Video privacy protection method, video decryption method and related devices

Abstract

The invention provides a video privacy protection method, a video decryption method and related devices. Wherein the video encryption equipment can encrypt the video frame containing the privacy information in the original video by adopting the initialization vector and the encryption key, so that the privacy protection function can be realized. In the process of carrying out compression coding on the privacy protection video, the video encryption equipment can encrypt the initialization vector and / or the encryption key by adopting preset password information, and writes encryption parameter data obtained by encryption into video coding data. On one hand, for an illegal attacker who does not know the preset password information, the original video cannot be accurately restored, so that the information security can be further ensured. And on the other hand, for a legal authorizer with preset password information, the lossless compressed encoding data can be accurately decrypted by using the complete reversibility of encryption and decryption, so that the original video is accurately restored, and reversible video privacy protection is realized.

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to a video privacy protection method, a video decryption method and related devices. Background Art

[0002] With the development and popularization of video surveillance technology, video surveillance systems provide good security for public and private places. Video surveillance systems installed in public places such as stations, shopping malls, and streets can monitor and record suspicious behaviors in public places in real time. Video surveillance systems installed in private places can monitor the real-time situation in the place and issue an alarm when abnormal activities or unexpected events are detected in the place.

[0003] In order to realize the real-time live broadcast function and AI (Artificial Intelligence) analysis function of the video, the video surveillance system usually uploads the collected surveillance video to the cloud server, which puts forward privacy protection requirements for the privacy subjects (such as faces, license plates, etc.) and private places (such as bedrooms and bathrooms) involved in the surveillance video.

[0004] At present, the existing technology mainly achieves video privacy protection in two ways. The first is to blur the privacy area of ​​the video frame through Gaussian blur algorithm and mosaic algorithm, and obtain a privacy-protected video accordingly. The second is to use a generative adversarial network to generatively replace the privacy area of ​​the video frame, so as to replace the real image content of the privacy area with other image content, and obtain a privacy-protected video accordingly. Although both methods achieve privacy protection in terms of visual effects, the irreversibility of these operations makes it impossible for other devices to accurately restore the original video based on the privacy-protected video, making it impossible for those with video permissions to view the original video, and it is not conducive to law enforcement agencies to conduct investigations and evidence collection.

[0005] Therefore, there is an urgent need to provide a reversible video privacy protection solution. Summary of the invention

[0006] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect that the existing technology cannot accurately restore the original surveillance video based on the privacy protection video.

[0007] In a first aspect, an embodiment of the present application provides a video privacy protection method, which is applied to a video encryption device, comprising:

[0008] Get the original video, initialization vector and encryption key;

[0009] Encrypting the to-be-encrypted video frame of the original video according to the initialization vector and the encryption key, and obtaining a privacy-protected video; wherein the to-be-encrypted video frame is a video frame including privacy information;

[0010] Encrypting the initialization vector and / or the encryption key using preset password information to obtain encryption parameter data;

[0011] According to the encryption parameter data, the privacy protection video is compressed and encoded using a lossless compression encoding algorithm to obtain video encoding data; wherein the video encoding data includes multiple NAL unit data, at least one of the NAL unit data is SEI data, and the first SEI data records the encryption parameter data.

[0012] In some embodiments, encrypting the to-be-encrypted video frame of the original video according to the initialization vector and the encryption key includes:

[0013] Determine a privacy area of ​​a target video frame; the target video frame is any of the video frames to be encrypted, and the privacy area is an image area corresponding to the privacy information;

[0014] The image data corresponding to the privacy area is encrypted according to the initialization vector and the encryption key.

[0015] In some embodiments, encrypting the image data corresponding to the privacy area according to the initialization vector and the encryption key includes:

[0016] Determine, according to the initialization vector and the encryption key, a first target vector, a second target vector, a third target vector, a first target key, a second target key, and a third target key;

[0017] Obtaining the channel value of each target pixel point in the first image channel to obtain a first channel value array; wherein each target pixel point is each pixel point located in the privacy area;

[0018] Using the first target vector and the first target key, perform encryption calculation on the first channel value array, and obtain a first encrypted array according to the encryption calculation result of the first channel value array;

[0019] Obtaining the channel value of each target pixel in the second image channel to obtain a second channel value array;

[0020] Using the second target vector and the second target key, perform encryption calculation on the second channel value array, and obtain a second encrypted array according to the encryption calculation result of the second channel value array;

[0021] Obtaining the channel value of each target pixel in the third image channel to obtain a third channel value array;

[0022] Using the third target vector and the third target key, perform encryption calculation on the third channel value array, and obtain a third encrypted array according to the encryption calculation result of the third channel value array;

[0023] Determine the encrypted pixel value of each target pixel based on the first encrypted array, the second encrypted array, and the third encrypted array;

[0024] The actual pixel value of each target pixel point is modified to the encrypted pixel value of the target pixel point.

[0025] In some embodiments, determining the first target vector, the second target vector, the third target vector, the first target key, the second target key, and the third target key respectively according to the initialization vector and the encryption key comprises:

[0026] Using a preset hash algorithm, performing a hash calculation on the initialization vector, the encryption key, and a preset first channel identifier to obtain a first hash value;

[0027] Using a preset division rule, the first Hash value is divided into the first target vector and the first target key;

[0028] Using the preset hash algorithm, performing hash calculation on the initialization vector, the encryption key and a preset second channel identifier to obtain a second hash value; wherein the second channel identifier is different from the first channel identifier;

[0029] Using the preset division rule, the second Hash value is divided into the second target vector and the second target key;

[0030] Using the preset hash algorithm, performing hash calculation on the initialization vector, the encryption key and a preset third channel identifier to obtain a third hash value; wherein the third channel identifier is different from the first channel identifier and the second channel identifier;

[0031] The preset division rule is adopted to divide the third Hash value into the third target vector and the third target key.

