WO2021026848A1

WO2021026848A1 - Image processing method and device, and photographing apparatus, movable platform and storage medium

Info

Publication number: WO2021026848A1
Application number: PCT/CN2019/100673
Authority: WO
Inventors: 翁松伟; 杨增闯
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2019-08-14
Filing date: 2019-08-14
Publication date: 2021-02-18
Also published as: CN112204945A

Abstract

An image processing method, an image processing device, a photographing apparatus, a movable platform and a storage medium. The image processing method comprises: obtaining an image to be processed, and obtaining a target region corresponding to a main object (S101); identifying a non-main object in a non-target region according to a preset requirement (S102); and performing fuzzy processing on the non-main object to obtain a target image comprising the main object and the non-main object subjected to the fuzzy processing (S103).

Description

Image processing method, equipment, photographing device, movable platform and storage medium

Technical field

This application relates to the field of image processing technology, and in particular to an image processing method, equipment, photographing device, movable platform and storage medium.

Background technique

The camera module is the core module for digital camera products and pan/tilt camera products, and it is also a standard configuration module for mobile devices such as mobile phones.

In crowded places or places with traffic and other objects, when the user takes pictures or video of the main object, there are other people or vehicles and other objects nearby. It is usually easy to take pictures of irrelevant people or vehicles and other objects into the image. Existing camera modules cannot exclude surrounding people or vehicles and other objects in taking photos or videos. On the one hand, taking pictures of irrelevant people in the surroundings can easily infringe on the portrait rights of surrounding people and may easily cause unnecessary disputes. Shooting objects such as vehicles into the image may appear to have just captured the license plate number of the vehicle into the image, which may involve the privacy of the owner and may also easily cause unnecessary disputes. On the other hand, objects such as unrelated people or vehicles around are likely to affect the protruding of the main subject.

Summary of the invention

Based on this, the present application provides an image processing method, image processing equipment, photographing device, movable platform and storage medium, aiming to solve the technical problem that irrelevant surrounding people cannot be excluded when taking pictures or shooting.

In the first aspect, this application provides an image processing method, including:

Acquiring the image to be processed, and acquiring the target area corresponding to the subject object in the image to be processed;

Identifying a non-subject object in a non-target area according to preset requirements, where the non-target area is an area outside the target area in the image to be processed;

Blur processing is performed on the non-subject object to obtain a target image including the subject object and the non-subject object after the blur processing.

In a second aspect, the present application provides an image processing device, the image processing device includes: a memory and a processor;

The memory is used to store computer programs;

The processor is used to execute the computer program and when executing the computer program, implement the following steps:

In a third aspect, the present application provides a photographing device, the photographing device includes: a memory and a processor;

The memory is used to store computer programs;

In a fourth aspect, the present application provides a movable platform, the movable platform includes a photographing device, and the photographing device includes a memory and a processor;

The memory is used to store computer programs;

The processor is configured to execute the computer program and, when executing the computer program, implement the image processing method described in any one of the above.

In a fifth aspect, the present application provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the processor realizes any of the above Image processing method.

The embodiments of the application provide an image processing method, image processing equipment, photographing device, movable platform and storage medium, to obtain the target area of the subject in the image to be processed, and identify non-target areas other than the target area according to preset requirements The non-subject object in the non-subject object is blurred to obtain the target image including the subject object and the non-subject object after the blur process. Since the non-subject object in the target image has been blurred, in this way, Exclude non-subject objects from the target image; on the one hand, it can prevent non-subject objects from being overwhelming and affecting the main object in the target image; on the other hand, it can avoid possible violations of non-subject objects and avoid unnecessary dispute.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the application.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings needed in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic flowchart of an embodiment of an image processing method according to the present application;

FIG. 2 is an effect diagram after blurring and transition processing of the image to be processed using the image processing method of this application;

3 is a schematic flowchart of another embodiment of the image processing method according to the present application;

4 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 5 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 6 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 7 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 8 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 9 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 10 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 11 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 12 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 13 is a schematic flowchart of another embodiment of the image processing method of the present application;

FIG. 14 is a schematic flowchart of another embodiment of the image processing method of the present application;

15 is a schematic flowchart of another embodiment of the image processing method of the present application;

Fig. 16 is a schematic structural diagram of an embodiment of an image processing device of the present application.

detailed description

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The flowchart shown in the drawings is merely an illustration, and does not necessarily include all contents and operations/steps, nor does it have to be executed in the described order. For example, some operations/steps can also be decomposed, combined or partially combined, so the actual execution order may be changed according to actual conditions.

