CN114339307A

CN114339307A - Video desensitization method and device, computer equipment and storage medium

Info

Publication number: CN114339307A
Application number: CN202111667059.2A
Authority: CN
Inventors: 林新星; 钟华平; 何聪辉
Original assignee: Shanghai Sensetime Lingang Intelligent Technology Co Ltd
Current assignee: Shanghai Sensetime Lingang Intelligent Technology Co Ltd
Priority date: 2021-12-31
Filing date: 2021-12-31
Publication date: 2022-04-12

Abstract

The present disclosure provides a video desensitization method, apparatus, computer device and storage medium, wherein the method comprises: receiving an uploaded video to be processed; receiving a video desensitization task for a video to be processed; determining image content corresponding to the target desensitization content type in the video to be processed based on the target desensitization content type in the video desensitization task; and desensitizing the image content to obtain a desensitized target video.

Description

Video desensitization method and device, computer equipment and storage medium

Technical Field

The present disclosure relates to the field of image processing technologies, and in particular, to a video desensitization method, apparatus, computer device, and storage medium.

Background

With the increasing importance of the data security problem, how to distribute the collected video data to the outside on the basis of protecting the privacy and the security of the user is a problem worthy of research.

When a user needs to perform desensitization processing on a shot video, content parts needing desensitization in each frame of video image usually need to be identified manually, and related processing is performed on the content parts by means of some drawing software or video processing software, so that the whole processing process is relatively complicated and consumes a long time.

Disclosure of Invention

The embodiment of the disclosure at least provides a video desensitization method, a video desensitization device, computer equipment and a storage medium.

In a first aspect, an embodiment of the present disclosure provides a video desensitization method, including:

receiving an uploaded video to be processed;

receiving a video desensitization task for the video to be processed;

determining image content corresponding to the target desensitization content type in the video to be processed based on the target desensitization content type in the video desensitization task;

and desensitizing the image content to obtain a desensitized target video.

In this embodiment, on one hand, after the video uploaded by the user and the video desensitization task are acquired, the embodiment of the present disclosure can implement automatic desensitization processing on the video to be processed, and improve the efficiency of acquiring the target video while ensuring the security of the video data. On the other hand, the embodiment of the disclosure can support selective processing of image content corresponding to multiple desensitization content types, that is, not only can the removal of different types of image content in the video to be processed be realized, but also the selection of a target desensitization content type from the multiple desensitization content types in a mode of uploading a video desensitization task is supported, so that the flexibility of desensitization processing of the video to be processed is improved.

In a possible implementation, the receiving the uploaded to-be-processed video includes:

receiving a plurality of uploaded videos and video identifications corresponding to the videos; the video identification represents whether each video needs desensitization treatment or not;

and based on the video identification, taking the video needing desensitization processing as the video to be processed.

Based on the embodiment, the video to be processed can be accurately determined from the uploaded video based on the video identification.

In one possible implementation, the pending video is multiple, and the receiving of the video desensitization task for the pending video includes:

receiving a video desensitization task for each of the pending videos.

According to the implementation mode, based on the received video desensitization task of each video to be processed, the sensitive information in each video to be processed can be accurately removed, and the safety of the obtained target video after each desensitization process is improved.

In one possible implementation, in the case that the video to be processed is a video in a captured road environment, the target desensitization content type includes: at least one of human face, license plate and video characters.

According to the embodiment, the information such as the face, the license plate and the video characters is personalized sensitive data which often appears in the video shot under the road environment, and the desensitization content type matched with the three information is set, so that the safety of the shot road environment video can be improved, and the information leakage of users is avoided.

In one possible embodiment, the method further comprises:

updating the processing state of the video to be processed according to the current progress of desensitization processing on the video to be processed;

and after the processing state indicates that the video to be processed successfully completes desensitization processing, changing the operation state of the video to be processed into a downloadable state.

According to the embodiment, the processing state of each video to be processed is updated, so that the real-time processing state of each video to be processed can be displayed for a user, and the operation state of each video to be processed can be timely changed; and the target video after desensitization is acquired in time by downloading the to-be-processed video in a downloadable state.

In one possible embodiment, the method further comprises:

and responding to a downloading request of a user for the to-be-processed video in a downloadable state, and downloading the processed target video corresponding to the to-be-processed video to a local appointed storage position.

According to the embodiment, the desensitized target video is downloaded to the local, so that the target video can be processed locally, for example, the target video is watched, the content of the target video is intercepted, and the like.

In a possible implementation, after acquiring the target video, the method further includes:

and playing the processed target video corresponding to the desensitized content type selected by the user.

According to the implementation mode, the effect of removing the image contents respectively corresponding to the desensitization content types from the to-be-processed video can be previewed in advance by playing the processed target video corresponding to the desensitization content type selected by the user.

In one possible implementation, determining, based on a target desensitization content type in the video desensitization task, image content in the to-be-processed video corresponding to the target desensitization content type includes:

identifying a target object with the same type as the target desensitization content in each frame of video image of the video to be processed;

desensitizing the image content to obtain a desensitized target video, comprising:

and carrying out fuzzy processing on the identified target object to obtain the target video.

According to the implementation mode, the identified target object is the image content needing desensitization, based on accurate identification of the target object, the identified target object is subjected to fuzzy processing, accurate desensitization of the image content needing desensitization can be achieved, and the target video with high safety is obtained.

In a possible implementation manner, the identification of the target object of the same type as the target desensitization content in each frame of video image of the video to be processed is identified by using a pre-trained target neural network, which is a neural network trained by using a plurality of sample images and capable of being used for identifying at least one target object of the same type as the target desensitization content.

According to the embodiment, the trained target neural network has reliable identification precision, and each frame of video image of the video to be processed is identified by using the target neural network, so that the target object of each frame of video image can be accurately determined. Furthermore, based on fuzzy processing of the identified target object, accurate desensitization of the video to be processed can be achieved.

In a possible implementation manner, the blurring the identified target object to obtain the target video includes:

for each frame of the video image, in response to identifying a plurality of the target objects in the video image, matting out an initial sub-image corresponding to each of the target objects from the video image;

blurring each initial sub-image to obtain a target sub-image corresponding to each initial sub-image;

and replacing the initial sub-image corresponding to the video image by adopting each target sub-image, and obtaining the target video based on each replaced video image.