[0032] In some embodiments, the plurality of NAL unit data include N encrypted video data and N custom SEI data, and the N encrypted video data correspond one to one with the N custom SEI data;

[0033] In the video encoding data, any of the custom SEI data is adjacent to the corresponding target encrypted video data, and any of the custom SEI data records the privacy area position information corresponding to the target encrypted video data;

[0034] The encrypted video data is NAL unit data for recording encrypted video frames, the encrypted video frames are obtained by encrypting the video frames to be encrypted, and N is the total number of video frames to be encrypted in the original video.

[0035] In some embodiments, the encryption parameter data is data obtained by encrypting the encryption key using the preset password information; the first SEI data records the initialization vector and the encryption parameter data.

[0036] In a second aspect, an embodiment of the present application provides a video decryption method, which is applied to a video decryption device, including:

[0037] Obtaining video encoding data; wherein the video encoding data is generated by the video privacy protection method described in any one of the above embodiments;

[0038] Reading first SEI data of the video encoding data, and extracting encryption parameter data from the first SEI data;

[0039] Decrypting the encrypted parameter data using a preset password information, and obtaining an initialization vector and an encryption key according to the decryption result;

[0040] The initialization vector and the encryption key are used to decrypt multiple NAL unit data of the video encoding data to obtain a decrypted video.

[0041] In some embodiments, the video file of the decrypted video includes N custom SEI data, where N is a positive integer;

[0042] After obtaining the decrypted video, the method further includes:

[0043] Deleting N pieces of the custom SEI data from the video file of the decrypted video;

[0044] The encryption parameter data is deleted from the first SEI data.

[0045] In a third aspect, an embodiment of the present application provides a video privacy protection device, which is applied to a video encryption device, including:

[0046] A data acquisition module, used to acquire original video, initialization vector and encryption key;

[0047] A privacy protection module, configured to encrypt the video frame to be encrypted of the original video according to the initialization vector and the encryption key, and obtain a privacy-protected video; wherein the video frame to be encrypted is a video frame including privacy information;

[0048] A parameter encryption module, used to encrypt the initialization vector and / or the encryption key using a preset password information, and obtain encrypted parameter data;

[0049] A compression coding module is used to compress and encode the privacy protection video using a lossless compression coding algorithm according to the encryption parameter data, and obtain video coding data; wherein the video coding data includes multiple NAL unit data, at least one of the NAL unit data is SEI data, and the first SEI data records the encryption parameter data.

[0050] In a fourth aspect, an embodiment of the present application provides a video decryption apparatus, which is applied to a video decryption device, including:

[0051] A coding data acquisition module, used to acquire video coding data; wherein the video coding data is generated by the video privacy protection method described in any one of the above embodiments;

[0052] A SEI reading module, used for reading the first SEI data of the video encoding data and extracting encryption parameter data from the first SEI data;

[0053] A parameter decryption module, used to decrypt the encrypted parameter data using a preset password information, and obtain an initialization vector and an encryption key according to the decryption result;

[0054] The video decryption module is used to decrypt multiple NAL unit data of the video encoding data using the initialization vector and the encryption key to obtain a decrypted video.

[0055] In the solutions provided in some embodiments of the present application, the video encryption device can use an initialization vector and an encryption key to encrypt video frames containing privacy information in the original video, thereby protecting the privacy subjects and privacy areas in the original video and realizing a privacy protection function.

[0056] In the process of compressing and encoding the privacy-protected video, the video encryption device can use the preset password information to encrypt the initialization vector and / or encryption key, and write the encrypted encryption parameter data into the video encoding data. On the one hand, for illegal attackers who do not know the preset password information, they cannot accurately restore the original video, thereby further ensuring information security. On the other hand, for the legal authorized person who has the preset password information, they can use the complete reversibility of encryption and decryption to obtain the initialization vector and encryption key from the video encoding data, and use the initialization vector and encryption key to accurately decrypt the lossless compression encoding data to accurately restore the original video and achieve reversible video privacy protection. At the same time, the present application can also perform privacy encryption protection on videos of any format. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0058] Figure 1 FIG. 1 is an application environment diagram of a video privacy protection method and a video decryption method in one embodiment;

[0059] Figure 2 A schematic diagram of a frame of an original video frame in one embodiment;

[0060] Figure 3 A schematic diagram of a frame image processed by an AI recognition algorithm in one embodiment;

[0061] Figure 4 A schematic diagram of an encrypted frame image in one embodiment;

[0062] Figure 5 A schematic diagram of a decrypted frame image in one embodiment;

[0063] Figure 6 A schematic diagram of a process of a video privacy protection method in one embodiment;

[0064] Figure 7 A schematic diagram of a video decryption method in one embodiment;

[0065] Figure 8 is a structural schematic diagram of a video privacy protection device in one embodiment;

[0066] Fig. 9 is a schematic structural diagram of a video decryption device in one embodiment;

[0067] Fig.10 FIG. 1 is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0069] In some embodiments, the video privacy protection method and video decryption method provided by the present application can be applied to Figure 1 In the application environment shown. Among them, the acquisition device refers to a video acquisition device, which can be installed in public and / or private places in a legal and compliant manner to collect original videos. For example, the acquisition device may be a surveillance camera. It should be noted that the image / video acquisition, storage, use, processing, transmission, provision and disclosure involved in this application are in compliance with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0070] A video encryption device refers to a device used to encrypt an original video to generate a privacy-preserving video. A video decryption device refers to a device used to decrypt a privacy-preserving video to generate the original video. The cloud storage function can be realized through a cloud server, that is, the privacy-preserving video can be uploaded to a cloud server for storage.

[0071] It is understood that the video encryption device and the video decryption device can be implemented by any device, and this document does not impose specific restrictions on this. In one example, the video encryption device and the video decryption device can be a local computing device or a computing device that has been security-certified. In another example, the video encryption device and the acquisition device can be integrated into one, and the integrated acquisition device can have a video acquisition function and a video encryption function. In another example, the video decryption device can be a video playback device, for example, an electronic terminal that has been authorized and authenticated.