When shooting the main subject, take non-subject objects such as unrelated people or objects into the image. On the one hand, the non-subject object affects the key appearance of the subject object; on the other hand, it may cause infringement on the non-subject object to avoid causing disturbance. Necessary disputes. The embodiment of the application obtains the target area of the subject object in the image to be processed, recognizes the non-subject object in the non-target area, and blurs the non-subject object to obtain a target image including the subject object and the non-subject object after the blur process . Since the non-subject objects in the target image have been blurred, in this way, the non-subject objects can be excluded from the target image; the non-subject objects can be prevented from affecting the key appearance of the subject objects in the target image; the non-subject objects can be avoided Possible violations caused by the object, avoid unnecessary disputes. At the same time, the method can be adjusted according to the user's shooting needs, and by blurring the undesired objects in the image to be processed, the processing effect of beautiful composition and prominent main body is achieved.

This application can be applied to image processing scenes, and can also be applied to shooting scenes. Specifically, the present application can be applied to image processing equipment, shooting devices (for example, digital cameras, mobile equipment equipped with camera modules, etc.), image processing scenes and/or shooting scenes of a movable platform. Movable platforms refer to various platforms that can move automatically or under controlled conditions, such as: PTZ (for example: PTZ camera, etc.), unmanned aerial vehicles, vehicles, unmanned vehicles, ground robots, and so on.

Hereinafter, some embodiments of the present application will be described in detail with reference to the drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

Referring to Fig. 1, Fig. 1 is a schematic flowchart of an embodiment of an image processing method according to the present application. The method includes:

Step S101: Acquire an image to be processed, and acquire a target area corresponding to a subject object in the image to be processed.

The image to be processed refers to an image that has not been processed by the image processing method of the embodiment of the present application. The number of images to be processed is not limited, and may be one frame, such as a single frame image obtained in a photographing scene, or multiple frames, such as multiple frames of video images obtained in a photographing scene. The image to be processed may be an image that has been taken, or an image obtained in a preview state that has not yet been taken, or an image obtained during the shooting process, and so on. That is, this embodiment does not limit the manner of acquiring the image to be processed. In this manner, the application scope and application scenarios of the method of the embodiment of the present application can be expanded.

The scope and number of subject objects are not limited, and can be determined according to specific practical applications. In this way, the scope of application can be further expanded. The main object refers to the main object in the image to be processed, which can be a person or other objects besides the person, such as vehicles, buildings, plants, animals, etc. The main object can be more than one, for example: the main object is a single character, or the main object is a character and a vehicle next to the character, or the main object is a character, a vehicle and a puppy next to the character, or the main object is a vehicle and The puppy next to it, wait. In more application scenarios, the main object usually includes characters.

The size, contour, and acquisition method of the target area are not limited, and can be determined according to specific practical applications. In this way, the application range can be further expanded. The target area refers to the area corresponding to the main object in the image to be processed. It should be noted that the target area can completely include the entire subject object, for example: the subject object is a person, the target area includes the entire person; the target area can also include only a part of the subject object, for example: the subject object is a person, the target area Include only the character's head, or only the character's head and shoulders, etc. The contour of the target area can match the contour of the main object, which just coincides with the contour of the main object; or it can not match the contour of the main object, just include the corresponding main object. The target area can be generated automatically or adjusted manually; the target area can also be manually selected and generated, or adjusted manually.