According to the embodiment, the initial sub-images corresponding to the target objects are extracted, and the initial sub-images are subjected to the fuzzy processing, so that compared with the operation of directly performing the fuzzy processing on the whole video image, the overall fuzzy processing efficiency can be improved.

In a possible implementation, for any of the initial sub-images, the blurring process is performed on the initial sub-image according to the following steps:

dividing the initial sub-image into a plurality of processing regions;

determining a target pixel value corresponding to each processing region based on the pixel value of each pixel point in each processing region;

and replacing the pixel values corresponding to the pixel points in each processing area with the determined target pixel values to obtain the target sub-image corresponding to the initial sub-image.

In this embodiment, the pixel values of the pixel points in different processing regions are different, the obtained target pixel value corresponding to each processing region is also different, and the pixel values of the processing regions are replaced by using different target pixel values, so that the processing regions in the target sub-image obtained after replacement are different in pixel value, that is, color change, and the target sub-image obtained after replacement is more natural.

In a possible implementation manner, the determining a target pixel value corresponding to each processing region based on pixel values corresponding to respective pixel points in each processing region includes:

and determining a pixel value mean value corresponding to each processing area based on the pixel value of each pixel point in each processing area, and taking the pixel value mean value corresponding to each processing area as the target pixel value corresponding to the processing area.

In this embodiment, the pixel mean value is used as the target pixel value, so that the target pixel value can represent the concentration degree of each pixel point of the corresponding processing region, and further the pixel values of the processing regions after the pixel values are replaced are more balanced.

and determining a pixel value extreme value corresponding to each processing area based on the pixel value of each pixel point in each processing area, and taking the pixel value extreme value corresponding to each processing area as the target pixel value corresponding to the processing area.

This embodiment can make the difference in pixel value between the respective processing areas after replacing the pixel value more conspicuous if the pixel extremum is used as the target pixel value.

In a second aspect, embodiments of the present disclosure also provide a video desensitization apparatus, including:

the receiving module is used for receiving the uploaded video to be processed; and receiving a video desensitization task for the video to be processed;

the determining module is used for determining image content corresponding to the target desensitization content type in the video to be processed based on the target desensitization content type in the video desensitization task;

and the processing module is used for carrying out desensitization processing on the image content to obtain a desensitized target video.

In a possible implementation manner, the receiving module is configured to receive a plurality of uploaded videos and video identifiers corresponding to the videos; the video identification represents whether each video needs desensitization treatment or not;

In a possible implementation manner, the number of the videos to be processed is multiple, and the receiving module is configured to receive a video desensitization task for each of the videos to be processed.

In a possible implementation manner, the processing module is further configured to update the processing state of the video to be processed according to a current progress of desensitization processing on the video to be processed;

In a possible embodiment, the apparatus further comprises:

and the downloading module is used for responding to a downloading request of a user for the to-be-processed video in a downloadable state, and downloading the processed target video corresponding to the to-be-processed video to a local appointed storage position.

In a possible embodiment, the apparatus further comprises:

and the display module is used for playing the processed target video corresponding to the desensitization content type selected by the user after the target video is obtained.

In a possible implementation manner, the determining module is configured to identify a target object of the same type as the target desensitization content in each frame of video image of the video to be processed;

and the processing module is used for carrying out fuzzy processing on the identified target object to obtain the target video.

In a possible implementation, the processing module is configured to, for each frame of the video image, in response to identifying a plurality of the target objects in the video image, extract an initial sub-image corresponding to each of the target objects from the video image;

and replacing the initial sub-image corresponding to the to-be-video image by adopting each target sub-image, and obtaining the target video based on each replaced video image.

In a possible implementation, the processing module is configured to, for any of the initial sub-images, perform blurring on the initial sub-image according to the following steps:

dividing the initial sub-image into a plurality of processing regions;

In a possible implementation manner, the processing module is configured to determine a pixel value mean value corresponding to each processing region based on pixel values of respective pixels in each processing region, and use the pixel value mean value corresponding to each processing region as the target pixel value corresponding to the processing region.

In a possible implementation manner, the processing module is configured to determine a pixel value extremum corresponding to each processing region based on pixel values of respective pixel points in each processing region, and use the pixel value extremum corresponding to each processing region as the target pixel value corresponding to the processing region.

In a third aspect, this disclosure also provides a computer device, a processor, and a memory, where the memory stores machine-readable instructions executable by the processor, and the processor is configured to execute the machine-readable instructions stored in the memory, and when the machine-readable instructions are executed by the processor, the machine-readable instructions are executed by the processor to perform the steps in the first aspect or any one of the possible implementations of the first aspect.

In a fourth aspect, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, where the computer program is executed to perform the steps in the first aspect or any one of the possible implementation manners of the first aspect.

For the description of the effects of the video desensitization apparatus, the computer device, and the computer-readable storage medium, reference is made to the description of the video desensitization method, which is not repeated herein.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.

Fig. 1 illustrates a flow chart of a video desensitization method provided by an embodiment of the present disclosure;

fig. 2 is a schematic diagram illustrating a comparison between a to-be-processed video and a target video corresponding to the to-be-processed video provided by an embodiment of the present disclosure;

fig. 3 is a schematic diagram illustrating a video uploading interface provided by an embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating a data selection interface provided by an embodiment of the present disclosure;

FIG. 5 is a schematic diagram illustrating a task status indication page provided by an embodiment of the present disclosure;

FIG. 6 is a schematic diagram illustrating a video details page provided by an embodiment of the present disclosure;

fig. 7 shows a schematic illustration of a presentation of a video list page provided by an embodiment of the disclosure;

fig. 8 is a schematic illustration showing a download progress showing window provided by the embodiment of the disclosure;

FIG. 9 is a schematic illustration showing a target video preview page provided by an embodiment of the present disclosure;

fig. 10 shows a schematic diagram of a video desensitization apparatus provided by an embodiment of the present disclosure;

fig. 11 shows a schematic structural diagram of a computer device provided by an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of embodiments of the present disclosure, as generally described and illustrated herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the disclosure, as claimed, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

Furthermore, the terms "first," "second," and the like in the description and in the claims, and in the drawings described above, in the embodiments of the present disclosure are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein.

