WO2023061082A1

WO2023061082A1 - Image security processing method and apparatus, electronic device, and storage medium

Info

Publication number: WO2023061082A1
Application number: PCT/CN2022/116227
Authority: WO
Inventors: 陈斌; 王国利; 张骞; 黄畅
Original assignee: 北京地平线信息技术有限公司
Priority date: 2021-10-14
Filing date: 2022-08-31
Publication date: 2023-04-20
Also published as: CN113936202A

Abstract

Disclosed in embodiments of the present disclosure are an image security processing method and apparatus, an electronic device, and a storage medium. The method comprises: determining a geographic position when an image sensor acquires an image to be processed; determining a geographic security level corresponding to the geographic position; determining a target object in said image on the basis of the geographic security level; and performing privacy protection processing on an image area where the target object is located. According to the embodiments of the present disclosure, privacy protection processing can be performed on a corresponding target object on the basis of security protection requirements of different geographic positions, such that corresponding security protection is realized; and meanwhile, consumption of computing resources due to privacy protection processing on unnecessary objects can be avoided.

Description

Image security processing method and device, electronic equipment and storage medium

This disclosure claims the priority of the Chinese patent application with application number 202111199504.7 and titled "Image security processing method and device, electronic equipment and storage medium" filed on October 14, 2021, the entire contents of which are incorporated by reference in In this disclosure.

technical field

The present disclosure relates to image processing technology, in particular to an image security processing method and device, electronic equipment and a storage medium.

Background technique

Image security is one of the important areas of information security. Image acquisition using image acquisition equipment is widely used in all aspects of society, such as driving, mobile phones, monitoring, Internet of Things and so on. Since the collected images may involve personal privacy and national security, it is often necessary to perform image security processing on the collected images, such as coding faces, coding license plates, and coding sensitive objects related to national security.

Existing image security processing methods usually perform unified security processing on all collected images.

Contents of the invention

In order to solve the above-mentioned technical problems, the present disclosure is proposed. Embodiments of the present disclosure provide an image security processing method and device, electronic equipment, and a storage medium.

According to an aspect of an embodiment of the present disclosure, an image security processing method is provided, including:

Determine the geographic location when the image sensor collects the image to be processed;

determining the geographic security level corresponding to the geographic location;

determining a target object in the image to be processed based on the geographic security level;

Perform privacy and security protection processing on the image area where the target object is located.

According to another aspect of the embodiments of the present disclosure, an image security processing device is provided, including:

The first determining module is used to determine the geographic location when the image sensor collects the image to be processed;

The second determination module is used to determine the geographic security level corresponding to the geographic location;

A third determination module, configured to determine the target object in the image to be processed based on the geographic security level;

A processing module, configured to perform privacy protection processing on the image region where the target object is located.

According to still another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, the storage medium stores a computer program, and the computer program is used to execute the image security processing method described in any of the above-mentioned embodiments of the present disclosure. .

According to still another aspect of the embodiments of the present disclosure, an electronic device is provided, and the electronic device includes:

processor;

memory for storing said processor-executable instructions;

The processor is configured to execute the image security processing method described in any one of the above-mentioned embodiments of the present disclosure.

Based on the image security processing method and device, electronic equipment, and storage medium provided by the above-mentioned embodiments of the present disclosure, when performing security processing on the image to be processed, the geographic security level corresponding to the geographic location when the image sensor collects the image to be processed is determined to be processed. The target object in the image, and perform privacy protection processing on the image area where the target object is located, realize the privacy protection processing of the corresponding target object based on the security protection requirements of different geographical locations, and realize the corresponding security protection; at the same time, it can avoid Privacy protection processing of non-essential objects consumes computing resources.

The technical solution of the present disclosure will be described in further detail below with reference to the drawings and embodiments.

Description of drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail with reference to the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure, and constitute a part of the specification, and are used together with the embodiments of the present disclosure to explain the present disclosure, and do not constitute limitations to the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.

Fig. 1 is a schematic flowchart of an image security processing method provided by an exemplary embodiment of the present disclosure.

Fig. 2 is a schematic flowchart of an image security processing method provided by another exemplary embodiment of the present disclosure.

Fig. 3 is a schematic flowchart of an image security processing method provided by yet another exemplary embodiment of the present disclosure.

Fig. 4 is a schematic flowchart of an image security processing method provided by yet another exemplary embodiment of the present disclosure.

