the size of the entire video data through the redundancy of a certain amount of data, and changes the content of the video from the source. On the other hand, since the privacy data to be protected is replaced with other data, the privacy data is encrypted in a chaotic manner, and encoded together with the data to be encoded, the possibility of the privacy data being cracked can also be reduced. In addition, the video signal stream obtained by this encoding method, if the data other than non-privacy data is publicly available, can be transmitted in plain text to a certain extent, which greatly reduces the process of encrypting non-essential data during data transmission. Therefore, the privacy-preserving encrypted video encoding proposed in this embodiment can take into account the characteristics of privacy data protection and efficient data processing.

[0061] The present embodiment provides a privacy-preserving encrypted video encoding method, which obtains a monitoring video of a target monitoring area from a video acquisition device side, marks an area of ​​interest in the monitoring video, converts the monitoring video into a video signal stream, cuts the video signal stream to obtain a general video signal stream and an interested video signal stream, performs two-dimensional mapping on the interested video signal stream to obtain a two-dimensional mapped coupling item of the interested video signal, performs component analysis on the two-dimensional mapped coupling item to obtain multiple coupled components, scrambles the multiple coupled components to obtain a chaotic video signal stream, mixes and encodes the chaotic video signal stream and the general video signal stream in an initial order to obtain a coded signal stream, thereby identifying privacy information in the picture content in the monitoring video, encrypting the privacy information, and improving the security of privacy data transmission.

[0062] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the privacy-preserving encrypted video encoding method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0063] This application also provides a privacy-preserving encrypted video encoding device, please refer to Figure 6 , the privacy-preserving encrypted video encoding device comprises: The area locking module 10 is used to obtain the monitoring video of the target monitoring area from the video acquisition device side and mark the area of ​​interest in the monitoring video; The video processing module 20 is used to convert the monitoring video into a video signal stream, and cut the video signal stream to obtain a general video signal stream and an interested video signal stream; A signal mapping module 30, configured to perform two-dimensional mapping on the video signal stream of interest to obtain a two-dimensional mapping coupling item of the video signal of interest; A component scrambling module 40 is used to scramble the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scramble the plurality of coupling components to obtain a scrambled video signal stream; The signal encoding module 50 is used to perform mixed encoding on the chaotic video signal stream and the general video signal stream in an initial order to obtain an encoded signal stream.

[0064] In one embodiment, the area locking module 10 is also used to obtain a monitoring video of the target monitoring area from the video acquisition device side, perform edge detection on the monitoring video, and determine multiple scene partitions in the monitoring video; perform content recognition on the scene partitions respectively to obtain content recognition results; match the content recognition results with preset features of interest to determine the similarity between the content recognition results and the preset area of ​​interest; when the similarity is greater than a threshold of interest, mark the content recognition result as an area of ​​interest.

[0065] In one embodiment, the video processing module 20 is also used to convert the monitoring video into a video stream signal, perform frame-by-frame detection on the monitoring stream signal based on timing, and obtain a frame detection result and frame detection timing information; when the frame detection result is a marked frame, record the position of the marked frame; determine the marked signal stream according to the position of the marked frame, determine the start and end frame positions of the marked signal stream, and determine the first cutting point and the second cutting point of the video signal stream according to the start and end frame positions; cut the video signal stream into multiple general video signal stream segments and multiple interested video signal stream segments based on the first cutting point and the second cutting point; and combine the multiple general video signal stream segments and the multiple interested video signal stream segments based on the detection timing information to obtain a general video signal stream and an interested video signal stream.

[0066] In one embodiment, the signal mapping module 30 is further used to perform channel separation on the video signal stream of interest to obtain multiple non-overlapping video signal sub-streams of interest of preset sizes; respectively determine the frame sequence of the video signal sub-stream of interest; perform frame-by-frame two-dimensional mapping on the frame sequence to determine the two-dimensional mapping coupling items of the video signal of interest.

[0067] In one embodiment, the component scrambling module 40 is further used to divide the two-dimensional mapping coupling item into components based on a video signal substream of interest of a preset size to obtain multiple coupling components; determine the two-dimensional configuration of the coupling components, and determine the row components and column components of the coupling components in the two-dimensional configuration; scramble the row components and column components according to a preset scrambling strategy, scramble and shift the row components and column components to obtain a chaotic video signal stream.

[0068] In one embodiment, the component scrambling module 40 is also used to determine the start and end frame positions of the chaotic video signal stream, determine the index position according to the start and end frame positions; generate an index code, and extract the interference video stream from the data interference database based on the index code; determine the start and end frame positions of the interference video stream, match the start and end frame positions of the interference video stream with the index position, use the interference video stream as an explicit chaotic video signal stream, and use the chaotic video signal stream as an implicit chaotic video signal stream, and the explicit chaotic video signal stream and the implicit chaotic video signal stream are in a corresponding relationship.