Reference herein to "a plurality or a number" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

Research shows that in all industries at present, there may be demands for acquiring and using videos, but sensitive contents may exist in videos shot by using shooting equipment, for example, face information and license plate information included in driving videos shot by a driving recorder, and privacy character information (such as user passwords and user birthdays) in screen recording videos. If the sensitive content in the video is not processed, the sensitive content is directly published externally or directly acquired by a required user, the problem of sensitive content leakage is caused, and the data security is greatly influenced. Therefore, how to remove sensitive content in video data to improve the security of the video data becomes an important issue, but today, there is no reasonable video desensitization procedure for removing the sensitive content.

Based on the above research, the present disclosure provides a video desensitization method, apparatus, computer device, and storage medium, and the video desensitization method provided by the embodiment of the present disclosure includes: on one hand, based on the method, automatic desensitization processing of the video to be processed can be realized only by acquiring the video uploaded by a user and the video desensitization task, and the efficiency of acquiring the target video is improved while the safety of video data is ensured. On the other hand, the embodiment of the disclosure can support selective processing of image content corresponding to multiple desensitization content types, that is, not only can the removal of different types of image content in the video to be processed be realized, but also the selection of a target desensitization content type from the multiple desensitization content types in a mode of uploading a video desensitization task is supported, so that the flexibility of desensitization processing of the video to be processed is improved.

The above-mentioned drawbacks are the results of the inventor after practical and careful study, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to the above-mentioned problems should be the contribution of the inventor in the process of the present disclosure.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

It should be noted that specific terms mentioned in the embodiments of the present disclosure include:

mp 4: a set of compression coding standards for audio and video information;

avi: audio video interleaved, an audio video interleaved format, is a multimedia container format introduced by microsoft corporation;

wmv: windows media video format is a generic name of a series of video codecs developed by microsoft and related video coding formats;

3 gp: 3rd generation partnership project, third generation partnership project, a video coding container format for 3G streaming media;

and zip: a file format for data compression and document storage;

tar: a file format for data compression and document storage;

7 z: a brand new compression format, which has an extremely high compression ratio;

gz: a compressed file format.

To facilitate understanding of the present embodiment, a detailed description is first given of a video desensitization method disclosed in the embodiments of the present disclosure, where an execution subject of the video desensitization method provided in the embodiments of the present disclosure is generally a computer device with certain computing power, and in some possible implementations, the video desensitization method may be implemented by a processor calling computer-readable instructions stored in a memory.

The video desensitization method provided by the embodiment of the present disclosure is described below by taking an execution subject as a computer device as an example.

As shown in fig. 1, a flow chart of a video desensitization method provided for the embodiment of the present disclosure may include the following steps:

s101: and receiving the uploaded to-be-processed video.

Here, the video to be processed may be a video captured by any video capture device, and may include objects corresponding to one or more desensitization content types, and the object corresponding to each desensitization content type may include one or more objects. For example, the video to be processed may be a video including a plurality of faces, and a video including a plurality of faces and a plurality of license plates.

The desensitization content type may be a type of sensitive content included in the video to be processed, for example, in a case that the sensitive content is face information, the desensitization content type may be a face type, and an object included in the video to be processed and corresponding to the desensitization content type may be each face appearing in the video; under the condition that the sensitive content is license plate information, the desensitization content type can be a license plate type, and an object corresponding to the desensitization content type and included in the video to be processed can be each license plate appearing in the video.

In specific implementation, when a user needs to remove sensitive content in at least one video, the user can log in a video desensitization platform corresponding to the video desensitization method provided by the embodiment of the present disclosure at a client, and after the logging is successful, the user enters a video upload interface corresponding to the video desensitization platform. Furthermore, the user can upload each video as the to-be-processed video in the video uploading interface, and then the server can receive the to-be-processed video uploaded by the client.

S102: a video desensitization task for a video to be processed is received.

Here, the video desensitization task may be a task uploaded by a user to remove image content in the to-be-processed video that matches the target desensitization content type.

In specific implementation, a user may select one or more target desensitization content types for a video to be processed from a plurality of desensitization content types displayed in a data selection interface corresponding to the desensitization platform. Then, the client can create image content corresponding to the target desensitization content type in the video to be processed by the user based on the target desensitization content type selected by the user, perform video desensitization tasks of desensitization processing, and send the video desensitization tasks to the server. Taking the target desensitization content type including the face type as an example, the generated video desensitization task may be a face desensitization task for removing each frame of video image in the video to be processed.

Further, the server side can acquire the uploaded video desensitization task for the to-be-processed video.

The multiple desensitization content types displayed in the data selection interface are types which are preset and respectively correspond to various sensitive contents which may appear in the video. The number of desensitization content types may be set according to the actual application requirements and is not limited herein. Illustratively, the plurality of desensitization content types may be a face type, a license plate type, a text information type, a geographic marking information type, a building number information, and the like, respectively.

The target desensitization content type is one or more desensitization content types selected by a user from a plurality of desensitization content types.

S103: and determining image content corresponding to the target desensitization content type in the video to be processed based on the target desensitization content type in the video desensitization task.

Here, the image content corresponding to the target desensitization content type is image content corresponding to an image area where each target object matched with the target desensitization content type is located in each frame of video image in the video to be processed. For example, when the target desensitization content type is a license plate type, the image content corresponding to the target desensitization content type is the image content corresponding to the image area where the license plate of each frame of video image is located.

In specific implementation, video decoding and frame cutting processing can be performed on a video to be processed to obtain each frame of video image included in the video to be processed; and determining a target desensitization content type based on the received video desensitization task. The generated video desensitization task may then be performed to separately determine image content in each frame of video images that corresponds to the target desensitization content type.

In the case where the video desensitization task corresponds to multiple target desensitization content types, image content corresponding to each target desensitization content type in each frame of video images may be determined.

Here, if there is no image content corresponding to the target desensitization content type in any one frame of video image, the desensitization process described in S104 described below may not be performed on that frame of video image.

S104: and desensitizing the image content to obtain a desensitized target video.

Here, the desensitization processing may be a deletion processing, a replacement processing, an image information overlay processing (such as mosaic overlay) or the like for the image content, and the purpose of the desensitization processing is to perform occlusion for the image content matching the target desensitization content type to ensure the security of the image content.

The target video is a video which does not include image content corresponding to the target desensitization content type, and each frame of video image in the target video does not include image content corresponding to the target desensitization content type.

