Video sensitive information processing method, apparatus, device, and medium

Abstract

A video sensitive information processing method, device, equipment and medium are disclosed, which comprises: first, acquiring a first target picture, identifying a to-be-desensitized area in the first target picture, and replacing low-bit data at a first target pixel in the to-be-desensitized area with high-bit data. Then, the high-bit data at the first target pixel is subjected to irreversible desensitization processing to obtain a processed desensitized video. That is, the present application can both hide effective information and achieve security, and subsequent restoration can be performed using the hidden effective information. At the same time, since the effective information is directly hidden in the processed image, there is no need to store a large and complex amount of data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular, to a video sensitive information processing method, device, equipment and medium. BACKGROUND

[0002] According to market demand and regulatory requirements, some video recording devices must eliminate sensitive information in the video. The sensitive information includes but is not limited to: face, license plate, confidential facility, etc.

[0003] The conventional sensitive information elimination method includes locating and identifying the sensitive information in the video through a target recognition algorithm, and then eliminating the sensitive information through related shielding processing, such as mosaic, color filling, etc. However, if there is a subsequent video restoration requirement, this method still needs to backup the sensitive information of the original video. For example, if there are thirty faces in one frame of video, the thirty image blocks need to be backed up. Since the video contains many frames, and the sensitive information in the video is constantly changing, it can be intuitively understood that the amount of additional stored data is very large and complex. SUMMARY

[0004] Therefore, it is necessary to provide a video sensitive information processing method, device, equipment and medium to solve the problem of large and complex additional storage data in the prior art.

[0005] A video sensitive information processing method, the method comprising:

[0006] obtaining a first target picture, identifying a desensitization area in the first target picture, and replacing low-bit data at a first target pixel in the desensitization area with high-bit data; wherein the first target picture is any one frame in a video to be desensitized, the first target pixel is any one pixel in the desensitization area, the low-bit data is binary data of a preset number of bits in a preset low-bit area in a byte used to store color data at the target pixel, and the change of the binary data in the preset low-bit area will not cause a visual difference in human eyes, and the high-bit data is binary data of a preset number of bits in a preset high-bit area in a byte used to store color data at the target pixel, and the change of the binary data in the preset high-bit area will cause a visual difference in human eyes;

[0007] irreversibly desensitizing the high-bit data at the first target pixel to obtain a desensitized video after processing.

[0008] In one embodiment, after obtaining the desensitized video after processing, the method further comprises:

[0009] identify a region to be restored in the second target picture, and replace high-bit data at a second target pixel in the region to be restored with low-bit data to obtain a processed restored video; wherein the second target picture is any one frame in the desensitized video, and the second target pixel is any one pixel in the region to be restored.

[0010] In one of the embodiments, the method further comprises:

[0011] In the first target picture, pixels in a region to be desensitized are marked;

[0012] The identifying the region to be restored in the second target picture comprises:

[0013] In the second target picture, a region covered by the pixels carrying the mark is identified as the region to be restored.

[0014] In one of the embodiments, the method further comprises:

[0015] In the preset high-bit region, binary data of a preset number of bits at a first preset position is used as high-bit data, and in the preset low-bit region, binary data of a preset number of bits at a second preset position is used as low-bit data; wherein the preset number of bits is less than or equal to the number of bits of binary data in the preset high-bit region and the preset low-bit region.

[0016] In one of the embodiments, the irreversibly desensitizing the high-bit data at the first target pixel comprises:

[0017] The high-bit data at the first target pixel is filled with a preset value.

[0018] In one of the embodiments, the irreversibly desensitizing the high-bit data at the first target pixel comprises:

[0019] A plurality of first target pixels are set as an array, and the high-bit data between different pixels in the array are exchanged.

[0020] In one of the embodiments, the irreversibly desensitizing the high-bit data at the first target pixel comprises:

[0021] A plurality of first target pixels are set as an array, and the average of all high-bit data in the array is calculated, and the average is used to replace the high-bit data of all pixels in the array.