[0069] In one embodiment, the signal encoding module 50 is further used to arrange the chaotic video signal stream and the general video signal stream in an initial order to obtain a video stream sequence to be encoded; replace the corresponding chaotic video signal stream in the video stream sequence to be encoded with an explicit chaotic video signal stream, convert the chaotic video signal stream into an implicit chaotic video signal stream, and determine a matching index based on the explicit chaotic video signal stream and the implicit chaotic video signal stream; and perform mixed encoding on the video stream sequence to be encoded and the matching index to obtain a coded signal stream.

[0070] The privacy-preserving encrypted video encoding device provided by the present application adopts the privacy-preserving encrypted video encoding method in the above embodiment, which can solve the technical problem in the prior art that private information is easily leaked during video transmission. Compared with the prior art, the beneficial effects of the privacy-preserving encrypted video encoding device provided by the present application are the same as the beneficial effects of the privacy-preserving encrypted video encoding method provided by the above embodiment, and other technical features in the privacy-preserving encrypted video encoding device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0071] The present application provides a privacy-preserving encrypted video encoding device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the privacy-preserving encrypted video encoding method in the above-mentioned embodiment one.

[0072] Reference below Figure 7 , which shows a schematic diagram of the structure of a privacy-preserving encrypted video encoding device suitable for implementing the embodiment of the present application. The privacy-preserving encrypted video encoding device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The privacy-preserving encrypted video encoding 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.

[0073] like Figure 7As shown, the privacy-preserving encrypted video encoding device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the privacy-preserving encrypted video encoding device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the privacy-preserving encrypted video encoding device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a privacy-preserving encrypted video encoding device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0074] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0075] The privacy-preserving encrypted video encoding device provided by the present application adopts the privacy-preserving encrypted video encoding method in the above embodiment, which can solve the technical problem in the prior art that private information is easily leaked during video transmission. Compared with the prior art, the beneficial effects of the privacy-preserving encrypted video encoding device provided by the present application are the same as the beneficial effects of the privacy-preserving encrypted video encoding method provided by the above embodiment, and other technical features in the privacy-preserving encrypted video encoding device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0076] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0077] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0078] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the privacy-preserving encrypted video encoding method in the above-mentioned embodiment.

[0079] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0080] The computer-readable storage medium may be included in the privacy-preserving encrypted video encoding device; or may exist independently without being assembled into the privacy-preserving encrypted video encoding device.

[0081] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the privacy-preserving encrypted video encoding device, the privacy-preserving encrypted video encoding device: Acquire a monitoring video of the target monitoring area from the video acquisition device side, and mark the area of ​​interest in the monitoring video; Converting the monitoring video into a video signal stream, and cutting the video signal stream to obtain a general video signal stream and an interested video signal stream; Performing two-dimensional mapping on the video signal stream of interest to obtain a two-dimensional mapping coupling item of the video signal of interest; Segmenting the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scrambling the plurality of coupling components to obtain a chaotic video signal stream; The chaotic video signal stream and the general video signal stream are mixed and encoded in an original order to obtain an encoded signal stream.

[0082] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0083] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0084] The modules involved in the embodiments of the present application may be implemented by software or hardware, wherein the name of the module does not limit the unit itself in some cases.

[0085] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned privacy-preserving encrypted video encoding method, and can solve the technical problem in the prior art that privacy information is easily leaked during video transmission. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the privacy-preserving encrypted video encoding method provided by the above-mentioned embodiment, and are not described in detail here.

[0086] The present application also provides a computer program product, including a computer program, which implements the steps of the privacy-preserving encrypted video encoding method as described above when the computer program is executed by a processor.

[0087] The computer program product provided by the present application can solve the technical problem in the prior art that privacy information is easily leaked during video transmission. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the privacy-preserving encrypted video encoding method provided by the above embodiment, which will not be described in detail here.

[0088] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A privacy-preserving encrypted video encoding method, characterized in that: The privacy-preserving encrypted video encoding method is applied to the video acquisition device side, and the privacy-preserving encrypted video encoding method includes: Acquire a monitoring video of the target monitoring area from the video acquisition device side, and mark the area of ​​interest in the monitoring video; Converting the monitoring video into a video signal stream, and cutting the video signal stream to obtain a general video signal stream and an interested video signal stream; Performing two-dimensional mapping on the video signal stream of interest to obtain a two-dimensional mapping coupling item of the video signal of interest; Segmenting the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scrambling the plurality of coupling components to obtain a chaotic video signal stream; The chaotic video signal stream and the general video signal stream are mixed and encoded in an original order to obtain an encoded signal stream.