Step S102: Identify the non-subject object in the non-target area according to the preset requirements, and the non-target area is the area outside the target area in the image to be processed.

The non-target area is relative to the target area and refers to the area outside the target area in the image to be processed. The size and/or contour of the non-target area changes with the change of the size and/or contour of the target area.

Non-subject objects are relative to subject objects, and refer to objects that need to be blurred in non-target areas. Similarly, the scope and number of non-subject objects are not limited, and can be determined according to specific practical applications. In this way, the scope of application can be further expanded. Non-subject objects can be people, or other objects besides people, such as vehicles, buildings, plants, animals, and so on. The non-subject object can be more than one, for example: the non-subject object is a single character, or the non-subject object is a character and the vehicle next to the character, or the non-subject object is a character, the vehicle next to the character, or the non-subject object is Vehicles, etc. In many application scenarios, since it is easy to infringe the portrait rights of others or expose private information such as the license plate numbers of other people's vehicles, non-subject objects usually include persons and/or vehicles and other objects that contain other people's private information.

The preset requirements refer to the preset requirements for identifying non-subject objects. For example: specify non-subject objects, how to identify non-subject objects? The characteristics of non-subject objects used for identification, the unique characteristics of non-subject objects, how to distinguish between non-subject objects and subject objects, etc. The preset requirements are not limited here, and the corresponding requirements can be preset according to specific practical applications. In this way, the scope of application can be further expanded.

Step S103: Blur processing is performed on the non-subject object to obtain a target image including the subject object and the non-subject object after the blur processing.

Blurring non-subject objects refers to blurring the area occupied by non-subject objects, so that the non-subject objects become blurred. The subject object is retained in the target image obtained in this way, and the non-subject object becomes blurred.

The blur processing includes, but is not limited to, one or more blur processing including horizontal blur, vertical blur, radial blur, oblique blur, mosaic, area filling, and background coverage.

Horizontal blur is an effect processing method that blurs from the horizontal direction; horizontal blur processing can highlight the performance effects of image phantom and dynamic. Vertical blur is a method of processing blur from the vertical direction; vertical blur processing can highlight the dynamic, gloss, texture and other performance effects of the image. Radial blur is a gradual blur effect processing method that radiates from the center to the outside; radial blur processing can highlight the shock of the image or highlight the performance effects of fast moving speed. Oblique blur is a method of blurring from the oblique direction; oblique blur processing can highlight the coolness of the image, tilt rotation, shock, and the depth of field of the lens. Mosaic is an effect that degrades the gradation details in a specific area of an image and causes color blocks to be disrupted. This blurring effect appears to be composed of small grids, and its purpose is usually to make it unrecognizable. Area filling is an effect processing method that completely fills a certain color or pattern in a closed area of an image. Background overlay is an effect processing method that covers a specific area of an image with another background; the other background can be the background in the image or other backgrounds outside the image.

In specific practical applications, different fuzzy processing methods can be selected for fuzzy processing according to actual conditions and processing effects to be achieved.

By blurring non-subject objects, it has strong pertinence. On the one hand, it can avoid displaying non-subject objects that are unwilling to display on the image, avoiding possible infringement or leakage of privacy information; on the other hand, it can also highlight the main object .

The embodiment of the application obtains the target area of the subject object in the image to be processed, recognizes the non-subject object in the non-target area, and blurs the non-subject object to obtain a target image including the subject object and the non-subject object after the blur process . Since the non-subject objects in the target image have been blurred, in this way, the non-subject objects can be excluded from the target image; the non-subject objects can be prevented from affecting the key appearance of the subject objects in the target image; the non-subject objects can be avoided The subject may cause infringement to avoid unnecessary disputes.

In a practical application, in order to further highlight the main object, and to make the connection between the target area and the blurred non-target area in the target image as natural and beautiful as possible, there is no clear boundary, and the target area Transition processing on the edge, the specific instructions are as follows:

Wherein, in step S103, before obtaining the target image including the subject object and the blurred non-subject object, it may further include: performing transition processing on the edge of the target area; at this time, obtaining the target image including the subject object and the blurred object The target image of the non-subject object may specifically include: obtaining the target image including the subject object after the transition processing is performed on the edge of the target area and the non-subject object after the blur processing is performed.