[0072] See also Figure 1 Some embodiments of the present application provide a completely reversible video privacy protection method and video decryption method. The video privacy protection method may include steps such as privacy area identification, privacy area encryption, and encoding to form a privacy protection video, and the video decryption method includes steps such as decryption and restoration when the correct password is obtained.

[0073] Specifically, the acquisition device can acquire the original video and obtain a video file. The original video includes one or more video frames, and at least one video frame is a video frame to be encrypted including privacy information. The video encryption device can use an AI recognition algorithm to identify the privacy area of ​​the video frame to be encrypted, and perform encryption calculation on the image data corresponding to the privacy area according to the encryption key and the initialization vector to obtain a privacy-protected video. The video encryption device can upload the video encoding data corresponding to the privacy-protected video to the cloud server for cloud storage through the cloud server. In one example, the original video frame can be as follows: Figure 2 As shown, the privacy area identified by AI can be Figure 3 As shown in the rectangular box, the encrypted video frame can be Figure 4 shown.

[0074] Without knowing the encryption key and initialization vector, the video playback effect corresponding to the video encoding data can be as follows Figure 4 As shown. It can be seen that this application can effectively protect privacy and is applicable to surveillance video privacy protection in public and private places. Even if the video is stored in the cloud, the cloud storage administrator or illegal attacker can only see the privacy-protected video.

[0075] In the case of having the encryption key and the initialization vector, the encryption key and the initialization vector can be used to decrypt the video encoding data involved in the privacy protection video, and the following is obtained: Figure 5 The original video shown. It can be seen that the key owner can use the complete reversibility of encryption to decrypt the video encoding data to obtain the accurate original video and watch the original clear video, thus providing a technical solution for video viewing by legal authorized persons or legal electronic evidence collection.

[0076] It should be noted that Figure 2 , Figure 3 and Figure 5 The blurring of the face area is to meet the relevant provisions of patent examination. Figure 2 The original video frame shown, Figure 3 The privacy region identification results and Figure 5 The decoded video frames shown are all clear image frames that have not been blurred, thereby providing a technical solution for video viewing by legally authorized persons or legal electronic evidence collection.

[0077] Therefore, the solutions provided by some embodiments of the present application have at least one of the following advantages:

[0078] (1) It can effectively protect privacy and is suitable for surveillance video privacy protection in public and private places. Even if the video is stored in the cloud, the cloud storage administrator or attacker can only see the privacy-protected video. Only the key owner can decrypt and watch the original clear video.

[0079] (2) Privacy areas can be flexibly specified. In practice, privacy areas that need to be encrypted can be provided based on AI or manual selection.

[0080] (3) When encrypting a video with privacy protection, it is not restricted to the original encoding format of the video (it can support encryption of any video format), and the format of the decrypted video can remain consistent with the original video.

[0081] (4) The video is encrypted using a secure national secret algorithm with high security strength. An attacker without the key cannot restore the original video.

[0082] (5) The video is completely reversible. When necessary, it can be decrypted using the correct password to produce a video that is completely identical to the original video, meeting the needs of legally authorized persons for viewing or video electronic evidence collection in judicial scenarios.

[0083] The following describes the video privacy protection method provided in the embodiment of the present application.

[0084] In some embodiments, the present application provides a video privacy protection method, and the following embodiments are described by taking the method applied to a video encryption device as an example. Figure 6 As shown, the video privacy protection method provided by this application includes the following steps:

[0085] S602: Obtain original video, initialization vector and encryption key.

[0086] The original video may be a video that has not been processed for privacy protection, for example, it may be an original surveillance video acquired by an acquisition device. An initialization vector (IV) refers to an initialization vector in a block cipher, which is used for video encryption. An encryption key refers to key information used for video encryption.

[0087] It is understood that the method for obtaining the original video, initialization vector and encryption key can be determined according to the actual situation, and this document does not specifically limit this. In one example, in order to improve data security and privacy protection, the encryption key and initialization vector can be randomly generated using a random algorithm. Furthermore, the data length of the encryption key and the initialization vector are both greater than or equal to 128 bits to meet the security strength requirements and further improve security.

[0088] S604: Encrypt the to-be-encrypted video frame of the original video according to the initialization vector and the encryption key, and obtain a privacy-protected video.

[0089] The original video includes at least one video frame, and the video frame to be encrypted refers to the video frame in the original video that includes private information. It should be noted that the specific information type of the private information can be determined according to the actual situation, and this document does not impose any specific restrictions on this. Figure 2-Figure 5 In the example of , the private information may be a face and a license plate. In other examples, the private information may be a specific location area, such as a bedroom, a bathroom, etc.

[0090] In this step, the video encryption device may use the initialization vector and the encryption key to encrypt each video frame to be encrypted in the original video, and obtain a privacy-protected video. It can be understood that the privacy-protected video includes encrypted video frames and video frames that do not include privacy information, and the encrypted video frames refer to video frame data obtained by encrypting the video frames to be encrypted in the original video.

[0091] For example, when the original video includes a first original video frame, a second original video frame, and a third original video frame, and the first original video frame does not include privacy information, and the second original video frame and the third original video frame both include privacy information, the video encryption device can encrypt the second original video frame and the third original video frame, respectively, and obtain a second encrypted video frame and a third encrypted video frame. The first original video frame, the second encrypted video frame, and the third encrypted video frame constitute a privacy-protected video.

[0092] It should be noted that, in the process of encrypting the video frame to be encrypted, the video encryption device may encrypt the entire image area of ​​the video frame to be encrypted, or encrypt a portion of the image area of ​​the video frame to be encrypted. At the same time, the video encryption device may implement encryption in any manner, as long as it implements encryption according to the initialization vector and the encryption key.

[0093] S606: Encrypt the initialization vector and / or encryption key using the preset password information, and obtain encryption parameter data.

[0094] The preset password information may be preset and used to encrypt the frame encryption information and obtain encryption parameter data.

[0095] Considering that the initialization vector and the encryption key are difficult to remember, the initialization vector and / or the encryption key can be encrypted using a preset password information. In this way, on the one hand, the initialization vector and / or the encryption key can be restored by the preset password information during decryption, which is easy to remember, and on the other hand, the security can be further improved to avoid the leakage of the initialization vector and / or the encryption key.