Fig. 5 is a schematic flowchart of an image security processing method provided by another exemplary embodiment of the present disclosure.

Fig. 6 is a schematic structural diagram of an image security processing device provided by an exemplary embodiment of the present disclosure.

Fig. 7 is a schematic structural diagram of an image security processing device provided by another exemplary embodiment of the present disclosure.

Fig. 8 is a schematic structural diagram of an image security processing device provided by yet another exemplary embodiment of the present disclosure.

Fig. 9 is a structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure.

Detailed ways

Hereinafter, exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited by the exemplary embodiments described here.

It should be noted that relative arrangements of components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise. Those skilled in the art can understand that terms such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc. necessary logical sequence. It should be understood that in the embodiments of the present disclosure, "plurality" may refer to two or more than two, and "at least one" may refer to one, two or more than two. Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and devices should be considered part of the description.

The embodiments of the present disclosure can be applied to any first electronic device with a camera function, such as an imaging device such as a monitoring camera, or can also be applied to a terminal device, a computer system, a server, etc. that communicate with the first electronic device with a camera function. Two electronic devices, the first electronic device with camera function sends the original image data collected by the image sensor and the geographic location when collecting the original image data to the second electronic device, and the second electronic device returns to the first electronic device after security processing , the second electronic device is operable with numerous other general purpose or special purpose computing system environments or configurations.

A first electronic device and a second electronic device such as a terminal device, a computer system, a server, etc. may be described in the general context of computer system executable instructions (such as program modules) executed by the computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc., that perform particular tasks or implement particular abstract data types. The computer system/server can be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computing system storage media including storage devices.

exemplary system

Embodiments of the present disclosure may be applicable to a vehicle monitoring system, the vehicle monitoring system may include a camera device and a server, the camera device communicates with the server, and transmits the captured monitoring images to the server for storage and other processing, and the camera device is set outside the vehicle for preset Position, the preset position is determined according to the scene information that can capture the geographic location of the vehicle.

In the embodiment of the present disclosure, after the image sensor collects the image to be processed, the camera device can first determine the geographic location when the image sensor collects the image to be processed, then determine the geographic security level corresponding to the geographic location, and determine the location to be processed based on the geographic security level. The target object in the image, and then perform privacy and security protection processing on the image area where the target object is located. In practical applications, the image security processing of the image to be processed can be realized by adding an image security processing unit between the image sensor and the image signal processor (Image Signal Processing, referred to as: ISP), and the image security processing unit can use a GPU (graphics processing unit, graphics processor) or AI (Artificial Intelligence, artificial intelligence) chip; in addition, the image security processing of the image to be processed can also be implemented by the ISP, which can be set according to actual needs, which is not limited in this disclosure. In some applications, the image security processing of the image to be processed can also be realized by a second electronic device other than the camera device, and by communicating with the camera device, the image to be processed collected by the image sensor of the camera device is transmitted to the second electronic device. The second electronic device returns to the camera device after image security processing.

exemplary method

Fig. 1 is a schematic flowchart of an image security processing method provided by an exemplary embodiment of the present disclosure. This embodiment can be applied to electronic equipment, as shown in Figure 1, including the following steps:

Step 101, determine the geographic location when the image sensor captures the image to be processed.

In the embodiment of the present disclosure, the image to be processed may be a scene image of the current geographic location collected by the image sensor. Exemplarily, the image to be processed may be a scene image of the geographic location of the vehicle collected by the camera outside the vehicle during assisted driving or automatic driving of the vehicle. The scene image of the geographic location of the vehicle may include any object captured by the camera outside the vehicle, for example, a license plate, a human face, a building, a road facility, etc., which are not limited in this embodiment of the present disclosure.

In the embodiment of the present disclosure, the image to be processed may be an unprocessed original image (also referred to as raw data) collected by an image sensor. The unprocessed original image is specifically an unprocessed image obtained by converting the light source signal captured by the image sensor into a digital signal. Exemplarily, the image to be processed may be an unprocessed original scene image of the geographic location of the vehicle collected by the camera outside the vehicle during assisted driving or automatic driving.

In the embodiment of the present disclosure, the geographic location when the image sensor collects the image to be processed may be determined by a positioning device, and may be represented by latitude and longitude coordinates. The positioning device can be set in the device where the image sensor is located, or can also be set near the device where the image sensor is located, so as to ensure that the geographic location determined by the positioning device is consistent with the geographic location when the image sensor collects the image to be processed.