Further, performing transition processing on the edge of the target area may include: performing one or more processing of feathering, sharpening, liquefying, and enhancing contrast on the edge of the target area.

Feathering processing is to blur the image, making the edges of the image more hazy, softer, and blurred, creating a sense of beauty. Sharpening is to improve the contrast and brightness of image pixels, make the image brighter, and make the edges look more prominent and sharp. Liquefaction is to make the image smooth and smooth, especially to create a perfect and beautiful portrait effect. Enhancing the contrast means to strengthen the contrast between the light and dark of the image, so that the bright part of the image will be brighter and the dark part will be darker; after the contrast is strengthened, the contrast between the original two objects will expand. In specific practical applications, different transition processing methods can be selected for transition processing according to actual conditions and processing effects to be achieved. Refer to FIG. 2, which is an effect diagram after blurring and transition processing of the image to be processed using the image processing method of this application. The left and right sides of the main character in the picture are blurred by the flow of people, and the transition processing adopts the feathering process. The edge of the main character is natural, soft and aesthetic, and the main character image is prominent.

The image to be processed may be one frame, such as a photographing scene, or multiple frames, such as a photographing scene. If the image to be processed is of multiple frames, in step S101, obtaining the target area corresponding to the subject object in the image to be processed may include: obtaining the target area corresponding to the subject object in the multiple frames of image to be processed. Specifically, the target area corresponding to the subject object in each frame of the image to be processed can be obtained separately.

Referring to FIG. 3, in one embodiment, if the subject object remains unchanged, the position of the subject object in the image to be processed does not change much, and the non-subject object remains unchanged, etc., in order to simplify the process and speed up the processing, steps S101 may specifically include:

Sub-step S101a1: Obtain the target area corresponding to the main object in one frame of the image to be processed.

Sub-step S101a2: Use the area corresponding to the target area in one frame of the to-be-processed image as the target area corresponding to the subject object in the other multiple frames of the to-be-processed image.

In this embodiment, the target area corresponding to the subject object in one frame of the to-be-processed image is acquired, the target area corresponds to the area corresponding to the subject object in the other multiple frames of the to-be-processed image, and the target area is in one of the frames to be processed. The corresponding area in the image is used as the target area corresponding to the main object in the other multi-frame images to be processed. In this way, the process can be simplified and the processing speed can be accelerated. In addition to image processing, it is especially suitable for camera application scenarios.

Correspondingly, when the image to be processed is one or more frames, in step S103, the non-subject object is blurred, which specifically includes: selecting one or more frames of the image to be processed, and comparing one or more frames of the image to be processed Blur processing.

As mentioned above, the target area can be automatically generated or adjusted manually; the target area can also be manually selected and generated or adjusted manually. The contour of the target area can match or not match the contour of the main object. Hereinafter, taking the image to be processed is a frame as an example, a possible way of obtaining the target area corresponding to the subject object in the image to be processed is specifically described.

In one embodiment, the system automatically recognizes the main object and generates the original object frame. The original object frame can be manually adjusted, or one of multiple original object frames can be selected as the target object frame, or the size of the object frame can be adjusted, or the object can be adjusted The outline of the frame matches the outline of the main object, or according to the actual situation, multiple adjustment processing procedures are combined to achieve the ultimate goal of obtaining the target area corresponding to the main object in the image to be processed.

Specifically, if the number of original object frames is one, please refer to FIG. 4. In step S101, obtaining the target area corresponding to the subject object in the image to be processed may include: sub-step S101b1, sub-step S101b2, sub-step S101b3, and sub-steps S101b4.

Sub-step S101b1: Identify the main object in the image to be processed according to the object recognition algorithm.

Sub-step S101b2: generate and display the original object frame according to the main object.

Sub-step S101b3: if the number of the original object frame is one, the original object frame is taken as the target object frame.