For example, for image content which is matched with the target desensitization content type in each frame of video image, the image content may be covered by using a mosaic covering method, so as to obtain each frame of video image after desensitization processing. Then, the target video can be obtained by combining the sequence of the video images of the frames after the desensitization processing in the video to be processed and the sequence of the video images without the image content corresponding to the target desensitization content type in the video to be processed.

As shown in fig. 2, a schematic diagram of a comparison between a to-be-processed video and a target video corresponding to the to-be-processed video is provided, where the to-be-processed video includes two running vehicles, i.e., a vehicle 1 and a vehicle 2, the vehicle 1 includes two faces and one license plate, and the vehicle 2 includes one license plate and one face, and in the target video, the vehicle 1 includes two faces and one license plate that have been subjected to mosaic processing, and one license plate and one face in the vehicle 2 have also been subjected to mosaic processing.

After the target video is obtained, the video format of the target video can be converted into a preset target format, so that the video format of the target video is unified.

Thus, the video desensitization method provided by the embodiment of the present disclosure includes: on one hand, based on the method, automatic desensitization processing of the video to be processed can be realized only by acquiring the video uploaded by a user and the video desensitization task, and the efficiency of acquiring the target video is improved while the safety of video data is ensured. On the other hand, the embodiment of the disclosure can support selective processing of image content corresponding to multiple desensitization content types, that is, not only can the removal of different types of image content in the video to be processed be realized, but also the selection of a target desensitization content type from the multiple desensitization content types in a mode of uploading a video desensitization task is supported, so that the flexibility of desensitization processing of the video to be processed is improved.

In one embodiment, for S101, the following steps may be performed:

s101-1: and receiving the uploaded videos and video identifications corresponding to the videos.

Here, each video uploaded by the user may correspond to a video identifier capable of uniquely identifying the video. In addition to identifying the video, the video identification may also include indication information that can characterize whether a desensitization process is required for the corresponding video.

In specific implementation, a video uploading interface can be displayed for a user; the video uploading interface comprises first indication information indicating an input video identifier and second indication information indicating a to-be-processed video corresponding to the video identifier.

Here, the video upload interface is an interface for managing the to-be-processed video provided for the user, for example, uploading the to-be-processed video, deleting the uploaded to-be-processed video, naming the to-be-processed video, and the like. The first indication information may specifically include information indicating that a user inputs a video identifier in a first preset area in the video uploading interface, and include indication information indicating that a user inputs a video tag in a second preset area in the video uploading interface, where the video tag is used to perform supplementary description on an input video. For example, the Video identification entered by the user may be Video1, and the Video tag may be xiaoming-12.9, which may indicate that the Video1 is a Video shot on day 9 of 12 months for xiaoming.

The first indication information may further include format restriction information for information input by the user, for example, the format restriction information may support only inputting chinese and english, numbers, and underlines, and may not exceed 20 characters. The specific format restriction information may be set according to an actual application scenario, and is not limited herein.

The second indication information may specifically include indication information indicating that a user inputs a to-be-processed video corresponding to the video identifier, and a video uploading history, and the video uploading record information may specifically include, for example, information indicating the number of to-be-processed videos to be uploaded, information indicating the number of to-be-processed videos that have been successfully uploaded, and information indicating the number of to-be-processed videos that have failed to be uploaded; in addition, the second indication information may further include reprocessing indication information for the to-be-processed video that fails to be uploaded, for example, retransmission failure item information for indicating that the to-be-processed video that fails to be uploaded is re-uploaded, and clearing failure item information for indicating that the to-be-processed video that fails to be uploaded is emptied.

In addition, the video uploading interface can further comprise a first determining component used for indicating confirmation of video uploading and a first canceling component used for canceling video uploading.

Fig. 3 is a schematic diagram of a video upload interface according to an embodiment of the present disclosure. The first indication information and the second indication information included in fig. 3 are only used as an example, and the specific content of the first indication information and the specific content of the second indication information may be set according to an actual application requirement, which is not specifically limited in the embodiment of the present disclosure.

When the step is implemented specifically, when the user has a requirement of video desensitization, the user can log in the video desensitization platform, and after the user logs in successfully, an initial page corresponding to the video desensitization platform can be displayed to the user, so that the user can initiate a video desensitization instruction on the initial page. The video desensitization platform may then present a video upload interface including the first indication information and the second indication information to the user in response to the video desensitization instruction. Wherein the video desensitization instruction may be initiated when the user clicks a video desensitization button in the initial page.

Furthermore, the user can upload the videos to be processed on the video uploading interface according to the first indication information and the second indication information in the video uploading interface, and set information such as a video identifier and a video tag for each uploaded video to be processed. Here, the user may upload one or more videos to be processed, and the video format of the videos to be processed uploaded by the user may be any format, for example, mp4 format, avi format, wmv format, 3gp format, and so on.

In the case where a user uploads a plurality of videos to be processed, the plurality of videos to be processed may be regarded as one video set. The user uploads the videos to be processed in batches through the video uploading interface, after the videos are successfully uploaded, the videos to be processed in batches can be processed in a centralized mode, and the video desensitization efficiency is improved.

In addition, the user can also directly upload a video file compression package in any compression format or upload a video set comprising a plurality of videos to be processed. One or more videos to be processed may be included in the video file compression package, and the compression format may be, for example, a zip format, a tar format, a 7z format, a gz format, or the like. And the video identification corresponding to the video file compression package is used for representing whether desensitization treatment needs to be carried out on each video corresponding to the video file compression package.

Therefore, a user can complete a series of video management work such as video uploading, uploading cancellation and the like in a visual interface through visual operation.

Further, a plurality of uploaded videos and video identifications corresponding to the videos may be received.

S101-2: and based on the video identification, taking the video needing desensitization processing as the video to be processed.

In specific implementation, the video to be processed, which needs to be desensitized, can be screened from the received multiple videos according to the received video identifiers. Here, the determined video to be processed may include one or more.

In addition, in the process of uploading the video and the video identifier, if the user determines that the uploaded video is required to be used as the video to be processed, the video identifier corresponding to the video can be uploaded, otherwise, the video identifier corresponding to the video is not uploaded. In this way, the video corresponding to each received video identifier can be directly used as the video to be processed.

Under the condition that a user uploads a video file compression package, the video file compression package can be decompressed under the condition that the video file compression package is obtained, so that each to-be-processed video included in the video file compression package is obtained.