[0022] A video sensitive information processing device, the device comprises:

[0023] The sensitive information backup module is configured to acquire a first target picture, identify a to-be-desensitized region in the first target picture, and replace low-bit data at a first target pixel in the to-be-desensitized region with high-bit data; wherein the first target picture is any frame in a to-be-desensitized video, the first target pixel is any pixel in the to-be-desensitized region, the low-bit data is binary data of a preset number of bits in a preset low-bit region in a byte used to store color information at the target pixel, and a change in the binary data in the preset low-bit region does not cause a visual difference in human eyes, and the high-bit data is binary data of a preset number of bits in a preset high-bit region in the byte used to store color information at the target pixel, and a change in the binary data in the preset high-bit region causes a visual difference in human eyes;

[0024] The sensitive information hiding module is configured to perform irreversible desensitization processing on the high-bit data at the first target pixel, and acquire a processed desensitized video.

[0025] A computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, causes the processor to perform the steps of the video sensitive information processing method.

[0026] A video sensitive information processing device includes a memory and a processor, and the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to perform the steps of the video sensitive information processing method.

[0027] The present application provides a video sensitive information processing method, device, equipment and medium, first acquire a first target picture, identify the to-be-desensitized region in the first target picture, and replace the low-bit data at the first target pixel in the to-be-desensitized region with high-bit data. Wherein, the change of the binary data in the preset high-bit region will cause the visual difference in human eyes, which can be understood as the main effective information of the image, and this part of information will change the image content obviously once it changes. And the change of the binary data in the preset low-bit region will not cause the visual difference in human eyes, and the sensitive information in the image can be effectively backed up by replacing the low-bit data at the first target pixel in the to-be-desensitized region with high-bit data. Then, the high-bit data at the first target pixel is desensitized irreversibly, and a processed desensitized video is acquired. In this way, all sensitive information can be hidden, and the purpose of "eliminating" sensitive information with naked eyes is achieved, thereby ensuring that sensitive information will not be easily leaked. That is, the present application can hide effective information and achieve security, and subsequent restoration can be performed using the hidden effective information. At the same time, since the effective information is directly hidden in the processed image, it is not necessary to store a large and complex amount of data. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0029] Wherein:

[0030] Figure 1 It is a flowchart of the video sensitive information processing method in the first embodiment;

[0031] Figure 2 It is a schematic diagram of determining the preset high bit area and the preset low bit area in an embodiment;

[0032] Figure 3 It is a schematic diagram of the first embodiment before data replacement;

[0033] Figure 4 It is a schematic diagram of the first embodiment of data replacement;

[0034] Figure 5 It is a schematic diagram of the second embodiment before data replacement;

[0035] Figure 6 It is a schematic diagram of the second embodiment of data replacement;

[0036] Figure 7 It is a flowchart of the video sensitive information processing method in the second embodiment;

[0037] Figure 8 It is a schematic diagram of the first embodiment of desensitization processing;

[0038] Figure 9 It is a schematic diagram of the first embodiment of data restoration;

[0039] Figure 10 It is a structural schematic diagram of the video sensitive information processing device in an embodiment;

[0040] Figure 11 It is a structural block diagram of the video sensitive information processing device in an embodiment. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0042] As shown in Figure 1 , Figure 1 is a flowchart of the video sensitive information processing method in the first embodiment. The video sensitive information processing method provides the following steps:

[0043] In step 102, a first target picture is obtained, a to-be-desensitized area in the first target picture is identified, and low-bit data at a first target pixel in the to-be-desensitized area is replaced with high-bit data.

[0044] Specifically, a to-be-desensitized video is first obtained. The method of obtaining the to-be-desensitized video is not specifically limited in this embodiment, and can be obtained by real-time shooting or from a storage. It can be obtained by shooting through a mobile terminal such as a mobile phone, or can be obtained by shooting through a non-mobile terminal such as a desktop computer.

[0045] After obtaining the to-be-desensitized video, any frame in the to-be-desensitized video is obtained as the first target picture in this step. In the first target picture, all sensitive information (such as face / vehicle license plate / confidential facility, etc.) is located and identified by a target tracking algorithm, such as R-CNN algorithm, YOLO algorithm, etc. Further, the area covered by all sensitive information in the first target picture is taken as the to-be-desensitized area, and any pixel in the to-be-desensitized area is taken as the first target pixel in this step.

