CN117749974A - Video processing method, video restoration method and video restoration device - Google Patents

Abstract

The invention discloses a video processing method, restoration method and device. The video processing method includes: obtaining the driving video of the current vehicle; identifying sensitive information in the driving video; encrypting the sensitive information; generating a code corresponding to the encrypted sensitive information; and setting the code to In the driving video, the sensitive information in the driving video is hidden; and the processed driving video is uploaded to cloud storage. The video processing method disclosed in the embodiment of the present invention adopts two information processing methods of encryption and overwriting for sensitive information in the video, which can well solve the pain point of users being unable to remotely obtain driving videos for evidence collection, and can upload videos to the cloud to satisfy privacy requirements. Information protection requirements, and license plate information can be obtained to meet the needs of evidence collection.

Description

A video processing method, restoration method and device

Technical field

The present invention relates to the technical field of video processing, and in particular to a video processing method, restoration method and device.

Background technique

As an important reference for handling traffic accidents, driving videos are usually recorded by driving recorders and uploaded to the cloud for remote viewing by users. In order to protect vehicle information, sensitive information such as the license plate and portrait of the vehicle in the driving video needs to be coded or blurred before the video is uploaded. However, during the traffic accident handling process, the sensitive information processed using the above privacy protection cannot be restored after the user obtains the driving video, which results in the driving video not being able to play an actual role as evidence in the traffic accident process.

Contents of the invention

In order to solve at least one technical problem existing in the above-mentioned prior art, embodiments of the present invention provide a video processing method, restoration method and device. The technical solutions are as follows:

The first aspect provides a video processing method, including:

Get the driving video of the current vehicle;

Identify sensitive information in the driving video;

Encrypt the sensitive information;

Generate a code corresponding to the encrypted sensitive information;

Place the encoding in the driving video, and hide the sensitive information in the driving video;

Upload the processed driving video to cloud storage.

Further, the encryption process on the sensitive information includes:

The sensitive information is encrypted according to randomly generated encryption rules, and the encryption rules include the correspondence between randomly generated plaintext and ciphertext.

Further, placing the encoding in the driving video and hiding the sensitive information in the driving video includes:

Determine the superimposed position of the encoding in the driving video according to the position of the sensitive information;

Superimpose the encoding to the superimposed position in the driving video;

Obtain the pattern that blocks the sensitive information;

The pattern is superimposed on the position of the sensitive information so that the pattern blocks the sensitive information.

Further, determining the superimposed position of the encoding in the driving video based on the position of the sensitive information includes:

Identify the positional relationship between vehicles in the driving video;

According to the positional relationship of each vehicle in the image, the superimposed position of the code is determined correspondingly at a blank position in the driving video.

Further, the method also includes:

Obtain the unique identification information of the current vehicle;

Generate encryption rules corresponding to the identification information.

In a second aspect, a video restoration method is provided, comprising:

Obtain the driving video of the current vehicle stored in the cloud database, where the driving video includes codes corresponding to sensitive information;

Identify the code and restore the sensitive information corresponding to the code in the driving video.

Further, the obtaining the driving video in the cloud database includes:

Send a video acquisition request, where the video acquisition request includes identification information of the current vehicle;

After receiving the information that the identification information has been authenticated, the driving video in the cloud database is obtained.

Further, identifying the code and restoring the sensitive information corresponding to the code in the driving video includes:

Scan the encoding in the driving video to obtain the encrypted sensitive information;

The sensitive information corresponding to the encoding is parsed according to encryption rules.

Further, video restoration methods also include:

Obtain the unique identification information of the current vehicle;

Generate encryption rules corresponding to the identification information.

In a third aspect, a video processing device is provided, including:

Video acquisition module, used to obtain the driving video of the current vehicle;

An information identification module, used to identify sensitive information in the driving video;

An encryption module, used to encrypt the sensitive information;

An encoding module, used to generate encoding corresponding to the encrypted sensitive information;

A video processing module, configured to place the encoding in the driving video and hide the sensitive information in the driving video;

A transmission module is used to upload the driving video to cloud storage.