In an optional example, the positioning device may be any one of positioning devices such as a Beidou positioning device and a GPS positioning device, which is not limited in this embodiment of the present disclosure.

Step 102, determine the geographic security level corresponding to the geographic location.

In the embodiment of the present disclosure, the geographic security level may be used to identify the level of geographic information security requirements of the geographic location, and the geographic security level of the geographic location may be determined according to the geographic information security requirements of the geographic location. Specifically, a higher geographic security level may be determined for a geographic location with a higher geographic information security requirement; a lower geographic security level may be determined for a geographic location with a lower geographic information security requirement. It should be noted that geographic information security specifically refers to the protection of hardware, software, and data in systems involved in the collection, processing, storage, processing, transmission, service, and application of geographic information.

For example, in the process of vehicle assisted driving or automatic driving, if the geographical location of the image to be processed collected by the camera outside the vehicle is an undisclosed place, and the geographical information security requirements of the undisclosed place are high, the geographical security level of the geographical location can be determined as High level; if the geographical location of the image to be processed collected by the camera outside the vehicle is a semi-public place, and the geographical information security requirements of the semi-public place are medium, the geographic security level of the geographical location can be determined as a medium level; if the camera outside the vehicle collects the image to be processed The geographical location of the image is a public place, and the geographical information security requirements of the public place are low, and the geographical security level of the geographical location can be determined as a low level.

In an optional example, the geographic security level may include more than two levels. For example, the two or more levels may include: geographic security level one, geographic security level two, and geographic security level three. For example, two or more levels It may also include: geographic security level A, geographic security level B, and geographic security level C, which are not limited in this embodiment of the present disclosure.

In an optional example, any one or more of symbols such as Roman numerals, lowercase Arabic numerals, uppercase Arabic numerals, Chinese numerals, lowercase English letters, and uppercase English letters can be used to name different geographic security levels to distinguish between different geographical locations. Security level, the embodiment of the present disclosure does not limit the naming manner of the geographic security level.

Step 103, determine the target object in the image to be processed based on the geographic security level.

In the embodiments of the present disclosure, when the image sensor collects images to be processed, it is easy to collect images of objects (also referred to as sensitive objects) in the current geographic location that do not want to be known to the public. The target object in the image to be processed is a sensitive object that needs privacy protection processing in the image to be processed.

In an optional example, sensitive objects may include, but are not limited to, license plates, human faces, buildings, and road facilities.

In the embodiment of the present disclosure, sensitive object types corresponding to each geographic security level may be preset, and the sensitive object types corresponding to each geographic security level may be partly the same or completely different.

As an example, it is possible to set the sensitive object type corresponding to geo-security level 1 as building, the sensitive object type corresponding to geo-security level 2 as license plate, and the sensitive object type corresponding to geo-security level 3 as face.

As another example, the types of sensitive objects corresponding to the first level of geographic security may be buildings and road facilities, the types of sensitive objects corresponding to the second level of geographic security may be license plates and buildings, and the types of sensitive objects corresponding to the third level of geographic security may be license plates and faces.

In the embodiment of the present disclosure, the level of each geographic security level can be distinguished according to preset rules. In an optional example, the default rule may be that the smaller the Arabic numeral contained in the name of the geographical security level, the higher the geographical security level, or that the larger the Arabic number contained in the name of the geographical security level, the higher the geographical security level. It may also be that the lower the English letters contained in the naming of the geographical security level, the higher the geographical security level, or the earlier the English letters contained in the naming of the geographical security level, the higher the geographical security level. It should be noted that using the size of the Arabic numerals contained in the naming of the geographic security level, or the order of the English letters can simply and effectively distinguish different geographic security levels, but it is not limited to this. Other methods, such as using the naming of the geographic security level The size of Roman numerals contained in , the size of Chinese numerals, etc. are also applicable. In an optional example, in each geographic security level, a higher geographic security level may correspond to a greater number of sensitive object types, and a lower geographic security level may correspond to a smaller number of sensitive object types. It should be noted that, the embodiment of the present disclosure does not limit the specific number of sensitive object types corresponding to each geographic security level.