In addition, in the process of acquiring the to-be-processed video uploaded by the user, if the video acquisition fails, failure prompt information can be generated and displayed to the user so as to prompt the user to upload the to-be-processed video again.

Therefore, based on the steps, each to-be-processed video uploaded by the user through the video uploading interface and the video identification corresponding to each to-be-processed video can be obtained.

After the videos to be processed uploaded by the user are acquired, the initial page can be displayed again, or the data selection interface can be displayed.

In an embodiment, the video desensitization method provided by the present disclosure may also be packaged as a video desensitization service, and a user may invoke the video desensitization service on a personal platform, and further, the service may directly multiplex each to-be-processed video stored in the personal platform.

In one embodiment, where the pending video includes a plurality, a video desensitization task may be received for each pending video.

In specific implementation, a data selection interface can be displayed for a user; the data selection interface shows: the third indication information indicates that the video to be processed which needs to be processed currently is selected from at least one video to be processed, and the fourth indication information indicates that the target desensitization content type is selected from a plurality of desensitization content types.

Here, the data selection interface provides an interface for the user to select a video to be processed that currently needs to be processed, and to select a desensitization content type for the video to be processed.

The third indication information is used to indicate the user to select the video identifier of the video to be processed that needs to be processed currently, and specifically, the third indication information may include text prompt information and a video selection box. The fourth indication information may specifically include text prompt information and selection boxes respectively corresponding to desensitization content types, where selection boxes of the multiple selection boxes in the fourth indication information may be selected simultaneously, and all desensitization content types corresponding to the selected selection boxes are taken as target desensitization content types.

In addition, the data selection page can also comprise a second determination component for instructing the user to determine that the selected video to be processed is subjected to the process of removing the image content matched with the target desensitization content type, and a second cancellation component for canceling the operation.

Fig. 4 is a schematic diagram of a data selection interface provided in an embodiment of the present disclosure.

In specific implementation, a data selection interface can be displayed in response to data selection triggering operation of a user; the data triggering operation may be: an operation in which the user clicks the first determination component shown in fig. 3; alternatively, the user may click a target button in the initial page.

Furthermore, each video selected by the user in the video selection frame corresponding to the third indication information may be used as a video to be processed. For example, in response to the operation of clicking the video selection box, the video identifiers of the acquired videos to be processed are displayed to the user, and then in response to the operation of clicking the plurality of video identifiers by the user, each video to be processed corresponding to the video identifier clicked by the user is used as the current video to be processed. Or, each video identifier input by the user at the video selection frame may also be directly obtained, and the to-be-processed video corresponding to each input video identifier is used as the to-be-processed video currently required to be processed.

Moreover, for each video to be processed, each selection box selected by the user in the plurality of selection boxes corresponding to the fourth indication information may be used as a target selection box, and the desensitization content type corresponding to the target selection box may be used as the target desensitization content type. For example, when the user selects the face type selection box and the license plate type selection box, the target desensitization content type is the face type and the license plate type, that is, the synchronous desensitization processing of the face information and the license plate information is performed on the selected to-be-processed video that needs to be processed currently.

Then, in response to the operation that the user clicks the second determination component, based on the target desensitization content type, a video desensitization task corresponding to each to-be-processed video may be generated and sent to the server. Thus, the server may receive a video desensitization task for each pending video.

In addition, when the user uploads the video set, the user may select a video set file to be processed on the data selection interface, and select the target desensitization content type from the multiple selection boxes corresponding to the fourth indication information. Furthermore, in response to the operation that the user clicks the second determination component, based on the target desensitization content type, video desensitization tasks corresponding to each to-be-processed video in the video set are respectively generated and sent to the server.

In one embodiment, where the video to be processed is a video in a captured road environment, the target desensitization content types include: at least one of human face, license plate and video characters.

For example, the to-be-processed video may be a driving video uploaded by a user and shot by a driving recorder, and the multiple desensitization content types may include: the video text type can be, for example, landmark text information (such as place name, road name, and the like) appearing in driving video, and building name information (such as XX building, XXX company, and the like). The target desensitization content types may be, for example, a face type and a license plate type.

In addition, in addition to the desensitization content types, various types corresponding to objects that may appear in the video, such as a target animal type, a target building type, a target object type, and the like, may also be included, and the embodiments of the present disclosure are not particularly limited with respect to a specific desensitization content type.

In an embodiment, in the process of performing desensitization processing on the video to be processed, the progress of performing desensitization processing on the current video to be processed may also be obtained, and then the processing state corresponding to the video to be processed is updated according to the progress corresponding to the video to be processed. The processing state may specifically include three types, namely processing in progress, processing completion, and processing failure.

Here, when a video set including a plurality of videos to be processed is uploaded by a user, a processing state corresponding to the video set may be determined according to a processing progress corresponding to each video to be processed in the video set. Specifically, under the condition that the processing progress corresponding to each to-be-processed video in the video set is 100%, determining that the processing state corresponding to the video set is processing completion; under the condition that desensitization of a certain video to be processed fails, determining that the processing state corresponding to the video set is processing failure; otherwise, the processing state corresponding to the video set can be determined as processing.

Further, after it is determined that the processing state corresponding to the video to be processed indicates that the video has successfully completed the desensitization processing, that is, the target video corresponding to the video to be processed is obtained, the operation state of the video to be processed may be changed to a downloadable state, where the downloadable state is used to indicate that the video to be processed after the desensitization processing is available for the user to download.

Specifically, the task state indication page may be generated according to the processing state corresponding to each video to be processed, the target desensitization content type corresponding to each video to be processed, and the receiving time for receiving the video desensitization task corresponding to the video to be processed. As shown in fig. 5, a schematic diagram of a task state indication page provided by the embodiment of the present disclosure is shown, where relevant information of each video desensitization task is shown, where the relevant information includes the target desensitization content type, the receiving time, the processing state, and operation indication information of whether a video to be processed (i.e., a target video) after completing the desensitization processing is downloadable.