Further, the encryption module is specifically used for:

The sensitive information is encrypted according to a randomly generated encryption rule, where the encryption rule includes a correspondence between randomly generated plaintext and ciphertext.

Further, the video processing module includes:

The overlay position determination module is used to determine the overlay position encoded in the driving video based on the position of the sensitive information.

The occlusion pattern acquisition module is used to obtain patterns that occlusion sensitive information.

Further, the overlay position determination module is specifically used for:

Identify the positional relationship between vehicles in driving videos;

According to the positional relationship of each vehicle in the pattern, the superposition position of the code is determined corresponding to the blank position in the driving video.

Further, the video processing device also includes:

The identification information acquisition module is used to obtain the unique identification information of the current vehicle.

The encryption rule generation module is used to generate encryption rules corresponding to the identification information.

The fourth aspect provides a video restoration device, including:

A communication module, used to obtain the driving video stored in the cloud database, where the driving video includes codes corresponding to sensitive information;

A decoding module, used to identify the encoding and restore the sensitive information corresponding to the encoding in the driving video.

Further, the communication module is specifically used for:

Send a video acquisition request, which includes the identification information of the current vehicle;

After receiving the information that the identification information has been authenticated, the driving video in the cloud database is obtained.

Further, the decoding module includes:

The scanning module is used to scan the encoding in the driving video and obtain the encrypted sensitive information;

The decryption module is used to parse out the sensitive information corresponding to the encoding according to the encryption rules.

Furthermore, the decryption module is specifically used for:

Compare the encrypted sensitive information with the encryption rules to obtain the restored sensitive information. The encryption rules correspond to the identification information of the vehicle. The encryption rules include: the correspondence between randomly generated plaintext and ciphertext.

The beneficial effects brought by the technical solutions provided by the embodiments of the present invention are:

1. The video processing method disclosed in the embodiment of the present invention adopts two information processing methods: encryption and overwriting for sensitive information in the video. It can well solve the pain point of users being unable to remotely obtain driving videos for evidence collection. The video can be uploaded to the cloud. It meets the requirements for privacy information protection and can obtain license plate information to meet the needs of evidence collection.

2. In the video processing method disclosed in the embodiment of the present invention, the encryption rules are randomly generated based on the unique identification information of the current vehicle, and private encryption rules are configured for each vehicle. There are no rules and are not easy to be cracked.

3. The video restoration method disclosed in the embodiment of the present invention does not require the use of additional special tools or the need to transfer the video to a computer for restoration. Sensitive information in the video evidence can be quickly restored after an accident occurs.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without exerting creative efforts.

Figure 1 is a flow chart of a video processing method provided by an embodiment of the present invention;

Figure 2 is a schematic diagram of the original driving video provided by the embodiment of the present invention;

Figure 3 is a schematic diagram of a driving video after desensitization provided by an embodiment of the present invention;

Figure 4 is a schematic structural diagram of a video processing device module provided by an embodiment of the present invention;

Figure 5 is a flow chart of a video restoration method provided by an embodiment of the present invention;

Figure 6 is a schematic structural diagram of a video restoration device module provided by an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Some embodiments of the present invention are not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

Due to the need to protect private information, the driving video recorded by the vehicle equipment needs to be desensitized before being uploaded to the cloud database for storage. For example, the vehicle license plate information in the driving video needs to be desensitized in advance. At present, desensitization processing technology for videos often involves blocking the sensitive information in frame-by-frame screenshots of driving videos one by one and then uploading them. When restoring, it is necessary to restore frame by frame based on the correspondence between the screenshots in the uploaded video and the screenshots of the original video, so as to display the sensitive information in the video. This type of technology is more cumbersome to process videos, affecting video processing efficiency and user experience. The video processing method, restoration method and device disclosed in the embodiments of the present invention do not need to process the video frame by frame, and can not only perform video desensitization, but also simplify the video restoration process. The specific technical solutions are as follows:

As shown in Figure 1, a video processing method includes

S1. Obtain the driving video of the current vehicle.