[0096] In this step, the video encryption device may use the preset password information to encrypt the initialization vector, or may use the preset password information to encrypt the encryption key. Alternatively, the preset password information may be used to encrypt the initialization vector and the encryption key respectively.

[0097] S608: According to the encryption parameter data, a lossless compression coding algorithm is used to compress and encode the privacy-protected video, and video coding data is obtained.

[0098] The video encoding data includes multiple NAL unit data, at least one NAL unit data is SEI data, and the first SEI data records encryption parameter data. NAL (Network Abstraction Layer) unit data can be used to encapsulate video data and related information so that video data can be transmitted in different network environments. SEI data is supplementary enhancement information data.

[0099] In this step, lossless compression coding can be used to encode the privacy-preserving video to convert the data of the privacy-preserving video into video encoding data that can be transmitted in different network environments. At the same time, lossless compression coding can preserve the complete ciphertext image information so that the original video content can be accurately decrypted and restored during decryption.

[0100] The video encoding data may include multiple NAL unit data, and the multiple NAL unit data may include video data for recording video frame images and SEI data for recording supplementary enhancement information. The video encryption device may write encryption parameter data in the NAL unit data of the first SEI, so that the video encoding data carries frame encryption information for decryption.

[0101] Furthermore, in one example, the video encryption device may encrypt the encryption key using the preset password information to obtain the encrypted parameter data, and write the encrypted parameter data and the plain text data of the initialization vector into the first SEI data. In this way, the initialization vector and the encryption key may be obtained first during decryption, so that data decryption and playback can be performed simultaneously, thereby improving the video playback response efficiency.

[0102] In the present application, the video encryption device can use the initialization vector and the encryption key to encrypt the video frames containing the privacy information in the original video, so as to protect the privacy subject and the privacy area in the original video and realize the privacy protection function.

[0103] In the process of compressing and encoding the privacy-protected video, the video encryption device can use the preset password information to encrypt the initialization vector and / or encryption key, and write the encrypted encryption parameter data into the video encoding data. On the one hand, for illegal attackers who do not know the preset password information, they cannot accurately restore the original video, thereby further ensuring information security. On the other hand, for the legal authorized person who has the preset password information, they can use the complete reversibility of encryption and decryption to obtain the initialization vector and encryption key from the video encoding data, and use the initialization vector and encryption key to accurately decrypt the lossless compression encoding data to accurately restore the original video and achieve reversible video privacy protection. At the same time, the present application can also perform privacy encryption protection on videos of any format.

[0104] In some embodiments, encrypting a video frame to be encrypted of an original video according to an initialization vector and an encryption key includes:

[0105] Determine a privacy area of ​​a target video frame; the target video frame is any video frame to be encrypted, and the privacy area is an image area corresponding to the privacy information;

[0106] The image data corresponding to the privacy area is encrypted according to the initialization vector and the encryption key.

[0107] Specifically, for each video frame to be encrypted of the original video, the video encryption device may first determine the target subject and target area in the video frame to be encrypted that require privacy protection, and then determine the privacy area of ​​the target video frame.

[0108] In one example, the video encryption device can use an AI recognition algorithm to automatically identify the privacy area in the target video frame. Furthermore, the AI ​​recognition algorithm can be implemented based on the YOLO model. The trained YOLO model can support the recognition of typical privacy targets including faces and license plates. The recognition results can include the target subject and the location coordinates of the privacy area in each video frame.

[0109] In another example, the privacy area can be manually selected by the user. Furthermore, manually specifying the privacy area requires the support of a specific video viewing front end, and the user can mark the privacy area with a mouse or gesture. For example, when shooting with a fixed camera in the living room, the user can set the shooting area of ​​the bathroom and bedroom as a privacy area.

[0110] For each video frame to be encrypted of the original video, when the privacy area of ​​the video frame to be encrypted is determined, the video encryption device can encrypt the privacy area of ​​the video frame to be encrypted according to the initialization vector and the encryption key, that is, perform encryption calculation on the image data corresponding to the privacy area and obtain the encrypted video frame.

[0111] In this way, the privacy subject and privacy area of ​​the video frame can be encrypted as needed, and the privacy-protected video only blurs the specified video area, which will not affect the video-based AI applications and data analysis capabilities (such as crowd counting analysis and vehicle counting analysis, etc.).

[0112] In some embodiments, encrypting the image data corresponding to the privacy area according to the initialization vector and the encryption key includes:

[0113] Step A1: Determine a first target vector, a second target vector, a third target vector, a first target key, a second target key and a third target key respectively according to the initialization vector and the encryption key;

[0114] Step A2: acquiring the channel value of each target pixel point in the first image channel to obtain a first channel value array; wherein each target pixel point is a pixel point located in the privacy area;

[0115] Step A3: using the first target vector and the first target key to perform encryption calculation on the first channel value array, and obtaining a first encrypted array according to the encryption calculation result of the first channel value array;

[0116] Step A4: obtaining the channel value of each target pixel in the second image channel to obtain a second channel value array;

[0117] Step A5: using the second target vector and the second target key to perform encryption calculation on the second channel value array, and obtaining a second encrypted array according to the encryption calculation result of the second channel value array;

[0118] Step A6: obtaining the channel value of each target pixel in the third image channel to obtain a third channel value array;

[0119] Step A7: using the third target vector and the third target key to perform encryption calculation on the third channel value array, and obtaining a third encrypted array according to the encryption calculation result of the third channel value array;

[0120] Step A8: determining the encrypted pixel value of each target pixel point based on the first encrypted array, the second encrypted array and the third encrypted array;

[0121] Step A9: modify the actual pixel value of each target pixel point to the encrypted pixel value of the target pixel point.

[0122] In this embodiment, Figure 4As shown, when encrypting the privacy area of ​​the target video frame, the video encryption device can encrypt the plaintext value of each image channel and blur the privacy area according to the ciphertext value of each image channel. In this way, compared with the existing Gaussian blur algorithm and mosaic algorithm, the encryption method provided by this embodiment can have a better blurring visual effect, thereby further improving information security and avoiding privacy leakage.