[0046] In this embodiment, the low-bit data is binary data of a preset number of bits in a preset low-bit area in a byte used to store color data at the target pixel, and the change of the binary data in the preset low-bit area will not cause visual difference of human eyes. The high-bit data is binary data of a preset number of bits in a preset high-bit area in a byte used to store color data at the target pixel, and the change of the binary data in the preset high-bit area will cause visual difference of human eyes.

[0047] For example, in a scene where a video recording device processes video sensitive information (such as a vehicle license plate) based on a system on chip (SOC), the final product processed by an image signal processor (ISP) is code stream data in YUV format. In YUV format data, each pixel contains Y (luminance / gray scale) and UV (chrominance) color data.

[0048] For example, Y (luminance / gray scale) is taken as an example, as shown in Figure 2As shown, Y brightness in each pixel only needs 1 Byte, that is, 8-bit binary data "11101000" to describe, which means that the brightness level interval of each pixel is 0-255. In fact, in the 0-255 brightness level, through experiments, it is known that the change within 3 bits (0-7) will not cause visual differences for the human eye. Therefore, in this embodiment, first, as shown in Figure 2 The preset low-bit region and the preset high-bit region are divided, and if there is a change in binary data in the preset low-bit region, it will not cause visual differences for the human eye; if there is a change in binary data in the preset high-bit region, it will cause visual differences for the human eye. Of course, it can be understood that the visual sensitivity of different users is different, so the preset low-bit region and the preset high-bit region in the present application can be adaptively adjusted. If the user is sensitive to visual differences, the preset low-bit region can be reduced; otherwise, the preset low-bit region can be expanded.

[0049] Then, the high-bit data and the low-bit data are determined in the preset region, and data replacement is performed. In a specific embodiment, the way to determine the high-bit data and the low-bit data is: taking the binary data of the preset number of bits at the first preset position in the preset high-bit region as the high-bit data, and taking the binary data of the preset number of bits at the second preset position in the preset low-bit region as the low-bit data; wherein the preset number of bits is less than or equal to the number of bits of the binary data in the preset high-bit region and the preset low-bit region.

[0050] The way of data replacement is: replacing one binary data in the low-bit data with one binary data in the high-bit data, and repeating the operation until the replacement is completed. In this step, it is required that the replacement is one-to-one and cannot be repeated, so as to avoid data omission. And the corresponding relationship needs to be saved, so as to facilitate subsequent data restoration.

[0051] For example, in a specific embodiment, as shown in Figure 3 The preset number is set to 2, the 7th and 8th binary data in the preset high-bit region are taken as the high-bit data, and the 1st and 2nd binary data in the preset low-bit region are taken as the low-bit data. Further, as shown in Figure 4 The 7th binary data is replaced with the 1st binary data, and the 8th binary data is replaced with the 2nd binary data, at this time, the Y (brightness / gray scale) description of the first target pixel is "11101011", so that the effective information can be "backed up".

[0052] In another specific embodiment, as shown in Figure 5As shown, the preset number is set as 3, the 4th, 7th and 8th binary data are taken as high-bit data in the preset high-bit region, the 1st, 2nd and 3rd binary data are taken as low-bit data in the preset low-bit region. Further, the 1st binary data is replaced by the 7th binary data, the 2nd binary data is replaced by the 8th binary data, and the 3rd binary data is replaced by the 4th binary data. At this time, the Y (luminance / grey level) description at the first target pixel is "11101111", which can also "backup" the effective information.

[0053] It can be understood that the replacement principle of UV (chroma) and Y (luminance / grey level) is consistent, and can also be applied to the specific embodiments of Y (luminance / grey level) described above, which will not be repeated here.

[0054] In this embodiment, the same replacement processing based on step 102 is performed on all first target pixels in the first target picture, so that all sensitive information in the video to be desensitized can be backed up.

[0055] In step 104, the high-bit data at the first target pixel is irreversibly desensitized to obtain a processed desensitized video.

[0056] In this embodiment, the high-bit data is irreversibly desensitized, so that even if the processed desensitized video is lost, as long as the other party does not master the desensitization restoration technology corresponding to the sensitive information processing method of the video, there is no risk of sensitive information leakage, so it is relatively safe.