As an example, each geographic security level may include three levels: geographic security level A, geographic security level B, and geographic security level C. The higher the level. Therefore, among the various geographic security levels, the geographic security level A is the lowest, and the geographic security level C is the highest. It can be set that the sensitive object types corresponding to the geographic security level C can be license plates, faces, buildings, and road facilities. , the types of sensitive objects corresponding to geo-security level B are license plates, faces, and buildings, and the sensitive types corresponding to geo-security level A are license plates and faces.

In an optional example, a higher geographic security level can correspond to more sensitive object types, and a lower geographic security level can correspond to fewer sensitive object types. Specifically, a higher geographic security level can be determined through a preset threshold. Security level and lower geographic security level, for example, a level higher than or equal to a preset threshold may be considered a higher geographic security level in this disclosure, and a level lower than a preset threshold may be considered a lower geographic security level grade. It should be noted that, the embodiment of the present disclosure does not limit the specific number of sensitive object types corresponding to each geographical security level.

As an example, each geographic security level may include four levels of geographic security level A, geographic security level B, geographic security level C, and geographic security level D, among which the level of geographic security level A is the lowest, and the level of geographic security level D is the highest. , the preset threshold can be set as C level, so that it can be determined that geographic security level A and geographic security level B are lower geographic security levels, and geographic security level C and geographic security level D are higher geographic security levels, and then can be The types of sensitive objects corresponding to higher geographic security levels are license plates, faces, buildings, and road facilities, etc., and the types of sensitive objects corresponding to lower geographic security levels are license plates and faces. In practical applications, the sensitive object types corresponding to the geographic security levels determined in step 102 can be obtained according to the preset correspondence between each geographic security level and the sensitive object type, and the type identified from the image to be processed can be compared with the sensitive object type Image objects of the same type as target objects in the image to be processed.

Step 104, performing privacy protection processing on the image area where the target object is located.

Specifically, since step 103 has acquired the target object that needs to be processed for privacy protection in the image to be processed, the image data in the image area where the target object is located can be processed for privacy protection, for example, by means of image occlusion or image blurring Perform privacy protection processing to ensure the security of sensitive data in the image to be processed.

In the embodiment of the present disclosure, when performing security processing on the image to be processed, the target object in the image to be processed is determined based on the geographic security level corresponding to the geographic location when the image sensor collects the image to be processed, and the image area where the target object is located is determined. Privacy protection processing realizes the privacy protection processing of corresponding target objects based on the security protection requirements of different geographical locations to achieve corresponding security protection; at the same time, it can avoid the consumption of computing resources for privacy protection processing of unnecessary objects.

FIG. 2 is a schematic flowchart of an image security processing method provided by another exemplary embodiment of the present disclosure. As shown in FIG. 2 , on the basis of the above-mentioned embodiment shown in FIG. 1 , step 102 may include the following steps:

Step 102-1, acquiring a target geographic location for geographic location matching from preset geographic location matching information.

In the embodiment of the present disclosure, the preset geographic location matching information may be stored in the form of a database or a data table, and the preset geographic location matching information may include at least one preset geographic location, and each preset geographic location in the at least one preset geographic location The location area range corresponding to the location.

In the embodiment of the present disclosure, the geographic location of the image sensor determined in the above step 101 when the image to be processed is collected can be compared with each preset geographic location in the preset geographic location matching information and the location area range corresponding to each preset geographic location. Compare to obtain the target geographic location that the geographic location matches.

In an optional example, the target geographic location matched by the geographic location may be any preset geographic location that is the same as the geographic location, or may also be a preset geographic location corresponding to any location area that includes the geographic location.

Step 102-2, obtaining the target geographic security level corresponding to the target geographic location and the target object type corresponding to the target geographic security level from the preset geographic security matching information.

In the embodiments of the present disclosure, the preset geographic security matching information may be stored in the form of a database or a data table, and the preset geographic security matching information may include: the geographic security level corresponding to each preset geographic location, and the geographic security level corresponding to each geographic security level. object type.

In an optional example, the object types in the preset geographic security matching information may include any one or more of the following: license plate, human face, building, and road facilities.

In the embodiment of the present disclosure, the target geographic location determined in step 102-2 can be compared with each preset geographic location in the preset geographic security matching information, and the geographic location corresponding to the preset geographic location that is the same as the target geographic location can be obtained. The security level is used as the target geographic security level corresponding to the target geographic location.

Compare the target geographic security level corresponding to the target geographic location with each geographic security level in the preset geographic security matching information, and obtain the object type corresponding to the same geographic security level as the target geographic security level as the target geographic security level The corresponding target object type.