[0123] It can be understood that the first image channel, the second image channel, and the third image channel are three different image channels, which is not specifically limited herein. For example, the first image channel may be an H (hue) channel, the second image channel may be an S (saturation) channel, and the third image channel may be a V (brightness) channel. For another example, the first image channel may be an R (red) channel, the second image channel may be a G (green) channel, and the third image channel may be a B (blue) channel. For ease of description, some embodiments of the present application are described using RGB channels as an example.

[0124] The video encryption device can determine three target vectors and three target keys according to the initialization vector and the encryption key, wherein the three target vectors correspond to the three image channels one by one, and the three target keys correspond to the three image channels one by one.

[0125] The video encryption device can obtain the channel value of each pixel point (i.e., each target pixel point) located in the privacy area in the target video frame in the first image channel, and obtain the first channel value array. For example, the video encryption device can obtain the channel value of each target pixel point in the R channel according to the total number of pixels num in the calculated privacy area, and obtain the first channel value array R[num]. It can be understood that R[num] represents an array of length num composed of the R channel values ​​of each pixel in the privacy area of ​​the target video frame.

[0126] After obtaining the first channel value array, the video encryption device can use the first target vector and the first target key to perform encryption calculation on the first channel value array, and obtain the first encrypted array according to the encryption calculation result of the first channel value array. It can be understood that the first encrypted array is the ciphertext array corresponding to the first channel value array.

[0127] In one example, the video encryption device may generate a key stream of num bytes using the OFB (Output Feedback) working mode of the commercial SM4 algorithm, and XOR-encrypt the key stream with the plaintext value to obtain a ciphertext value, namely:

[0128] CR[num]=SM4_OFB_Encrypt(R[num],key_1,IV_1)

[0129] Where CR[num] is the first encrypted array of length num, key_1 is the first target key, and IV_1 is the first target vector.

[0130] For the second image channel and the third image channel, the video encryption device can complete the encryption calculation in a similar manner to the first image channel, and obtain the second encryption array and the third encryption array respectively. In one example, the second encryption array and the third encryption array can be calculated according to the following expression:

[0131] CG[num]=SM4_OFB_Encrypt(G[num],key_2,IV_2)

[0132] CB[num]=SM4_OFB_Encrypt(B[num],key_3,IV_3)

[0133] Wherein, CG[num] is the second encryption array; G[num] is an array of length num consisting of the G channel values ​​of each pixel in the privacy area of ​​the target video frame, that is, the second channel value array; key_2 is the second target key; IV_2 is the second target vector; CB[num] is the third encryption array; B[num] is an array of length num consisting of the B channel values ​​of each pixel in the privacy area of ​​the target video frame, that is, the third channel value array; key_3 is the third target key; IV_3 is the third target vector.

[0134] After determining the encryption arrays corresponding to the three image channels, the video encryption device can encrypt the privacy area of ​​the target video frame according to the ciphertext values ​​corresponding to the three image channels, and obtain the following: Figure 4 The encrypted video frame shown. In one example, the RGB ciphertext of each target pixel can be (CR[j], CG[j], CB[j]), j=0, 1, 2, ..., num-1.

[0135] In some embodiments, determining a first target vector, a second target vector, a third target vector, a first target key, a second target key, and a third target key respectively according to the initialization vector and the encryption key includes:

[0136] Step A11: using a preset hash algorithm to perform hash calculation on the initialization vector, the encryption key and the preset first channel identifier to obtain a first hash value;

[0137] Step A12: using a preset division rule to divide the first Hash value into a first target vector and a first target key;

[0138] Step A13: using a preset hash algorithm to perform hash calculation on the initialization vector, the encryption key and the preset second channel identifier to obtain a second hash value; wherein the second channel identifier is different from the first channel identifier;

[0139] Step A14: using a preset division rule to divide the second Hash value into a second target vector and a second target key;

[0140] Step A15: using a preset hash algorithm to perform hash calculation on the initialization vector, the encryption key and the preset third channel identifier to obtain a third hash value; wherein the third channel identifier is different from the first channel identifier and the second channel identifier;

[0141] Step A16: using a preset division rule to divide the third Hash value into a third target vector and a third target key.

[0142] In this embodiment, the target key corresponding to each image channel is different, and the target vector corresponding to each image channel is different. This can further improve the visual blur effect and increase the difficulty of cracking, thereby improving information security.

[0143] Specifically, each image channel corresponds to a channel identifier, and the channel identifiers corresponding to each image channel are different. For each image channel, the video encryption device can use a preset hash algorithm to perform hash calculations on the initialization vector, the encryption key, and the channel identifier corresponding to the image channel, and divide the hash value corresponding to the image channel into the target vector and target key corresponding to the image channel according to a preset division rule.

[0144] For example, the channel identifier corresponding to the R channel may be 1, the channel identifier corresponding to the G channel may be 2, and the channel identifier corresponding to the B channel may be 3. The video encryption device may use the initialization vector and the encryption key to derive the target key key_i and the target vector IV_i corresponding to each image channel based on the commercial secret SM3 hash algorithm. Specifically, key_i||IV_i=SM3(i,key,IV), i=1,2,3. That is, a 256-bit hash value is obtained using the SM3 hash algorithm, and the first 128 bits are taken as key_i, and the last 128 bits are taken as IV_i.

[0145] In some embodiments, multiple NAL unit data include N encrypted video data and N custom SEI data, and the N encrypted video data correspond one-to-one to the N custom SEI data; wherein the encrypted video data is NAL unit data used to record encrypted video frames, the encrypted video frames are obtained by encrypting the video frames to be encrypted, and N is the total number of video frames to be encrypted in the original video.

[0146] In the video encoding data, any custom SEI data is adjacent to the corresponding target encrypted video data, and any custom SEI data records the privacy region position information corresponding to the target encrypted video data, wherein the target encrypted video data refers to the encrypted video data corresponding to the custom SEI data.