Sub-step S101b4: Use the area corresponding to the target object frame in the image to be processed as the target area.

Object recognition includes two tasks: classification and detection. Classification is used to determine whether an image contains a certain type of object, and detection requires marking the location and size of these objects. Object recognition algorithms refer to algorithms for object recognition on images. Object recognition algorithms include but are not limited to: Convolutional Neural Networks (CNN), Regional Convolutional Neural Networks (Region CNN, RCNN), Faster-RCNN, Single Point Multi-Box Detector (Single Shot MultiBox Detector, SSD), etc.

In an embodiment, the object recognition algorithm includes a face recognition algorithm. The face recognition algorithm means that after detecting the face and locating the key feature points of the face, the main face area can be cropped out, and after preprocessing, it is fed into the back-end recognition algorithm; the recognition algorithm must complete the facial features Extract and compare with known faces in inventory to complete the final classification.

In this embodiment, the system can automatically recognize the subject object according to the object recognition algorithm, and then generate and display the original object frame corresponding to the subject object. The number of the original object frame is one. If the user has an opinion on the size and/or outline of the original object frame Without other requirements, the original object frame can be used as the target object frame, and the area corresponding to the target object frame in the image to be processed can be used as the target area. In this way, the user's selection process can be simplified and the processing speed can be accelerated. Using face recognition algorithms, in practical applications, its versatility and pertinence are stronger.

Referring to Fig. 5, if the user modifies the size of the target object frame in the image to be processed, before the sub-step S101b4, it may further include:

Sub-step S101b5: Obtain the size modification operation performed by the user on the target object frame in the image to be processed. The function of the size modification operation is to modify the size of the target object frame.

Sub-step S101b6: Generate and display the modified object frame according to the size modification operation.

Sub-step S101b7: re-use the modified object frame as the target object frame.

In this embodiment, the user can modify the size of the target object frame, which can meet user needs and improve user experience.

In one embodiment, the contour of the target area matches the contour of the main object. 6 and 7, in order to match the contour of the target area with the contour of the main object, the user needs to modify the contour of the target object frame in the image to be processed. Then, before sub-step S101b4 in Fig. 4 (as shown in Fig. 6 ), or after the sub-step S101b7 in FIG. 5 (as shown in FIG. 7, that is, after the user adjusts the size of the target object frame, the user also wishes to continue to adjust its outline), it may also include:

Sub-step S101b8: Obtain the contour modification operation performed by the user on the contour of the target object frame in the image to be processed. The function of the contour modification operation is to modify the contour of the target object frame.

Sub-step S101b9: Generate and display the modified object frame according to the contour modification operation, so that the contour of the modified object frame matches the contour of the main object.

Sub-step S101b10: Re-use the modified object frame as the target object frame.

In this embodiment, the user can modify the contour of the target object frame so that the contour of the modified object frame matches the contour of the main object, which can focus on the main object, meet user needs, and improve user experience.

If the number of original object frames is more than two, please refer to Fig. 8. After sub-step S101b2, it may further include:

Sub-step S101c1: If the number of original object frames is more than two, obtain a selection operation performed by the user on one of the original object frames in the image to be processed. The function of the selection operation is to select one of the original object frames from more than two original object frames.

Sub-step S101c2: Generate and display a target object frame according to the selection operation.

Sub-step S101c3: Use the area corresponding to the target object frame in the image to be processed as the target area.

In this embodiment, the system can automatically recognize the main object according to the object recognition algorithm, and then generate and display the original object frame corresponding to the main object. The number of original object frames is more than two, and the user can select one of the original object frames as the target object frame. In this way, the selection process of some users can be simplified, and the processing speed can be partially accelerated.

Similarly, referring to Fig. 9, if the user modifies the size of the target object frame in the image to be processed, before the sub-step S101c3, it may further include:

Sub-step S101c4: Obtain the size modification operation performed by the user on the target object frame in the image to be processed.

Sub-step S101c5: generate and display the modified object frame according to the size modification operation.