In the embodiment of the present disclosure, when determining the geographic security level corresponding to the geographic location, the geographic location can be quickly found by comparing the geographic location with the preset geographic location matching information and the preset geographic security matching information. The geographic security level corresponding to the geographic location and the target object type corresponding to the geographic security level help to reduce the time consumption of image security processing and improve the efficiency of image security processing.

Fig. 3 is a schematic flowchart of an image security processing method provided by another exemplary embodiment of the present disclosure. As shown in Fig. 3 , on the basis of the embodiment shown in Fig. 2 above, step 103 may include the following steps:

Step 103-1a, performing semantic segmentation on the image to be processed to obtain at least one region of interest in the image to be processed.

Step 103-2a, performing semantic recognition on at least one region of interest to obtain at least one object of interest in the image to be processed.

In the embodiment of the present disclosure, the first pre-trained image semantic analysis model can be used to perform semantic segmentation and semantic recognition on the image to be processed. The semantic segmentation can obtain at least one region of interest in the image to be processed, and the region of interest is the There may be an image area of an object of interest in the image. Semantic recognition can determine the type of each pixel in the area of interest. Based on each pixel in the area of interest and the type of each pixel, the object of interest in the area of interest (including pixels belonging to the object of interest) and the type of the object of interest. Types of objects of interest may include, but are not limited to, license plates, human faces, buildings, and road facilities.

In the embodiment of the present disclosure, the first pre-trained image semantic analysis model can be obtained in the following manner:

Construct the first initial image semantic analysis model; obtain a plurality of image samples from the training sample set; use the plurality of image samples as input respectively, provide the first initial image semantic analysis model, and use the first initial image semantic analysis model to The input image samples are respectively subjected to semantic segmentation and semantic recognition, and according to the output of the first initial image semantic analysis model, at least one object of interest of each predicted image sample is obtained; according to at least one object of interest of each predicted image sample The object and the object of interest annotation information of each image sample are used to adjust the model parameters of the first initial image semantic analysis model.

In an optional example, the first initial image semantic analysis model may be a convolutional neural network model or a fully convolutional neural network model.

Step 103-3a, based on the object type corresponding to the geographic security level, determine the target object from at least one object of interest.

At least one object of interest in the image to be processed has been determined through step 103-2a, the type of each object of interest is compared with the object type corresponding to the geographic security level, and the type and geographic security level are selected from at least one interested object Objects of interest corresponding to the same object type are used as target objects.

In the embodiment of the present disclosure, through the pre-trained image semantic analysis model, at least one object of interest in the image to be processed can be quickly and accurately identified, so that the target that needs privacy protection processing in the image to be processed can be quickly and accurately determined Objects that help improve the efficiency and accuracy of image security processing. At the same time, the hierarchical security processing of the image to be processed according to the geographic security level is helpful to improve the flexibility of image security processing compared with the existing method of uniform security processing for all collected images.

FIG. 4 is a schematic flowchart of a method for image security processing provided by another exemplary embodiment of the present disclosure. As shown in FIG. 4 , on the basis of the above-mentioned embodiment shown in FIG. 2 , step 102-2 may include the following steps:

Step 102-2a, obtaining the target geographic security level corresponding to the target geographic location from preset geographic security matching information.

In the embodiment of the present disclosure, the preset geographic security matching information can be stored in the form of a database or a data table, and the preset geographic security matching information can include: the geographic security level corresponding to each preset geographic location, and the objects corresponding to each geographic security level type and the object classes included in the corresponding object type.

In an optional example, the object types in the geographic security matching information include any one or more of the following: license plates, faces, buildings, and road facilities.

In the embodiments of the present disclosure, an object category is a further subdivision of an object type, and an object type can be further subdivided into more than one object category. Exemplarily, the object type "license plate" may include three object categories "military license plate", "civilian license plate" and "police license plate", and the object type "human face" may include two object categories "eyes" and "face". , the object type "building" may include an object category "building", and the object type "road facilities" may include two object categories "traffic light" and "road sign". It should be noted that the object type subdivision method and subdivision quantity disclosed in the embodiment of the present disclosure are not limited, and those skilled in the art can determine the object type subdivision method and subdivision quantity according to actual needs.

In step 102-2b, the target object type corresponding to the target geographic security level and the object categories included in the target object type are obtained from the preset geographic security matching information.