In addition, a video detail page jumping component can be further included in the task state indication page, after the user clicks the video detail page jumping component, the user can jump to a video detail page, and each video to be processed and the brief introduction information about each video to be processed are displayed in the video detail page. Or, in the case that the video to be processed by the user corresponds to a video set, the profile information displayed in the video detail page may be the profile information of the video set. In addition, in response to an operation of clicking any to-be-processed video in the video detail page by the user, in the case that it is determined that a target video corresponding to the video clicked by the user is generated, a target video preview page (which will be described in detail later) is generated for playing the target video. Fig. 6 is a schematic diagram of a video detail page provided by the embodiment of the present disclosure, which shows three videos to be processed corresponding to a video set, and profile information of the video set. Likewise, the video details page also exhibits a task state indication page jump component for jumping to the task state indication page,

in an embodiment, after the target video corresponding to the video to be processed is obtained, the video list page may be further displayed to the user in response to a request of the user to view a video list corresponding to the video to be processed. The video list page displays relevant information of each to-be-processed video and/or video set, such as a video identifier or a video set identifier of the to-be-processed video, object information corresponding to a target desensitization content type included in each to-be-processed video, the number of the to-be-processed videos included in the video set, creation time of the video set, an import state of the to-be-processed video or video set, and an operable state of the to-be-processed video or video set; and displaying search indication information for searching the video to be processed. The object information can be a license plate number for example under the condition that an object corresponding to the target desensitization content type is a license plate, the object information can be a face link under the condition that an object corresponding to the target desensitization content type is a face, and a face image can be obtained by clicking the face link; the import state can comprise three states of import, imported and not imported; the operable state may specifically include a view (or not viewable), edit, process, download (or not downloadable), delete, and the like state.

As shown in fig. 7, a schematic view of a video list page provided in the embodiment of the present disclosure is shown, where the schematic view includes video set identifiers corresponding to a plurality of video sets and video identifiers corresponding to a plurality of videos to be processed, object information is a license plate number, and search indication information shown in fig. 7 includes a video identifier search box for inputting the video identifiers, an object information search box for inputting the object information, a state filter box for selecting an import state, a time filter box for searching according to time information, a search determination button, and a reset search button; and a batch processing button for performing batch processing on the plurality of videos to be processed and a batch downloading button for performing batch downloading on the plurality of videos to be processed are also shown in fig. 7.

Further, in response to a download request for the to-be-processed video in a downloadable state, the processed target video corresponding to the to-be-processed video may be downloaded to the local designated storage location.

Here, the download request may be a download request for a target video corresponding to any one of the videos to be processed shown in the video list page. The method can also be used for downloading any video set displayed on a page in the video list, and the downloading request is used for downloading target videos corresponding to the videos to be processed in the video set in batches. Alternatively, the download request may also be a batch download request for a plurality of videos to be processed and a plurality of video sets shown in the video list page. The local storage location may be, for example, a local database, a local memory, or the like.

Taking the downloading request as an example of downloading a to-be-processed video in a downloadable state, the target video corresponding to the to-be-processed video may be downloaded to the local database in response to the downloading request. After the target video is successfully downloaded to the local storage location, the user can view the target video offline at any time.

In addition, in the process of downloading the target videos to the local storage position, a downloading progress display window can be generated and displayed according to the downloading progress corresponding to each target video. Specifically, the download progress display window may be displayed at a preset position of the video list page, for example, a middle position, an upper left corner position, a lower right corner position, and the like. Therefore, the user can obtain the real-time downloading condition of each target video in real time according to the downloading progress page.

As shown in fig. 8, a schematic view of a download progress display window provided in the embodiment of the present disclosure is shown, where the download progress display window is shown in the middle of the video list page shown in fig. 7.

In an embodiment, after target videos respectively corresponding to each to-be-processed video selected by a user are obtained, a target video preview page corresponding to each to-be-processed video may be further generated, where the target video preview page is a page showing the target video corresponding to the to-be-processed video, and includes a target video preview window of the target video corresponding to the to-be-processed video and a desensitization content type tag corresponding to a target desensitization content type.

Also, where the video desensitization task corresponds to multiple target desensitization content types, the desensitization content type tags may be type tags corresponding to each of the multiple target desensitization content types, respectively. For example, where the target desensitization content types include a face type and a license plate type, the desensitization content type tags may include a face tag and a license plate tag. And a progress control bar for controlling the video playing progress and a skip button for displaying the to-be-processed video corresponding to the target video are also displayed in the target video preview window, and a user can preview the to-be-processed video corresponding to the target video by clicking the skip button.

The step of displaying the target video preview page corresponding to the to-be-processed video selected by the user may be performed after the user clicks any to-be-processed video in the video detail pages.

In specific implementation, in response to an operation that a user can click any to-be-processed video displayed in the video detail page shown in fig. 6, a target video preview page including the target video is generated and displayed according to the target video corresponding to the to-be-processed video. In particular, the target video preview page may be presented at any page position, e.g., an intermediate position, of the video detail page shown in FIG. 6.

As shown in fig. 9, a schematic view of a target video preview page provided by the embodiment of the present disclosure is shown, where the target video preview page is shown in a middle position of the video detail page.

Furthermore, any desensitization content type label selected by the user from the at least one desensitization content type label can be responded, and the processed target video corresponding to the desensitization content type label selected by the user is played in the target video preview window.

Here, in the case that the desensitization content type tag includes a plurality of pieces, the sensitive information indicating that the to-be-processed video corresponding to the target video displayed in the target video preview window is removed includes a plurality of pieces, and may include, for example, face information and license plate information. In this case, the generated target video corresponding to the video to be processed may include a plurality of target videos, for example, the target videos may include a target video from which only the face information is removed, a target video from which only the license plate information is removed, and a target video from which both the face information and the license plate information are removed.

In the case that the target video corresponding to the video to be processed includes a plurality of target videos, the target video displayed in the target video preview window may be a video from which the sensitive information corresponding to each desensitization content type tag is removed.

In addition, in response to the operation of any desensitization content type label selected by the user in at least one desensitization content type label, the target video only with the sensitive information corresponding to the desensitization content type label removed is determined, and the target video is played at the target video preview window.

Therefore, the user can preview each target video corresponding to the video to be processed according to the displayed desensitization content type label, and the flexibility of target video playing is improved.

In an embodiment, regarding S103 above, in a specific implementation, the determined image content corresponding to the target desensitization content type in the video to be processed may be a target object of the same type as the target desensitization content identified from each frame of video image of the video to be processed.

Here, the image content corresponding to the target object is the image content corresponding to the target desensitization content type. Specifically, the target object may be a face, a license plate, or the like in the video image.