2. The method according to claim 1, characterized in that The step of obtaining a monitoring video of the target monitoring area from the video acquisition device side and marking the area of ​​interest in the monitoring video comprises: Acquire a monitoring video of a target monitoring area from the video acquisition device, perform edge detection on the monitoring video, and determine a plurality of scene partitions in the monitoring video; Performing content recognition on the scene partitions respectively to obtain content recognition results; Matching the content recognition result with a preset feature of interest to determine the similarity between the content recognition result and the preset region of interest; When the similarity is greater than an interest threshold, the content recognition result is marked as an interest region.

3. The method according to claim 1, characterized in that The steps of converting the monitoring video into a video signal stream, cutting the video signal stream, and obtaining a general video signal stream and an interested video signal stream include: Convert the monitoring video into a video stream signal, perform frame-by-frame detection on the monitoring stream signal based on the timing sequence, and obtain a frame detection result and frame detection timing information; When the frame detection result is a marked frame, recording the position of the marked frame; Determine a marker signal stream according to the position of the marker frame, determine the start and end frame positions of the marker signal stream, and determine a first cutting point and a second cutting point of the video signal stream according to the start and end frame positions; Cutting the video signal stream into a plurality of general video signal stream segments and a plurality of interested video signal stream segments based on the first cutting point and the second cutting point; Based on the detection timing information, the plurality of general video signal stream segments and the plurality of interested video signal stream segments are respectively combined to obtain a general video signal stream and an interested video signal stream.

4. The method according to claim 1, characterized in that The step of performing two-dimensional mapping on the video signal stream of interest to obtain the two-dimensional mapping coupling item of the video signal of interest comprises: Channel-separating the video signal stream of interest to obtain a plurality of non-overlapping video signal sub-streams of interest of preset sizes; respectively determining the frame sequence of the video signal substream of interest; Perform frame-by-frame two-dimensional mapping on the frame sequence to determine a two-dimensional mapping coupling item of the video signal of interest.

5. The method according to claim 1, characterized in that The step of dividing the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scrambling the plurality of coupling components to obtain a chaotic video signal stream comprises: The two-dimensional mapping coupling item is divided into components based on the interested video signal substream of a preset size to obtain a plurality of coupling components; Determine a two-dimensional configuration of the coupling component, and determine a row component and a column component of the coupling component in the two-dimensional configuration; The row components and column components are scrambled according to a preset scrambling strategy, and the row components and column components are scrambled and shifted to obtain a scrambled video signal stream.

6. The method according to claim 5, characterized in that After the step of scrambling the row components and the column components according to a preset scrambling strategy and scrambling and shifting the row components and the column components to obtain a scrambled video signal stream, the method further includes: Determine the start and end frame positions of the chaotic video signal stream, and determine the index position according to the start and end frame positions; generating an index code, and extracting an interference video stream from a data interference database based on the index code; Determine the start and end frame positions of the interference video stream, match the start and end frame positions of the interference video stream with the index position, use the interference video stream as an explicit chaotic video signal stream, use the chaotic video signal stream as an implicit chaotic video signal stream, and the explicit chaotic video signal stream corresponds to the implicit chaotic video signal stream.

7. The method according to claim 1, characterized in that The step of mixing and encoding the chaotic video signal stream and the general video signal stream in an initial order to obtain the encoded signal stream comprises: Arranging the chaotic video signal stream and the general video signal stream in an initial order to obtain a video stream sequence to be encoded; Replacing the corresponding chaotic video signal stream in the to-be-encoded video stream sequence with an explicit chaotic video signal stream, converting the chaotic video signal stream into an implicit chaotic video signal stream, and determining a matching index based on the explicit chaotic video signal stream and the implicit chaotic video signal stream; The to-be-encoded video stream sequence and the matching index are mixed and encoded to obtain an encoded signal stream.

8. A privacy-preserving encrypted video encoding device, characterized in that: The device comprises: An area locking module is used to obtain a monitoring video of a target monitoring area from the video acquisition device side and mark an area of ​​interest in the monitoring video; A video processing module, used for converting the monitoring video into a video signal stream, cutting the video signal stream to obtain a general video signal stream and an interested video signal stream; A signal mapping module, used for performing two-dimensional mapping on the video signal stream of interest to obtain a two-dimensional mapping coupling item of the video signal of interest; A component scrambling module, used for scrambling the two-dimensional mapping coupling item to obtain a plurality of coupling components, and scrambling the plurality of coupling components to obtain a chaotic video signal stream; The signal encoding module is used to perform mixed encoding on the chaotic video signal stream and the general video signal stream in an initial order to obtain an encoded signal stream.

9. A privacy-preserving encrypted video encoding device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the privacy-preserving encrypted video encoding method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the privacy-preserving encrypted video encoding method according to any one of claims 1 to 7 are implemented.

Images