[0147] For example, the plurality of NAL unit data includes first encrypted video data and second encrypted video data, the custom SEI data includes first custom SEI data and second custom SEI data, and the first encrypted video data corresponds to the first custom SEI data, and the second encrypted video data corresponds to the second custom SEI data. In this example, the target encrypted video data of the first custom SEI data refers to the first encrypted video data, and the first custom SEI data is adjacent to the first encrypted video data. The target encrypted video data of the second custom SEI data refers to the second encrypted video data, and the second custom SEI data is adjacent to the second encrypted video data.

[0148] Specifically, the privacy-protected video may include encrypted video frames. During the video encoding process, the video encryption device may add a custom SEI data before and after the NAL unit data corresponding to each encrypted video frame, and record the privacy area position information corresponding to the encrypted video frame in the custom SEI data, so that the position input during decryption can be provided through the SEI data. In one example, in order to improve decoding efficiency, the present application may add a custom SEI data before the NAL unit data corresponding to each encrypted video frame.

[0149] Since the custom SEI data includes a fixed NAL start header (3 bytes) and privacy area position information (coordinates of each corner of the privacy area), the encoding method provided in this embodiment only needs to add relatively few bytes compared to a frame of image data.

[0150] The video decryption method provided in the embodiment of the present application is described below.

[0151] In some embodiments, the present application provides a video decryption method, and the following embodiments are described by taking the method applied to a video decryption device as an example. Figure 7 As shown, the video decryption method provided by this application includes the following steps:

[0152] S702: Obtain video encoding data; wherein the video encoding data is generated based on the video privacy protection method described in any of the above embodiments;

[0153] S704: Read the first SEI data of the video encoding data, and extract encryption parameter data from the first SEI data;

[0154] S706: Decrypt the encrypted parameter data using the preset password information, and obtain the initialization vector and encryption key according to the decryption result;

[0155] S708: Decrypt multiple NAL unit data of the video encoding data using the initialization vector and the encryption key, and obtain the decrypted video.

[0156] Specifically, in the case of having the correct password information, the present application can realize decryption and restoration based on the password information. During the decryption and restoration process, the video decryption device can first read the first SEI data of the video encoding data, and read the encryption parameter data from the first SEI data, and use the preset password information to decrypt the encrypted parameter data to obtain the initialization vector and the encryption key.

[0157] In one example, when the encrypted parameter data is obtained by encrypting the encryption key using preset password information, and the first SEI data of the video encoding data includes plaintext data of the initialization vector and the encrypted parameter data, the video decryption device can read the plaintext initialization vector and the ciphertext encryption key (i.e., the encrypted parameter data) from the first SEI data, and use the preset password information to decrypt the ciphertext encryption key to obtain the plaintext encryption key.

[0158] When the initialization vector and the encryption key are obtained, the video decryption device can use the initialization vector and the encryption key to decrypt the encrypted video frame to obtain the original video frame before encryption, and can perform subsequent processing (such as video playback, etc.) based on it.

[0159] In one example, when the video encoding data includes N encrypted video data and N custom SEI data, the video decryption device can read the privacy area position information in the N custom SEI data in sequence, and use the encryption key and initialization vector to derive the decryption key and decryption vector corresponding to the image channel, and then perform decryption calculations on the pixel points of the privacy area position information based on the decryption key and decryption vector to obtain the original RGB plaintext value of each pixel point.

[0160] The specific calculation process of the decryption key and decryption vector corresponding to each image channel can refer to the calculation process of the target key and target vector in the above embodiment, which will not be repeated here. The process of decrypting the pixel points of the privacy area location information can refer to the following expression:

[0161] R[num]=SM4_OFB_Decrypt(CR[num],key_1,IV_1)

[0162] G[num]=SM4_OFB_Decrypt(CG[num],key_2,IV_2)

[0163] B[num]=SM4_OFB_Decrypt(CB[num],key_3,IV_3)

[0164] After decryption, if you want to output a file that is completely consistent with the original plaintext file, you also need to remove the information added during encryption. Therefore, in some embodiments, the video file of the decrypted video includes N custom SEI data, where N is a positive integer. After obtaining the decrypted video, the following steps are also included:

[0165] Step B1: Delete N custom SEI data from the video file of the decrypted video;

[0166] Step B2: Delete the encryption parameter data from the first SEI data, for example, remove the ciphertext encryption key and the plaintext data of the initialization vector of the first SEI data.

[0167] After data deletion, the video file of the decrypted video is completely consistent with the video file of the original video, thereby achieving complete reversibility and satisfying the electronic forensic data requirements in the legal sense.

[0168] The video privacy protection device provided in the embodiment of the present application is described below. The video privacy protection device described below and the video privacy protection method described above can be referred to each other.

[0169] In some embodiments, Figure 8 As shown, the present application provides a video privacy protection device 800, which is applied to a video encryption device, including:

[0170] The data acquisition module 802 is used to acquire the original video, the initialization vector and the encryption key;

[0171] The privacy protection module 804 is used to encrypt the video frame to be encrypted of the original video according to the initialization vector and the encryption key, and obtain a privacy-protected video; wherein the video frame to be encrypted is a video frame including privacy information;

[0172] A parameter encryption module 806, configured to encrypt the initialization vector and / or the encryption key using a preset password information, and obtain encrypted parameter data;

[0173] The compression coding module 808 is used to compress and encode the privacy protection video according to the encryption parameter data using a lossless compression coding algorithm to obtain video coding data; wherein the video coding data includes multiple NAL unit data, at least one of the NAL unit data is SEI data, and the first SEI data records the encryption parameter data.

[0174] In some embodiments, the privacy protection module 804 of the present application includes:

[0175] A privacy region determination unit, configured to determine a privacy region of a target video frame; the target video frame is any of the video frames to be encrypted, and the privacy region is an image region corresponding to the privacy information;

[0176] A frame encryption unit is used to encrypt the image data corresponding to the privacy area according to the initialization vector and the encryption key.