[0057] In the first embodiment of the desensitization processing, the scheme adopted is to fill the high-bit data at the first target pixel with a preset value. For example, when the preset number is 2, all high-bit data of the first target pixel can be filled with "11", or "10", or "01", or "00".

[0058] In the second embodiment of the desensitization processing, the scheme adopted is to set multiple first target pixels as an array and exchange the high-bit data between different pixels in the array. For example, pixel A, pixel B and pixel C are an array, the high-bit data of pixel A is "11", the high-bit data of pixel B is "10", and the high-bit data of pixel C is "01". After random exchange, the high-bit data of pixel A is replaced by "01", the high-bit data of pixel B is replaced by "11", and the high-bit data of pixel C is replaced by "10".

[0059] In the third embodiment of the desensitization processing, the adopted scheme is: a plurality of first target pixels are set as an array, the mean value of all high-bit data in the array is calculated, and the high-bit data of all pixels in the array is replaced by the mean value. For example, pixel A, pixel B and pixel C are an array, the high-bit data of pixel A is "11", the high-bit data of pixel B is "10", and the high-bit data of pixel C is "01". The mean value is calculated as 3, and the high-bit data of pixel A is replaced by "10", the high-bit data of pixel B is replaced by "10", and the high-bit data of pixel C is replaced by "10".

[0060] Of course, it can be understood that the embodiment can also adopt other irreversible desensitization processing modes for the high-bit data at the first target pixel, which is not limited here.

[0061] In the embodiment, the same desensitization processing based on step 104 is performed on all first target pixels in the first target picture, so that all sensitive information in the video to be desensitized can be hidden, and the purpose of "eliminating sensitive information with naked eyes" is achieved, thereby ensuring that the sensitive information will not be easily leaked.

[0062] In summary, the above-mentioned video sensitive information processing method first acquires a first target picture, identifies a desensitization region in the first target picture, and replaces the low-bit data at the first target pixel in the desensitization region with high-bit data. The binary data change in the preset high-bit region will cause the visual difference of the human eye, which can be understood as the main effective information of the image. Once this part of information changes, the image content will be obviously changed. The binary data change in the preset low-bit region will not cause the visual difference of the human eye. By replacing the low-bit data at the first target pixel in the desensitization region with high-bit data, the sensitive information in the image can be effectively backed up. Then, the high-bit data at the first target pixel is subjected to irreversible desensitization processing, and a processed desensitized video is obtained. In this way, all sensitive information can be hidden, and the purpose of "eliminating sensitive information with naked eyes" is achieved, thereby ensuring that the sensitive information will not be easily leaked. That is, the present application can hide effective information and achieve security. Subsequently, the hidden effective information can be used for restoration. At the same time, since the effective information is directly hidden in the processed image, it is not necessary to store a large and complex amount of data.

[0063] As Figure 7 shown, Figure 7 Fig. 2 is a flowchart of a video sensitive information processing method according to a second embodiment. The second embodiment relates to two stages of hiding and restoring video sensitive information.

[0064] The steps provided by the video sensitive information processing method in the embodiment include:

[0065] At step 702, a first target picture is acquired, a region to be desensitized in the first target picture is identified, and low-bit data at a first target pixel in the region to be desensitized is replaced with high-bit data.

[0066] In the second embodiment, step 702 is basically the same as step 102 in the video sensitive information processing method provided in the first embodiment of the present application. The difference is that, in the first target picture, pixels in the region to be desensitized are also marked, so that in the subsequent video restoration stage, the target tracking algorithm does not need to be used again, and the efficiency of video restoration can be improved.

[0067] At step 704, irreversible desensitization processing is performed on the high-bit data at the first target pixel, and a processed desensitized video is acquired.

[0068] In the second embodiment, step 704 is basically the same as step 104 in the video sensitive information processing method provided in the first embodiment of the present application, and will not be described again.

[0069] At step 706, a region to be restored in a second target picture is identified, and high-bit data at a second target pixel in the region to be restored is replaced with low-bit data, and a processed restored video is acquired.