As mentioned above, current vehicles are generally equipped with a vehicle-mounted video device (such as a driving recorder) for recording driving videos. During the driving process of the vehicle, the vehicle-mounted video device can record images of vehicles in front of the vehicle or around the vehicle in real time as a driving video. Driving videos can generally show the road conditions on which the current vehicle is traveling, the license plates of vehicles surrounding the current vehicle, vehicle brands and other information.

S2. Identify sensitive information in driving videos.

As mentioned above, sensitive information mainly includes license plate images, and may further include face images, advertising calls, and other images in videos that may lead to privacy leaks.

For example, a neural network algorithm can be used to identify the coordinate position of the sensitive information in the video image and parse the specific content of the sensitive information. For example, identify the license plate numbers in the left, center, and right lanes in front of the current vehicle in the video. It should be noted that since there may be many vehicle images displayed in the driving video, in general, there is no need to identify vehicles that are not adjacent to the current vehicle. In addition, sensitive information that cannot be displayed or is not clearly displayed in the driving video It is also possible not to identify it. In addition, text information in driving videos such as license plate information can also be identified using text extraction.

S3. Encrypt sensitive information.

As mentioned above, in order to facilitate information restoration, the encryption processing of sensitive information can use plaintext and ciphertext conversion methods, or common reversible encryption algorithms, such as: symmetric encryption algorithms (DES, AES, etc.), asymmetric encryption algorithms (RSA, etc.) . In the embodiment of the present invention, the encryption rules of the encryption process, or the keys used to verify the identities of the adder and the decryptor, are uniquely corresponding to the vehicle, so as to prevent the encryption or decryption of sensitive information from being misappropriated.

In one embodiment, step S3 specifically includes:

Sensitive information is encrypted according to randomly generated encryption rules, where the encryption rules include the correspondence between randomly generated plaintext and ciphertext.

The above has specifically disclosed the information encryption method based on plaintext to ciphertext conversion in the embodiment of the present invention. The encryption rules include the correspondence between randomly generated plaintext and ciphertext. The encryption rules uniquely correspond to the vehicle. For example, when the vehicle is powered on for the first time, a set of encryption rules is randomly generated, and the encryption rules correspond to the unique identification code of the vehicle. Encryption rules can be randomly generated based on preset plaintext and ciphertext libraries. Take license plate numbers as an example: 23 provinces can be randomly matched with 23 English letters, and letters and numbers can be randomly matched in the form of ASCII codes. For example: For example, if the word "京" is escaped to "28", after obtaining the encryption rules, it is easy to reverse "28" to the word "京". There is no operation to repair the video frame by frame, and it is very easy to implement. The above example focuses on encrypted recovery of license plates. Because the license plate is digital information, the content does not need to change after the same license plate is recognized, so the QR code can not change for a period of time, which has the advantage of not requiring frame-by-frame recovery. In addition, for example, for the encryption of face images, the recognized faces can be fixedly divided into several parts (such as 50*50 parts), and shuffled and rearranged according to random rules. When restoring the face images, the faces can be restored according to the rules. Restore sorting, fix frame by frame.

S4. Generate a code corresponding to the encrypted sensitive information.

As mentioned above, the encrypted sensitive information is converted into codes using encoding methods. The codes can be barcodes, QR codes, or combinations of numbers. In order to facilitate information acquisition, QR codes are preferred. It should be noted that sensitive information that cannot be displayed or cannot be displayed clearly in the driving video due to distance, weather, etc. does not need to be converted into encoding. In the embodiment of the present invention, the code corresponds to the encrypted sensitive information. Therefore, after the code is recognized, the encrypted information of the sensitive information can be obtained, but the sensitive information cannot be obtained directly. In addition, the encoding methods for different vehicles in the same driving video can be consistent or different. For example: the driving video shows the license plate numbers of three vehicles, and the license plate numbers of two of the vehicles can be encrypted and encoded using QR codes. , the license plate number of another vehicle can be encoded by barcode after being encrypted. Or the license plate numbers of the three vehicles are encoded using QR codes.