And performing desensitization processing on the image content to obtain a desensitized target video, and directly performing fuzzy processing on the identified target object to obtain the target video.

Wherein the target object after the blurring process is blocked, so that the desensitization process to the sensitive information (i.e. the target object) is also realized.

In one embodiment, identifying the target object of the same type as the target desensitization content in each frame of video image of the video to be processed is identified by using a pre-trained target neural network.

The target neural network is obtained by training a plurality of sample images and can be used for identifying at least one target object with the same type as the target desensitization content, namely, the target neural network can be used for identifying the target object corresponding to any video desensitization task.

Specifically, the pre-trained target neural network may include only one target neural network, and the target neural network may be capable of identifying a target object corresponding to any video desensitization task. Alternatively, the pre-trained target neural network may also include a plurality of target neural networks, and one target neural network may be used to identify a target object corresponding to one type of video desensitization task. For example, one target neural network can be used for identifying a face corresponding to a face desensitization task, one target neural network can be used for identifying a license plate corresponding to a license plate desensitization task, and one target neural network can be used for identifying a face and a license plate corresponding to a face and license plate desensitization task.

In specific implementation, after a video desensitization task is received, a trained target neural network can be used for carrying out video decoding and frame cutting on a video to be processed to obtain each frame of video image included in the video to be processed, and then a target object corresponding to the type of the target desensitization content in each frame of video image of the video to be processed is determined.

In addition, for the sample images used for training, the desensitization content types corresponding to different types of sample images are different, that is, different types of sample images include different types of target objects, for example, the sample image a includes a human face, the sample image B includes a license plate, and the sample image C includes a human face and a license plate. Even if a plurality of sample images contain the same type of target object, the corresponding image scenes are different. Therefore, a large number of sample images of different types and different scenes are utilized to train the multi-type recognition model, and the recognition accuracy of the trained multi-type recognition model can be effectively improved.

In addition, in one embodiment, after the trained target neural network identifies the target object with the same type as the target desensitization content in each frame of video image, the trained target neural network can also directly perform blurring processing on the target object, and directly output the target video based on the target object in each video image after the blurring processing.

In an embodiment, regarding the above S104, the following steps may be performed:

s104-1: for each frame of video image, in response to identifying a plurality of target objects in the video image, an initial sub-image corresponding to each target object is scratched from the video image.

In specific implementation, for each frame of video image, in a case that it is determined that a plurality of target objects are identified from the frame of video image, in response to identifying a plurality of target objects in the video image, an object Identity (ID) may be assigned to each target object; and then according to the position information corresponding to each target object, deducting the initial sub-image corresponding to each target object from the video image, and taking the object identifier corresponding to each target object as the image identifier of the corresponding initial sub-image.

In an embodiment, in the step of capturing the initial sub-images corresponding to the target objects from the video image according to the position information corresponding to each target object, the image area corresponding to the detection frame of the target object can be directly deducted to be used as the initial sub-image of the target object; or, the detection frame of the target object may be scaled according to a preset scaling ratio, and the image area corresponding to the scaled detection frame is deducted to be used as the initial sub-image of the target object.

In one embodiment, even if only one target object is identified from the video image, an initial sub-image corresponding to the target object can be deducted from the video image based on the position information corresponding to the target object.

S104-2: and carrying out fuzzy processing on each initial sub-image to obtain a target sub-image corresponding to each initial sub-image.

In specific implementation, each initial sub-image deducted from the video image may be subjected to blurring processing to obtain a target sub-image corresponding to each initial sub-image, and an image identifier corresponding to each initial sub-image is used as an image identifier corresponding to the initial sub-image.

S104-3: and replacing the initial sub-image corresponding to the video image by adopting each target sub-image, and obtaining the target video based on each replaced video image.

In specific implementation, the target object corresponding to each target sub-image may be determined according to the image identifier corresponding to each target sub-image and the object identifier corresponding to each target object, and then the target sub-image is used to replace the initial sub-image corresponding to the target object in the video image. Furthermore, the replacement of the initial sub-image corresponding to each target object in the video image can be realized based on the image identifier of the initial sub-image corresponding to each target sub-image and the object identifier corresponding to the target object, so as to obtain the target image.

And combining target images corresponding to each frame of video image based on the sequence of each frame of video image in the obtained video to be processed in the video to be processed to obtain the target video.

In one embodiment, for any initial sub-image, the blurring is performed on the initial sub-image according to the following steps:

step one, dividing an initial sub-image into a plurality of processing areas.

In this step, the initial sub-image may be equally divided into a plurality of processing regions having the same size according to the image size corresponding to the initial sub-image, for example, when the image size corresponding to the initial sub-image is 100 × 80, the initial sub-image may be divided into 100 processing regions, and the region size of each processing region is 10 × 8. Alternatively, the initial sub-image may be divided into the processing areas of the number of processing areas according to the preset number of processing areas. Or, the dividing manner may also be determined according to the object type of the target object, for example, when the object type of the target object is a face type, the initial sub-image may be divided into a plurality of processing areas according to the position information of the facial features; and under the condition that the object type of the target object is the license plate type, dividing the initial sub-image into a plurality of processing areas with the same size.

And step two, determining a target pixel value corresponding to each processing area based on the pixel value of each pixel point in each processing area.

In an embodiment, for each divided processing region, a pixel mean value corresponding to the processing region may be determined based on pixel values corresponding to respective pixel points in the processing region, and the determined pixel mean value is used as a target pixel value of the processing region.

In another embodiment, for each divided processing region, a pixel extremum corresponding to the processing region may also be determined based on pixel values corresponding to respective pixel points in the processing region, and the determined pixel extremum is used as a target pixel value of the processing region.

Or, for each divided processing region, one pixel value may be randomly selected from the pixel values corresponding to the respective pixel points in the processing region as a target pixel value.

And step three, replacing the pixel values corresponding to the pixel points in each processing area with the determined target pixel values to obtain the target sub-images corresponding to the initial sub-images.

In specific implementation, for each processing region, the pixel value corresponding to each pixel point in the processing region may be replaced with the determined target pixel value corresponding to the processing region, and after the pixel value replacement for each processing region is completed, the target sub-image is obtained.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

Based on the same inventive concept, the embodiment of the present disclosure further provides a video desensitization apparatus corresponding to the video desensitization method, and as the principle of the apparatus in the embodiment of the present disclosure for solving the problem is similar to the video desensitization method described above in the embodiment of the present disclosure, the implementation of the apparatus may refer to the implementation of the method, and repeated details are not described again.