[0070] The second target picture is any frame in the desensitized video, and the second target pixel is any pixel in the region to be restored.

[0071] In one specific embodiment, since the marking operation has been performed at step 702, the identification of the region to be restored is as follows: in the second target picture, the region covered by the pixel carrying the mark is identified as the region to be restored.

[0072] After the region to be restored is identified, the restoration processing is performed. In the embodiment, step 706 can be understood as the reverse operation of step 702.

[0073] For example, in combination with Figure 3 , it is assumed that before step 702 is performed, the Y (luminance / grey level) description of the first target pixel is "11101000". In combination with Figure 4 , after step 702 is performed, the 7th binary data is replaced with the 1st binary data, and the 8th binary data is replaced with the 2nd binary data. The Y (luminance / grey level) description of the first target pixel is "11101011", that is, the "backup" of the effective data is completed. In combination with Figure 8 , it is assumed that after step 704 is performed, the Y (luminance / grey level) description of the first target pixel is "10101011", that is, the hiding stage of the video sensitive information is completed. In combination with Figure 9, based on the correspondence stored in step 702, the 7th binary data is replaced by the 1st binary data, and the 8th binary data is replaced by the 2nd binary data, and the Y (brightness / gray scale) description at the second target pixel (the second target pixel here is the same as the first target pixel) is "11101011", thus completing the restoration phase of the video sensitive information.

[0074] As can be seen, the Y (brightness / gray scale) description at the first target pixel of the video to be desensitized is "11101000" before being processed, and the Y (brightness / gray scale) description at the first target pixel is "11101011" after being processed. The difference is only in the low bit data, and since the change of the low bit data will not cause visual difference in human eyes, the sensitive information is still effectively preserved after being restored.

[0075] In this embodiment, the same restoration processing based on step 706 is performed on all second target pixels in the second target picture, so that the processed and restored video is obtained.

[0076] The above-mentioned video sensitive information processing method only has a slight loss that cannot be detected by the naked eye when restoring the video sensitive information, and can be considered as 100% restoration to the original video. Moreover, no additional storage space is used to store the picture data of the original sensitive information, which can greatly reduce the product and technical implementation difficulty and cost, and can be performed in real time on various terminals.

[0077] In one embodiment, as shown in Figure 10 a video sensitive information processing device is provided, which comprises:

[0078] The sensitive information backup module 1002 is configured to acquire a first target picture, identify a desensitization area in the first target picture, and replace low bit data at a first target pixel in the desensitization area with high bit data; wherein the first target picture is any frame in the video to be desensitized, the first target pixel is any pixel in the desensitization area, the low bit data is binary data of a preset number of bits in a preset low bit area in a byte used to store color information at the target pixel, the change of the binary data in the preset low bit area will not cause visual difference in human eyes, and the high bit data is binary data of a preset number of bits in a preset high bit area in a byte used to store color information at the target pixel, the change of the binary data in the preset high bit area will cause visual difference in human eyes.

[0079] The sensitive information hiding module 1004 is configured to perform irreversible desensitization processing on the high bit data at the first target pixel, and acquire a processed and desensitized video.

[0080] Figure 11 An internal structure diagram of a video sensitive information processing device in one embodiment is shown. As shown inFigure 11 As shown in the figure, the video sensitive information processing device includes a processor, a memory and a network interface connected through a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the video sensitive information processing device stores an operating system, and can also store a computer program which, when executed by the processor, can enable the processor to implement the video sensitive information processing method. The internal memory can also store a computer program which, when executed by the processor, can enable the processor to execute the video sensitive information processing method. Those skilled in the art can understand that Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the video sensitive information processing device to which the scheme of the present application is applied. The specific video sensitive information processing device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0081] A video sensitive information processing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: obtaining a first target picture, identifying a to-be-desensitized area in the first target picture, and replacing low-bit data at a first target pixel in the to-be-desensitized area with high-bit data; performing irreversible desensitization processing on the high-bit data at the first target pixel to obtain a processed desensitized video.