S5. Place the code in the driving video and hide the sensitive information in the driving video.

As mentioned above, the processing of driving videos in the embodiment of the present invention includes superimposed encoding and sensitive information hiding. The encoding is used to obtain the ciphertext of the sensitive information. Obtaining the original text of the sensitive information requires further decryption processing. The hiding of sensitive information can be done by pattern overlay or mosaic occlusion. In the embodiment of the present invention, encoding and sensitive information are processed separately, which is beneficial to facilitate the identification of encoding and ensure the shielding effect of sensitive information.

In one embodiment step S5 includes:

S51. Determine the overlay position of the encoding in the driving video based on the position of the sensitive information.

S52. Superimpose the encoding onto the superimposed position in the driving video.

S53. Obtain the pattern that blocks sensitive information.

S54. Superimpose the pattern on the position of the sensitive information so that the pattern blocks the sensitive information.

As mentioned above, in order to ensure that the code is identifiable, the superimposed position of the code generally does not coincide with the position of sensitive information in the driving video. The encoded overlay position can be a specially reserved position in the image of the driving video, or it can be a blank position in the recognized video image.

The pattern used to block sensitive information can be randomly selected from a preset pattern library, or it can be a mosaic image of sensitive information, or it can be unified into an opaque color block. The size of the pattern is required to be slightly larger or consistent with the size of the sensitive information to ensure that the pattern can completely block the sensitive information.

It should be noted that the order of execution of the overlaying of codes, acquisition of patterns, and shielding of sensitive information in the above steps can be exchanged. For example, steps S53 and S54 are executed first and then S51 and S52 are executed.

In one embodiment, step S52 includes:

Identify the positional relationship between vehicles in driving videos;

According to the positional relationship of each vehicle in the image, the superimposed position of the code is determined correspondingly at the blank position in the driving video.

As mentioned above, the vehicles displayed in the driving video are vehicles other than the current vehicle, and generally include vehicles in front of the current vehicle adjacent to the current vehicle, or vehicles surrounding the current vehicle. In order to intuitively map the sensitive information of the corresponding vehicle in the video, the encoded position relationship of each vehicle corresponds to the position relationship between vehicles. For example: convert the recognized license plate into a QR code, and superimpose the QR code of the corresponding vehicle into the video according to the positional relationship between the left, center, and right vehicles in front of the current vehicle. The above-mentioned blank positions generally refer to positions in the video image that do not have key information and sensitive information, such as: road surface, sky, hood of the current vehicle, etc. In this embodiment, by corresponding the positional relationship between the superimposed position of the code and the vehicle, the user can intuitively and quickly learn the code corresponding to the vehicle without additionally marking the vehicle information on the code.

S6. Upload the processed driving video to cloud storage.

As mentioned above, in the driving video processed by the method disclosed in the embodiment of the present invention, the sensitive information has been blocked and can be restored by encoding the sensitive information displayed in the video without exposing privacy, and can be uploaded to cloud storage.

For example, Figure 2 shows an unprocessed driving video. The video image shows that there are three driving vehicles in front of the current vehicle, which are respectively located in the left, middle, and right lanes in front of the current vehicle (i.e., the vehicles in front of the current vehicle). The position relationship is: left, center, right), and the license plate number of the vehicle is displayed on the vehicle. Therefore, the license plate number needs to be desensitized before uploading to the cloud. According to the video processing method disclosed in the embodiment of the present invention, first identify the position and content of the license plate in the driving video; use encryption rules to encrypt the license plate number; generate a corresponding QR code for the encrypted license plate number; use black The color block blocks the license plate number, and the QR code corresponding to the license plate number is superimposed on the image of the driving video according to the position of the vehicle. As shown in Figure 3, the license plates of the three vehicles in front of the current vehicle in the picture are all blocked by black blocks, and the corresponding codes of the three vehicles are superimposed on the current vehicle displayed in the video image in order of left, center, and right. on the hood.