Compare the target geographic security level corresponding to the target geographic location determined in step 102-2a with the geographic security levels in the preset geographic security matching information, and obtain the object type corresponding to the same geographic security level as the target geographic security level as The target object type, and obtain each object category included in the target object type.

In the embodiment of the present disclosure, by further dividing the object types corresponding to the geographic security level into object categories, the accuracy of distinguishing the target objects requiring privacy protection processing in the image to be processed can be improved, thereby helping to improve the accuracy of image security processing.

Fig. 5 is a schematic flowchart of an image security processing method provided by another exemplary embodiment of the present disclosure. As shown in Fig. 5 , on the basis of the embodiment shown in Fig. 4 above, step 103 may include the following steps:

Step 103-1b, performing semantic segmentation on the image to be processed to obtain at least one region of interest in the image to be processed.

Step 103-2b, performing semantic recognition on at least one region of interest to obtain at least one object of interest in the image to be processed.

In the embodiment of the present disclosure, the second pre-trained image semantic analysis model can be used to perform semantic segmentation and semantic recognition on the image to be processed. The semantic segmentation can obtain at least one region of interest in the image to be processed, and the region of interest is the There may be an image area of an object of interest in the image. Semantic recognition can determine the category to which each pixel in the area of interest belongs. Based on each pixel in the area of interest and the category to which each pixel belongs, the object of interest in the area of interest (including pixels belonging to the object of interest) and the category of the object of interest.

In the embodiment of the present disclosure, the category of the object of interest is a subdivision of the type of the object of interest, and the subdivision manner of the type of the object in the region of interest is the same as the subdivision manner of the above object type.

In the embodiment of the present disclosure, the second pre-trained image semantic analysis model can be obtained in the following manner: constructing the second initial image semantic analysis model; obtaining multiple image samples from the training sample set; using the multiple image samples as The input is provided to the second initial image semantic analysis model, and the input image samples are respectively subjected to semantic segmentation and semantic recognition through the second initial image semantic analysis model, and each predicted image is obtained according to the output of the second initial image semantic analysis model. At least one object of interest in the image sample; adjust the model parameters of the second initial image semantic analysis model according to the predicted at least one object of interest in each image sample and the annotation information of the object of interest in each image sample. In an optional example, the second initial image semantic analysis model may be a convolutional neural network model or a fully convolutional neural network model.

Step 103-3b, based on the object type corresponding to the geographic security level and the object categories included in the corresponding object type, determine the target object from at least one object of interest.

At least one object of interest in the image to be processed has been determined via step 103-2b, and the category of each object of interest is compared with the object categories included in the object type corresponding to the geographic security level, and selected from at least one object of interest An object of interest whose category is the same as any object category in each object category is used as a target object.

In an optional example, the above step 104 may include: according to the mask image corresponding to the image to be processed, performing occlusion processing on pixels in the image area where the target object is located in the image to be processed to obtain target image data.

In the embodiment of the present disclosure, a mask image having the same size as the image to be processed is provided, and the image area requiring privacy protection processing is marked by the mask image.

In the embodiment of the present disclosure, in the mask image, a mark (for example, a value of 1) is set in the image area corresponding to the target object in the image to be processed that requires privacy protection processing, so that when the privacy protection processing is performed in the subsequent steps, it can be According to whether there is a mark in the image block of the mask image, it is determined whether to perform occlusion processing on the pixel points in the corresponding image block of the image to be processed.

In this embodiment, the mask image can be used to mark the image area where the target object in the image to be processed needs to be processed for privacy protection, which can facilitate subsequent steps to accurately perform privacy protection processing on the image to be processed, and can effectively protect the image to be processed Privacy data security in.

Any image security processing method provided in the embodiments of the present disclosure may be executed by any appropriate device with data processing capabilities, including but not limited to: terminal devices, servers, and the like. Alternatively, any image security processing method provided in the embodiments of the present disclosure may be executed by a processor, for example, the processor executes any image security processing method mentioned in the embodiments of the present disclosure by calling a corresponding instruction stored in a memory. I won't go into details below.

Exemplary device

Fig. 6 is a schematic structural diagram of an image security processing device provided by an exemplary embodiment of the present disclosure. The device of this embodiment can be used to implement the corresponding method embodiment of the present disclosure. The apparatus shown in FIG. 6 includes: a first determining module 201 , a second determining module 202 , a third determining module 203 and a processing module 204 .