[0082] A computer readable storage medium stores a computer program which, when executed by a processor, implements the following steps: obtaining a first target picture, identifying a to-be-desensitized area in the first target picture, and replacing low-bit data at a first target pixel in the to-be-desensitized area with high-bit data; performing irreversible desensitization processing on the high-bit data at the first target pixel to obtain a processed desensitized video.

[0083] It should be noted that the above video sensitive information processing method, device, equipment and computer readable storage medium belong to one overall inventive concept, and the contents in the video sensitive information processing method, device, equipment and computer readable storage medium embodiments can be mutually applicable.

[0084] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0085] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0086] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for processing sensitive video information, characterized in that, The method includes: A first target image is acquired, the area to be desensitized within the first target image is identified, and the low-order data at the first target pixel within the area to be desensitized is replaced with high-order data. Here, the first target image is any frame in the video to be desensitized, the first target pixel is any pixel within the area to be desensitized, the low-order data is binary data of a preset number of bits located within a preset low-order region in the byte used to store color data at the target pixel, where changes in the binary data within the preset low-order region will not cause visual differences in the human eye, and the high-order data is binary data of a preset number of bits located within a preset high-order region in the byte used to store color data at the target pixel, where changes in the binary data within the preset high-order region will cause visual differences in the human eye. Irreversibly desensitize the high-order data at the first target pixel to obtain the desensitized video. The process of obtaining the processed desensitized video further includes: Identify the area to be restored within the second target image, and replace the high-order data of the second target pixel within the area to be restored with the low-order data to obtain the processed restored video; wherein, the second target image is any frame in the desensitized video, and the second target pixel is any pixel in the area to be restored; The method further includes: In the first target image, the pixels in the area to be desensitized are marked; The identification of the region to be restored within the second target image includes: In the second target image, the area covered by the marked pixels is identified as the area to be restored.

2. The method according to claim 1, characterized in that, The method further includes: Within the preset high-order region, the binary data with a preset number of bits at the first preset position is taken as the high-order data, and within the preset low-order region, the binary data with a preset number of bits at the second preset position is taken as the low-order data; wherein, the preset number of bits is less than or equal to the number of bits in the binary data within the preset high-order region and the preset low-order region.

3. The method according to claim 1, characterized in that, The step of irreversibly desensitizing the high-order data at the first target pixel includes: Fill the high-order data at the first target pixel with a preset value.

4. The method according to claim 1, characterized in that, The step of irreversibly desensitizing the high-order data at the first target pixel includes: Multiple first target pixels are set into an array, and the high-order bits of different pixels in the array are swapped.

5. The method according to claim 1, characterized in that, The step of irreversibly desensitizing the high-order data at the first target pixel includes: Multiple first target pixels are set as an array, the mean of all high-order data in the array is calculated, and the mean is used to replace the high-order data of all pixels in the array.

6. A video-sensitive information processing device, characterized in that, The device includes: A sensitive information backup module is used to acquire a first target image, identify the area to be desensitized within the first target image, and replace the low-order data of the first target pixel within the area to be desensitized with high-order data. The first target image is any frame in the video to be desensitized, the first target pixel is any pixel within the area to be desensitized, the low-order data is binary data of a preset number of bits located within a preset low-order region in the bytes used to store color data at the target pixel, where changes in the binary data within the preset low-order region will not cause visual differences in the human eye, and the high-order data is binary data of a preset number of bits located within a preset high-order region in the bytes used to store color data at the target pixel, where changes in the binary data within the preset high-order region will cause visual differences in the human eye. The sensitive information hiding module is used to irreversibly desensitize the high-order data at the first target pixel to obtain the processed desensitized video. The process further includes, after obtaining the processed desensitized video, identifying the area to be restored within the second target image and replacing the high-order data at the second target pixel within the area to be restored with low-order data to obtain the processed restored video; wherein the second target image is any frame in the desensitized video and the second target pixel is any pixel in the area to be restored. The device is further configured to: mark pixels in the area to be desensitized in the first target image; and to identify the area to be restored in the second target image, including: identifying the area covered by the marked pixels in the second target image as the area to be restored.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the processor performs the steps of the method as described in any one of claims 1 to 5.

8. A video-sensitive information processing device, comprising a memory and a processor, characterized in that, The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 5.

Images