In one embodiment, the method disclosed in the embodiment of the present invention further includes:

Obtain the unique identification information of the current vehicle;

Generate encryption rules corresponding to the identification information.

As mentioned above, the encryption rules in the embodiment of the present invention uniquely correspond to the identification information of the vehicle, which can ensure that different vehicles use different encryption rules and the encrypted sensitive information is not easy to be cracked. The identification information of the vehicle can be the vehicle's VIN code, license plate number or Face ID, etc. Encryption rules include the correspondence between randomly generated plaintext and ciphertext. The identification information and encryption rules obtained above can be stored in the local and cloud databases of the vehicle service system.

As shown in Figure 4, based on the video processing method disclosed in the present invention, an embodiment of the present invention also provides a video processing device, including:

The video acquisition module 401 is used to acquire the driving video of the current vehicle.

The information identification module 402 is used to identify sensitive information in driving videos.

Encryption module 403 is used to encrypt sensitive information.

The encoding module 404 is used to generate encoding corresponding to the encrypted sensitive information.

The video processing module 405 is used to place encoding in the driving video and hide sensitive information in the driving video.

The transmission module 406 is used to upload the driving video to cloud storage.

As mentioned above, driving videos can generally display information such as the road conditions on which the current vehicle is traveling, the license plates of vehicles surrounding the current vehicle, and vehicle brands. The information identification module 402 can use a neural network algorithm to identify the coordinate position of sensitive information in the video image and parse the specific content of the sensitive information. The encryption module 403 can use plaintext and ciphertext conversion methods, or common reversible encryption algorithms, such as symmetric encryption algorithms (DES, AES, etc.), asymmetric encryption algorithms (RSA, etc.). Specifically, the encoding module 404 can perform a general encoding method to generate any one of barcodes, QR codes, or digital combinations corresponding to sensitive information. The video processing module 405 can hide sensitive information in a pattern overlay blocking method or a mosaic blocking method.

In one embodiment, the encryption module 403 is specifically used to:

Sensitive information is encrypted according to randomly generated encryption rules, where the encryption rules include the correspondence between randomly generated plaintext and ciphertext.

As mentioned above, the encryption rules uniquely correspond to the vehicle, and the encryption rules can be randomly generated based on the preset plaintext and ciphertext libraries.

In one embodiment, video processing module 405 includes:

The overlay position determination module is used to determine the overlay position encoded in the driving video based on the position of the sensitive information.

The occlusion pattern acquisition module is used to obtain patterns that occlusion sensitive information.

The overlay module is used to superimpose the encoding onto the overlay position in the driving video; and overlay the pattern onto the position of sensitive information so that the pattern blocks the sensitive information.

As mentioned above, in order to ensure the display effect of the code in the driving video and the shielding effect of sensitive information, the superimposed position of the code generally does not overlap with the position of sensitive information in the driving video. The superimposed position of the code can be a dedicated position reserved in the image of the driving video, or it can be a blank position in the video image identified. The superimposed position of the pattern needs to be able to cover the position of sensitive information.

Further, the overlay position determination module is specifically used for:

Identify the positional relationship between vehicles in driving videos;

According to the positional relationship of each vehicle in the image, the superimposed position of the code is determined correspondingly at the blank position in the driving video.

As mentioned above, the positional relationship of the encoded superposition position corresponds to the positional relationship of the corresponding vehicle. Blank locations generally refer to locations in video images that do not contain key or sensitive information, such as the road, sky, hood of the current vehicle, etc.

In one embodiment, the video processing device disclosed in the present invention further includes:

The identification information acquisition module is used to obtain the unique identification information of the current vehicle.

The encryption rule generation module is used to generate encryption rules corresponding to the identification information.

As mentioned above, the identification information of the vehicle may be the vehicle's VIN code, license plate number, or Face ID, etc. Encryption rules include the correspondence between randomly generated plaintext and ciphertext.