The first determination module 201 is used to determine the geographic location when the image sensor captures the image to be processed.

The second determination module 202 is used to determine the geographic security level corresponding to the geographic location.

The third determining module 203 is configured to determine the target object in the image to be processed based on the geographic security level.

The processing module 204 is configured to perform privacy protection processing on the image area where the target object is located.

Fig. 7 is a schematic structural diagram of an image security processing apparatus provided by another exemplary embodiment of the present disclosure. The second determination module 202 shown in Fig. 7 may include a first obtaining unit 202-1 and a second obtaining unit 202-2.

The first acquiring unit 202-1 is configured to acquire a target geographic location matched by the geographic location from preset geographic location matching information.

In an optional example, the preset geographic location matching information includes at least one preset geographic location, and a location area range corresponding to each preset geographic location in the at least one preset geographic location.

The second acquiring unit 202-2 is configured to acquire the target geographic security level corresponding to the target geographic location and the target object type corresponding to the target geographic security level from preset geographic security matching information.

In an optional example, the preset geographic security matching information includes: geographic security levels corresponding to each preset geographic location, and object types corresponding to each geographic security level.

In an optional example, the object types in the geographic security matching information include any one or more of the following: license plate, human face, building, and preset equipment.

Fig. 8 is a schematic structural diagram of an image security processing device provided by another exemplary embodiment of the present disclosure. The third determination module 203 shown in Fig. 8 may include a first identification unit 203-1, a second identification unit 203-2 and Determining unit 203-3.

The first recognition unit 203-1 is configured to perform semantic segmentation on the image to be processed to obtain at least one region of interest in the image to be processed.

The second recognition unit 203-2 is configured to perform semantic recognition on at least one region of interest to obtain at least one object of interest in the image to be processed.

The determining unit 203-3 is configured to determine the target object from at least one object of interest based on the object type corresponding to the geographic security level.

In an optional example, the second acquiring unit 202-2 is further configured to acquire the target geographic security level corresponding to the target geographic location from the preset geographic security matching information; The target object type of and the object categories included in the target object type.

In an optional example, the preset geographic security matching information includes: geographic security levels corresponding to each preset geographic location, object types corresponding to each geographic security level, and object categories included in the corresponding object types.

In an optional example, the determining unit 203-3 is further configured to determine the target object from at least one object of interest based on the object type corresponding to the geographic security level and each object category included in the corresponding object type.

In an optional example, the processing module 204 is specifically configured to, according to the mask image corresponding to the image to be processed, perform occlusion processing on pixels corresponding to the image area where the target object is located in the image to be processed to obtain target image data.

Exemplary electronic device

Hereinafter, an electronic device provided according to an exemplary embodiment of the present disclosure is described with reference to FIG. 9 . As shown in FIG. 9 , the electronic device includes one or more processors 901 and memory 902 .

The processor 901 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

Memory 902 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and/or cache memory (cache). The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, and the like. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 901 may execute the program instructions to implement the above-mentioned image security processing methods and/or other desired features. Various contents such as input signal, signal component, noise component, etc. may also be stored in the computer-readable storage medium.

In an example, the electronic device may further include: an input device 903 and an output device 904, and these components are interconnected through a bus system and/or other forms of connection mechanisms (not shown). The input device 903 may include, for example, a keyboard, a mouse, and the like. The output device 904 may include, for example, a display, a speaker, a printer, a communication network and remote output devices connected thereto, and the like.

Of course, for simplicity, only some of the components related to the present disclosure in the electronic device are shown in FIG. 9 , and components such as bus, input/output interface, etc. are omitted. In addition, the electronic device may also include any other suitable components according to specific applications.

Exemplary computer program product and computer readable storage medium

In addition to the above-mentioned methods and devices, embodiments of the present disclosure may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the above-mentioned "exemplary method" of this specification. Steps in the image security processing method according to various embodiments of the present disclosure described in the section.

The computer program product can be written in any combination of one or more programming languages to execute the program codes for performing the operations of the embodiments of the present disclosure, and the programming languages include object-oriented programming languages, such as Java, C++, etc. , also includes conventional procedural programming languages, such as the "C" language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute.

In addition, the embodiments of the present disclosure may also be a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when executed by a processor, cause the processor to perform the above-mentioned "Exemplary Method" section of this specification. The steps in the image security processing method according to various embodiments of the present disclosure described in .