As shown in fig. 10, a schematic diagram of a video desensitization apparatus provided for the embodiment of the present disclosure includes:

a receiving module 1001, configured to receive an uploaded video to be processed; and receiving a video desensitization task for the video to be processed;

a determining module 1002, configured to determine, based on a target desensitization content type in the video desensitization task, image content in the to-be-processed video corresponding to the target desensitization content type;

and the processing module 1003 is configured to perform desensitization processing on the image content to obtain a desensitized target video.

In a possible implementation manner, the receiving module 1001 is configured to receive a plurality of uploaded videos and video identifiers corresponding to the videos; the video identification represents whether each video needs desensitization treatment or not;

In a possible implementation manner, there are a plurality of the videos to be processed, and the receiving module 1001 is configured to receive a video desensitization task for each of the videos to be processed.

In a possible implementation manner, the processing module 1003 is further configured to update the processing state of the to-be-processed video according to a current progress of desensitization processing on the to-be-processed video;

In a possible embodiment, the apparatus further comprises:

the downloading module 1004 is configured to, in response to a downloading request of a user for a to-be-processed video in a downloadable state, download a processed target video corresponding to the to-be-processed video to a local specified storage location.

In a possible embodiment, the apparatus further comprises:

a display module 1005, configured to play the processed target video corresponding to the desensitization content type selected by the user after acquiring the target video.

In a possible implementation, the determining module 1002 is configured to identify a target object in each frame of video image of the video to be processed, where the target object is of the same type as the target desensitization content;

the processing module 1003 is configured to perform fuzzy processing on the identified target object to obtain the target video.

In a possible embodiment, the processing module 1003 is configured to, for each frame of the video image, in response to identifying a plurality of the target objects in the video image, extract an initial sub-image corresponding to each of the target objects from the video image;

In a possible implementation manner, the processing module 1003 is configured to, for any initial sub-image, perform blurring processing on the initial sub-image according to the following steps:

dividing the initial sub-image into a plurality of processing regions;

In a possible implementation manner, the processing module 1003 is configured to determine a pixel value mean value corresponding to each processing region based on pixel values of respective pixels in each processing region, and use the pixel value mean value corresponding to each processing region as the target pixel value corresponding to the processing region.

In a possible implementation manner, the processing module 1003 is configured to determine a pixel value extremum corresponding to each processing region based on pixel values of respective pixels in each processing region, and use the pixel value extremum corresponding to each processing region as the target pixel value corresponding to the processing region.

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

An embodiment of the present disclosure further provides a computer device, as shown in fig. 11, which is a schematic structural diagram of a computer device provided in an embodiment of the present disclosure, and includes:

a processor 1101 and a memory 1102; the memory 1102 stores machine-readable instructions executable by the processor 1101, the processor 1101 configured to execute the machine-readable instructions stored in the memory 1102, the processor 1101 performing the following steps when the machine-readable instructions are executed by the processor 1101: s101: receiving an uploaded video to be processed; s102: receiving a video desensitization task for a video to be processed; s103: based on the target desensitization content type in the video desensitization task, determining image content corresponding to the target desensitization content type in the video to be processed, and S104: and desensitizing the image content to obtain a desensitized target video.

The storage 1102 includes a memory 1121 and an external storage 1122; the memory 1121 is also referred to as an internal memory, and is used to temporarily store operation data in the processor 1101 and data exchanged with the external memory 1122 such as a hard disk, and the processor 1101 exchanges data with the external memory 1122 via the memory 1121.

For the specific execution process of the instruction, reference may be made to the steps of the video desensitization method described in the embodiments of the present disclosure, and details are not described here.

Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon a computer program, which, when being executed by a processor, performs the steps of the video desensitization method described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The computer program product of the video desensitization method provided in the embodiments of the present disclosure includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the steps of the video desensitization method described in the above method embodiments, which may be specifically referred to the above method embodiments and are not described herein again.

The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implementing, and for example, a plurality of units or components may be combined, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A video desensitization method, comprising:

receiving an uploaded video to be processed;

receiving a video desensitization task for the video to be processed;

and desensitizing the image content to obtain a desensitized target video.

2. The method of claim 1, wherein receiving the uploaded to-be-processed video comprises:

3. The method according to claim 1 or 2, wherein the pending video is plural, and receiving a video desensitization task for the pending video comprises:

receiving a video desensitization task for each of the pending videos.

4. The method of claim 1, wherein in the case that the video to be processed is a video in a captured road environment, the target desensitization content type comprises: at least one of human face, license plate and video characters.

5. The method of claim 1, further comprising:

6. The method of claim 5, further comprising:

7. The method of claim 1, wherein after the target video is acquired, the method further comprises:

8. The method according to any one of claims 1 to 7, wherein determining image content in the to-be-processed video corresponding to a target desensitization content type based on the target desensitization content type in the video desensitization task comprises:

9. The method of claim 8, wherein the identifying of the target object of the same type as the target desensitization content in each frame of video image of the video to be processed is performed by using a pre-trained target neural network, wherein the target neural network is trained by using a plurality of sample images and can be used to identify at least one target object of the same type as the target desensitization content.

10. The method of claim 8, wherein the blurring the identified target object to obtain the target video comprises:

11. The method according to claim 10, wherein for any of the initial sub-images, the initial sub-image is blurred according to the following steps:

dividing the initial sub-image into a plurality of processing regions;

12. The method according to claim 11, wherein the determining a target pixel value corresponding to each of the processing regions based on the pixel values corresponding to the respective pixel points in each of the processing regions comprises:

13. The method according to claim 11, wherein the determining a target pixel value corresponding to each of the processing regions based on the pixel values corresponding to the respective pixel points in each of the processing regions comprises:

14. A video desensitization apparatus, comprising:

15. A computer device, comprising: a processor, a memory storing machine readable instructions executable by the processor, the processor for executing the machine readable instructions stored in the memory, the machine readable instructions when executed by the processor, the processor performing the steps of the video desensitization method according to any of claims 1 to 13.

16. A computer-readable storage medium, having a computer program stored thereon, which, when executed by a computer device, performs the steps of a video desensitization method according to any of claims 1 to 13.