The video processing method and device disclosed in the embodiments of the present invention adopt two information processing methods: encryption and overwriting for sensitive information in the video, which can well solve the pain point of users being unable to remotely obtain driving videos for evidence collection. Videos can be uploaded to the cloud. It meets the requirements for privacy information protection and can obtain license plate information to meet the needs of evidence collection. In the video processing method disclosed in the embodiment of the present invention, encryption rules are randomly generated based on the unique identification information of the current vehicle, and private encryption rules are configured for each vehicle. There are no rules and are not easy to be cracked.

As shown in Figure 5, an embodiment of the present invention also discloses a video restoration method, which includes:

S1’ obtains the driving video of the current vehicle stored in the cloud database. The driving video includes codes corresponding to sensitive information.

As mentioned above, the driving video is recorded by a vehicle-mounted video device. The driving video has been desensitized, in which sensitive information is blocked, and the video image includes a code corresponding to the sensitive information.

S2’ identifies the code and restores the sensitive information corresponding to the code in the driving video.

As mentioned above, the encrypted information of sensitive information is obtained after identifying the encoding, and then the decryption rules are used to restore the encrypted information to sensitive information.

In one embodiment, step S1' includes:

Send a video acquisition request, which includes the identification information of the current vehicle;

After receiving the information that the identification information has been authenticated, the driving video in the cloud database is obtained.

As mentioned above, the identification information in the video acquisition request is used to verify the identity of the requesting terminal that sends the request. In addition to identification information, the video acquisition request may also include: the time of the driving video requested, the recording address of the driving video, etc. For example, after receiving the video acquisition request, the vehicle service system compares the vehicle identification information in the request with the actual vehicle identification information. After the comparison is successful, the cloud database sends the corresponding driving video to the requesting terminal.

In one embodiment, step S2' includes:

Scan the encoding in the driving video to obtain encrypted sensitive information;

Parse the sensitive information corresponding to the encoding according to the encryption rules.

As mentioned above, the requesting terminal scans the encoding in the driving video to obtain the encrypted information of the sensitive information, and uses the encryption rules in the requesting terminal to restore the sensitive information, where the encryption rules are the encryption corresponding to the current vehicle that the requesting terminal downloads from the cloud database after passing the identity verification. rule.

In one embodiment, sensitive information corresponding to the encoding is parsed according to encryption rules, including:

Compare the encrypted sensitive information with the encryption rules to obtain the restored sensitive information. The encryption rules correspond to the identification information of the vehicle. The encryption rules include: the correspondence between randomly generated plaintext and ciphertext.

As shown in Figure 3, after the user obtains the driving video from the cloud database, he scans the QR code in the video image with his mobile phone, and the mobile phone can directly decrypt and display the license plate number of the vehicle corresponding to the QR code. Therefore, when restoring the encrypted information in the video, the restoration method disclosed in the embodiment of the present invention does not need to process the screenshots of the driving video frame by frame, and only needs to scan the corresponding code to obtain sensitive information.

In one embodiment, the video restoration method disclosed in the present invention also includes:

Send the identification information of the current vehicle, where the identification information uniquely corresponds to the vehicle;

Receive the encryption rules corresponding to the identification information sent by the cloud database.

As mentioned above, for example, when the user uses the APP for the first time, he or she needs to enter the vehicle's VIN code and send it to the cloud database. The APP automatically downloads the encryption rules corresponding to this VIN code from the cloud algorithm library.

As shown in Figure 6, based on the video restoration method disclosed in the embodiment of the present invention, an embodiment of the present invention also provides a video restoration device, including:

The communication module 601 is used to obtain the driving video stored in the cloud database. The driving video includes codes corresponding to sensitive information.

The decoding module 602 is used to identify the encoding and restore the sensitive information corresponding to the encoding in the driving video.

In one embodiment, the communication module 601 is specifically used to:

Send a video acquisition request, which includes the identification information of the current vehicle;

After receiving the information that the identification information has been authenticated, the driving video in the cloud database is obtained.

As mentioned above, the identification information in the video acquisition request is used to verify the identity of the requesting terminal that sends the request. In addition to identification information, the video acquisition request may also include: the time of the driving video requested, the recording address of the driving video, etc.