[0177] In some embodiments, the frame encryption unit of the present application includes:

[0178] a key vector determination unit, configured to determine a first target vector, a second target vector, a third target vector, a first target key, a second target key and a third target key respectively according to the initialization vector and the encryption key;

[0179] A first channel value acquisition unit, used to acquire the channel value of each target pixel point in the first image channel to obtain a first channel value array; wherein each target pixel point is each pixel point located in the privacy area;

[0180] a first channel value encryption unit, configured to perform encryption calculation on the first channel value array by using the first target vector and the first target key, and obtain a first encrypted array according to the encryption calculation result of the first channel value array;

[0181] A second channel value acquisition unit, used to acquire the channel value of each target pixel point in the second image channel to obtain a second channel value array;

[0182] a second channel value encryption unit, configured to perform encryption calculation on the second channel value array by using the second target vector and the second target key, and obtain a second encrypted array according to the encryption calculation result of the second channel value array;

[0183] A third channel value acquisition unit, used to acquire the channel value of each target pixel point in the third image channel to obtain a third channel value array;

[0184] a third channel value encryption unit, configured to perform encryption calculation on the third channel value array by using the third target vector and the third target key, and obtain a third encrypted array according to the encryption calculation result of the third channel value array;

[0185] A pixel encryption unit, configured to determine the encrypted pixel value of each target pixel point based on the first encryption array, the second encryption array, and the third encryption array;

[0186] The pixel modification unit is used to modify the actual pixel value of each target pixel point into the encrypted pixel value of the target pixel point.

[0187] In some embodiments, the key vector determination unit of the present application includes:

[0188] A first hash calculation unit, configured to use a preset hash algorithm to perform a hash calculation on the initialization vector, the encryption key, and a preset first channel identifier to obtain a first hash value;

[0189] A first division unit, configured to divide the first Hash value into the first target vector and the first target key by using a preset division rule;

[0190] A second hash calculation unit, configured to use the preset hash algorithm to perform hash calculation on the initialization vector, the encryption key and a preset second channel identifier to obtain a second hash value; wherein the second channel identifier is different from the first channel identifier;

[0191] A second division unit, configured to divide the second Hash value into the second target vector and the second target key by adopting the preset division rule;

[0192] a third hash calculation unit, configured to use the preset hash algorithm to perform hash calculation on the initialization vector, the encryption key and a preset third channel identifier to obtain a third hash value; wherein the third channel identifier is different from the first channel identifier and the second channel identifier;

[0193] The third division unit is configured to divide the third Hash value into the third target vector and the third target key by adopting the preset division rule.

[0194] In some embodiments, the plurality of NAL unit data includes N encrypted video data and N custom SEI data, and the N encrypted video data correspond one to one with the N custom SEI data;

[0195] In the video encoding data, any of the custom SEI data is adjacent to the corresponding target encrypted video data, and any of the custom SEI data records the privacy area position information corresponding to the target encrypted video data;

[0196] The encrypted video data is NAL unit data for recording encrypted video frames, the encrypted video frames are obtained by encrypting the video frames to be encrypted, and N is the total number of video frames to be encrypted in the original video.

[0197] In some embodiments, the encryption parameter data is data obtained by encrypting the encryption key using the preset password information; the first SEI data records the initialization vector and the encryption parameter data.

[0198] The following is a description of a division unit for an apparatus provided in an embodiment of the present application. The division unit for an apparatus described below and the division unit for a method described above can be referenced to each other.

[0199] In some embodiments, Fig. 9 As shown, the present application provides a video decryption device 810, which is applied to a video decryption device, including:

[0200] A coding data acquisition module 812, used to acquire video coding data; wherein the video coding data is generated based on the video privacy protection method described in any of the above embodiments;

[0201] The SEI reading module 814 is used to read the first SEI data of the video encoding data and extract the encryption parameter data from the first SEI data;

[0202] The parameter decryption module 816 is used to decrypt the encrypted parameter data using the preset password information, and obtain the initialization vector and the encryption key according to the decryption result;

[0203] The video decryption module 818 is used to use the initialization vector and the encryption key to decrypt multiple NAL unit data of the video encoding data and obtain a decrypted video.

[0204] In some embodiments, the video file of the decrypted video includes N custom SEI data, where N is a positive integer. The video decryption device 810 of the present application also includes:

[0205] A first deleting unit, configured to delete the N custom SEI data from the video file of the decrypted video;

[0206] The second deleting unit is used to delete the encryption parameter data from the first SEI data.

[0207] In one embodiment, the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the video privacy protection method in any embodiment, and / or execute the steps of the video decryption method in any embodiment.

[0208] In one embodiment, the present application also provides a video encryption device, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the video privacy protection method in any embodiment.

[0209] In one embodiment, the present application further provides a video decryption device, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the video decryption method in any embodiment.

[0210] In some embodiments, the video encryption device and / or the video decryption device may be a computer device. Schematically, Fig.10 The internal structure diagram of a computer device provided in an embodiment of the present application is shown in FIG. 1 . In one example, the computer device may be a server. Fig.10 , the computer device 900 includes a processing component 902, which further includes one or more processors, and a memory resource represented by a memory 901, for storing instructions that can be executed by the processing component 902, such as an application. The application stored in the memory 901 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 902 is configured to execute instructions to perform the steps of the method described in any of the above embodiments.

[0211] The computer device 900 may further include a power supply component 903 configured to perform power management of the computer device 900, a wired or wireless network interface 904 configured to connect the computer device 900 to a network, and an input / output (I / O) interface 905. The computer device 900 may operate based on an operating system stored in the memory 901, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.

[0212] Those skilled in the art will understand that the internal structure of the computer device shown in the present application is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0213] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not clearly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. Herein, "one", "one", "said", "the" and "it" may also include plural forms, unless the context clearly indicates another way. A plurality refers to at least two cases, such as 2, 3, 5 or 8, etc. "And / or" includes any and all combinations of the relevant listed items.

[0214] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.