The basic principles of the present disclosure have been described above in conjunction with specific embodiments, but it should be pointed out that the advantages, advantages, effects, etc. mentioned in the present disclosure are only examples rather than limitations, and these advantages, advantages, effects, etc. Various embodiments of the present disclosure must have. In addition, the specific details disclosed above are only for the purpose of illustration and understanding, rather than limitation, and the above details do not limit the present disclosure to be implemented by using the above specific details.

The block diagrams of devices, devices, devices, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, devices, systems may be connected, arranged, configured in any manner. Words such as "including", "comprising", "having" and the like are open-ended words meaning "including but not limited to" and may be used interchangeably therewith. As used herein, the words "or" and "and" refer to the word "and/or" and are used interchangeably therewith, unless the context clearly dictates otherwise. As used herein, the word "such as" refers to the phrase "such as but not limited to" and can be used interchangeably therewith.

The methods and apparatus of the present disclosure may be implemented in many ways. For example, the methods and apparatuses of the present disclosure may be implemented by software, hardware, firmware or any combination of software, hardware, and firmware. The above sequence of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the sequence specifically described above unless specifically stated otherwise. It should also be pointed out that, in the devices, equipment and methods of the present disclosure, each component or each step can be decomposed and/or reassembled. These decompositions and/or recombinations should be considered equivalents of the present disclosure.

Claims

An image security processing method, comprising:

Determine the geographic location when the image sensor collects the image to be processed;

determining the geographic security level corresponding to the geographic location;

determining a target object in the image to be processed based on the geographic security level;

Perform privacy protection processing on the image area where the target object is located.
The method according to claim 1, wherein said determining the geographic security level corresponding to said geographic location comprises:

Obtaining the target geographic location matched by the geographic location from preset geographic location matching information; wherein the preset geographic location matching information includes at least one preset geographic location;

Obtain the target geographic security level corresponding to the target geographic location and the target object type corresponding to the target geographic security level from the preset geographic security matching information; wherein, the preset geographic security matching information includes: each preset Set the geographic security level corresponding to the geographic location and the object type corresponding to each geographic security level.
The method according to claim 2, wherein the object types in the geographic security matching information include any one or more of the following: license plates, human faces, buildings and road facilities.
The method according to claim 2, wherein said determining the target object in the image to be processed based on the geographic security level comprises:

Semantically segmenting the image to be processed to obtain at least one region of interest in the image to be processed;

Perform semantic recognition on the at least one region of interest to obtain at least one object of interest in the image to be processed;

A target object is determined from the at least one object of interest based on the object type corresponding to the geographic security level.
The method according to claim 2, wherein said acquiring the target geographic security level corresponding to the target geographic location and the target object type corresponding to the target geographic security level from the preset geographic security matching information includes:

Obtain the target geographic security level corresponding to the target geographic location from the preset geographic security matching information;

The target object type corresponding to the target geographic security level and the object categories included in the target object type are obtained from the preset geographic security matching information; wherein, the preset geographic security matching information further includes: the object Each object class that the type includes.
The method according to claim 5, wherein said determining the target object in the image to be processed based on the geographic security level comprises:

Semantically segmenting the image to be processed to obtain at least one region of interest in the image to be processed;

Perform semantic recognition on the at least one region of interest to obtain at least one object of interest in the image to be processed;

A target object is determined from the at least one object of interest based on the object type corresponding to the geographic security level and each object category included in the corresponding object type.
The method according to any one of claims 1-6, wherein the performing privacy protection processing on the image area where the target object is located comprises:

According to the mask image corresponding to the image to be processed, occlusion processing is performed on the pixels in the image area where the target object is located in the image to be processed to obtain target image data.
An image security processing device, comprising:

The first determining module is used to determine the geographic location when the image sensor collects the image to be processed;

The second determination module is used to determine the geographic security level corresponding to the geographic location;

A third determination module, configured to determine the target object in the image to be processed based on the geographic security level;

A processing module, configured to perform privacy protection processing on the image region where the target object is located.
A computer-readable storage medium, the storage medium stores a computer program, and the computer program is used to execute the image security processing method described in any one of claims 1-7.
An electronic device comprising:

processor;

memory for storing said processor-executable instructions;

The processor is configured to read the executable instruction from the memory, and execute the instruction to implement the image security processing method described in any one of claims 1-7.