In one embodiment, the decoding module 602 includes:

The scanning module is used to scan the encoding in the driving video and obtain the encrypted sensitive information;

The decryption module is used to parse out the sensitive information corresponding to the encoding according to the encryption rules.

In one embodiment, the decryption module is specifically used for:

Compare the encrypted sensitive information with the encryption rules to obtain the restored sensitive information. The encryption rules correspond to the identification information of the vehicle. The encryption rules include: the correspondence between randomly generated plaintext and ciphertext.

The video restoration method and device disclosed in the embodiments of the present invention do not require the use of additional special tools or the need to transfer the video to a computer for restoration. Sensitive information in the video evidence can be quickly restored after an accident occurs.

The technical solutions provided by this application have been introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; At the same time, for those of ordinary skill in the art, there will be changes in the specific implementation and application scope based on the ideas of this application. In summary, the contents of this specification should not be construed as limiting this application.

All the above optional technical solutions can be combined in any way to form optional embodiments of the present invention, and will not be described again one by one.

The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection of the present invention. within the range.

Claims (10)

1. A video processing method, comprising:

acquiring a driving video of a current vehicle;

identifying sensitive information in the driving video;

encrypting the sensitive information;

generating a code corresponding to the encrypted sensitive information;

the codes are placed in the driving video, and the sensitive information in the driving video is subjected to hiding treatment;

and uploading the processed driving video to a cloud for storage.

2. The method of claim 1, wherein said encrypting said sensitive information comprises:

encrypting the sensitive information according to a randomly generated encryption rule, wherein the encryption rule comprises a corresponding relation between a randomly generated plaintext and a randomly generated ciphertext.

3. The method of claim 1, wherein said placing said code in said live video and concealing said sensitive information in said live video comprises: comprising the following steps:

determining the superposition position of the codes in the driving video according to the position of the sensitive information;

superposing the codes at superposition positions in the driving video;

acquiring a pattern for shielding the sensitive information;

and superposing the pattern on the position of the sensitive information, so that the pattern shields the sensitive information.

4. A method according to claim 3, wherein said determining the overlay position of said code in said driving video based on the position of said sensitive information comprises:

identifying the position relation among vehicles in the driving video;

and correspondingly determining the superposition position of the codes at the blank position in the driving video according to the position relation of each vehicle in the image.

5. The method of any one of claims 1-4, wherein the method further comprises:

acquiring unique identification information of the current vehicle;

and generating an encryption rule corresponding to the identification information.

6. A video restoration method, comprising:

acquiring a driving video of a current vehicle stored in a cloud database, wherein the driving video comprises codes corresponding to sensitive information;

and identifying the code, and restoring the sensitive information corresponding to the code in the driving video.

7. The method of claim 6, wherein the obtaining the driving video in the cloud database comprises:

transmitting a video acquisition request, wherein the video acquisition request comprises identification information of the current vehicle;

and after receiving the information passing through the identification information authentication, acquiring the driving video in a cloud database.

8. The method of claim 6, wherein the identifying the code to restore the sensitive information in the driving video corresponding to the code comprises:

scanning the codes in the driving video to acquire the encrypted sensitive information;

and analyzing the sensitive information corresponding to the code according to an encryption rule.

9. A video processing apparatus, comprising:

the video acquisition module is used for acquiring the driving video of the current vehicle;

the information identification module is used for identifying sensitive information in the driving video;

the encryption module is used for carrying out encryption processing on the sensitive information;

the coding module is used for generating codes corresponding to the encrypted sensitive information;

the video processing module is used for placing the codes in the driving video and hiding the sensitive information in the driving video;

and the transmission module is used for uploading the driving video to a cloud for storage.

10. A video reproduction apparatus, comprising:

the communication module is used for acquiring driving videos stored in the cloud database, wherein the driving videos comprise codes corresponding to the sensitive information;

and the decoding module is used for identifying the codes and restoring the sensitive information corresponding to the codes in the driving video.