[0215] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A video privacy protection method, characterized in that: Applicable to video encryption equipment, including: Get the original video, initialization vector and encryption key; Encrypting the to-be-encrypted video frame of the original video according to the initialization vector and the encryption key, and obtaining a privacy-protected video; wherein the to-be-encrypted video frame is a video frame including privacy information; Encrypting the initialization vector and / or the encryption key using preset password information to obtain encryption parameter data; According to the encryption parameter data, the privacy protection video is compressed and encoded using a lossless compression encoding algorithm to obtain video encoding data; wherein the video encoding data includes multiple NAL unit data, at least one of the NAL unit data is SEI data, and the first SEI data records the encryption parameter data.

2. The method according to claim 1, characterized in that The step of encrypting the video frame to be encrypted of the original video according to the initialization vector and the encryption key comprises: Determine a privacy area of ​​a target video frame; the target video frame is any of the video frames to be encrypted, and the privacy area is an image area corresponding to the privacy information; The image data corresponding to the privacy area is encrypted according to the initialization vector and the encryption key.

3. The method according to claim 2, characterized in that The encrypting the image data corresponding to the privacy area according to the initialization vector and the encryption key includes: Determine, according to the initialization vector and the encryption key, a first target vector, a second target vector, a third target vector, a first target key, a second target key, and a third target key; Acquire the channel value of each target pixel point in the first image channel to obtain a first channel value array; wherein each target pixel point is each pixel point located in the privacy area; Using the first target vector and the first target key, perform encryption calculation on the first channel value array, and obtain a first encrypted array according to the encryption calculation result of the first channel value array; Obtaining the channel value of each target pixel in the second image channel to obtain a second channel value array; Using the second target vector and the second target key, perform encryption calculation on the second channel value array, and obtain a second encrypted array according to the encryption calculation result of the second channel value array; Obtaining the channel value of each target pixel in the third image channel to obtain a third channel value array; Using the third target vector and the third target key, perform encryption calculation on the third channel value array, and obtain a third encrypted array according to the encryption calculation result of the third channel value array; Determine the encrypted pixel value of each target pixel based on the first encrypted array, the second encrypted array, and the third encrypted array; The actual pixel value of each target pixel point is modified to the encrypted pixel value of the target pixel point.

4. The method according to claim 3, characterized in that The determining, according to the initialization vector and the encryption key, a first target vector, a second target vector, a third target vector, a first target key, a second target key, and a third target key, respectively, comprises: Using a preset hash algorithm, performing a hash calculation on the initialization vector, the encryption key, and a preset first channel identifier to obtain a first hash value; Using a preset division rule, the first Hash value is divided into the first target vector and the first target key; Using the preset hash algorithm, performing hash calculation on the initialization vector, the encryption key and a preset second channel identifier to obtain a second hash value; wherein the second channel identifier is different from the first channel identifier; Using the preset division rule, the second Hash value is divided into the second target vector and the second target key; Using the preset hash algorithm, performing hash calculation on the initialization vector, the encryption key and a preset third channel identifier to obtain a third hash value; wherein the third channel identifier is different from the first channel identifier and the second channel identifier; The preset division rule is adopted to divide the third Hash value into the third target vector and the third target key.

5. The method according to any one of claims 2 to 4, characterized in that: The plurality of NAL unit data include N encrypted video data and N custom SEI data, and the N encrypted video data correspond to the N custom SEI data one by one; In the video encoding data, any of the custom SEI data is adjacent to the corresponding target encrypted video data, and any of the custom SEI data records the privacy area position information corresponding to the target encrypted video data; The encrypted video data is NAL unit data for recording encrypted video frames, the encrypted video frames are obtained by encrypting the video frames to be encrypted, and N is the total number of video frames to be encrypted in the original video.

6. The method according to any one of claims 1 to 4, characterized in that: The encryption parameter data is data obtained by encrypting the encryption key using the preset password information; the first SEI data records the initialization vector and the encryption parameter data.

7. A video decryption method, characterized in that: Applicable to video decryption equipment, including: Acquire video encoding data; wherein the video encoding data is generated based on the video privacy protection method according to any one of claims 1 to 6; Reading first SEI data of the video encoding data, and extracting encryption parameter data from the first SEI data; Decrypting the encrypted parameter data using a preset password information, and obtaining an initialization vector and an encryption key according to the decryption result; The initialization vector and the encryption key are used to decrypt multiple NAL unit data of the video encoding data to obtain a decrypted video.

8. The method according to claim 7, characterized in that The video file of the decrypted video includes N custom SEI data, where N is a positive integer; After obtaining the decrypted video, the method further includes: Deleting N pieces of the custom SEI data from the video file of the decrypted video; The encryption parameter data is deleted from the first SEI data.

9. A video privacy protection device, characterized in that: Applicable to video encryption equipment, including: A data acquisition module, used to acquire original video, initialization vector and encryption key; A privacy protection module, configured to encrypt the video frame to be encrypted of the original video according to the initialization vector and the encryption key, and obtain a privacy-protected video; wherein the video frame to be encrypted is a video frame including privacy information; A parameter encryption module, used to encrypt the initialization vector and / or the encryption key using a preset password information, and obtain encrypted parameter data; A compression coding module is used to compress and encode the privacy protection video using a lossless compression coding algorithm according to the encryption parameter data, and obtain video coding data; wherein the video coding data includes multiple NAL unit data, at least one of the NAL unit data is SEI data, and the first SEI data records the encryption parameter data.

10. A video decryption device, characterized in that: Applicable to video decryption equipment, including: A coding data acquisition module, used to acquire video coding data; wherein the video coding data is generated based on the video privacy protection method according to any one of claims 1 to 6; A SEI reading module, used for reading the first SEI data of the video encoding data and extracting encryption parameter data from the first SEI data; A parameter decryption module, used to decrypt the encrypted parameter data using a preset password information, and obtain an initialization vector and an encryption key according to the decryption result; The video decryption module is used to decrypt multiple NAL unit data of the video encoding data using the initialization vector and the encryption key to obtain a decrypted video.

Images