Sub-step S101c6: Re-use the modified object frame as the target object frame.

In an embodiment, the contour of the target area matches the contour of the main object. Similarly, referring to Figures 10 and 11, in order to match the contour of the target area with the contour of the main object, the user needs to modify the contour of the target object frame in the image to be processed. Then, before the substep S101c3 of Fig. 8 (such as Fig. 10), or after sub-step S101c6 of Fig. 9 (as shown in Fig. 11, that is, after the user adjusts the size of the target object frame, he also wishes to continue to adjust its outline), it may also include:

Sub-step S101c7: Obtain the contour modification operation performed by the user on the contour of the target object frame in the image to be processed.

Sub-step S101c8: Generate and display the modified object frame according to the contour modification operation, so that the contour of the modified object frame matches the contour of the main object.

Sub-step S101c9: Re-use the modified object frame as the target object frame.

Of course, the target area can also be manually selected and generated, or manually adjusted. The specific instructions are as follows:

Referring to FIG. 12, in one embodiment, in step S101, obtaining a target area corresponding to a subject object in the image to be processed may include:

Sub-step S101d1: Acquire the user's frame selection operation on the subject object in the image to be processed. The function of the frame selection operation is to use the frame to select the main object and determine the size of the frame.

Sub-step S101d2: Generate and display a target object frame according to the frame selection operation.

Sub-step S101d3: Use the area corresponding to the target object frame in the image to be processed as the target area.

In this embodiment, the user directly selects the subject object in the image to be processed (on the one hand, the subject object can be selected, on the other hand, the size of the frame can be adjusted) to determine the target object frame. If there are no other requirements for the contour, the area corresponding to the target object frame in the image to be processed can be used as the target area. In this way, the participation enthusiasm of users can be fully utilized, user needs can be met, and user experience can be improved.

In one embodiment, the contour of the target area matches the contour of the main object. Similarly, referring to Fig. 13, in order to match the contour of the target area with the contour of the main object, the user needs to modify the contour of the target object frame in the image to be processed. Then, before the sub-step S101d3, it may further include:

Sub-step S101d4: Obtain the contour modification operation performed by the user on the contour of the target object frame in the image to be processed.

Sub-step S101d5: Generate and display the modified object frame according to the contour modification operation, so that the contour of the modified object frame matches the contour of the main object.

Sub-step S101d6: re-use the modified object frame as the target object frame.

The following specifically describes the more common preset requirements in practical applications and possible ways to identify non-subject objects in the non-target area based on the preset requirements.

In an actual application, the preset requirements include using ethnic characteristics to distinguish people from objects other than people, and/or using other object characteristics to distinguish between other objects and people.

All people on the earth belong to the same species, the race. Ethnic characteristics refer to the common genetic physical characteristics of races, such as torso ratio, height, limb length, facial contour, head shape, eye shape, nose shape, lip shape, and so on. Ethnic characteristics can distinguish people from other objects.

Other objects include but are not limited to other animate objects and other inanimate objects. Other living objects include, but are not limited to, various pets. Other inanimate objects include but are not limited to vehicles, buildings, etc. Other object features can distinguish other objects and people, for example, the feature of a dog can distinguish a dog from a person, the feature of a vehicle can distinguish a vehicle from a person, and so on.

In this embodiment, ethnic characteristics can be used to distinguish people from objects other than people, other object characteristics can also be used to distinguish other objects from people, or both ethnic characteristics and other object characteristics can be used to distinguish between people and other objects. Other objects outside.

At this time, in step S102, recognizing the non-subject object in the non-target area according to the preset requirements may include: recognizing the non-subject object in the non-target area according to the preset ethnic characteristics and/or the preset features of other objects. This feature and/or preset other object features matching objects, and mark them as non-subject objects.

In this embodiment, the recognition range is a non-target area, and a non-subject object is an object in the non-target area that matches a preset ethnic feature and/or preset features of other objects. For example: a non-subject object is a person in a non-target area (preset ethnic characteristics), or a non-subject object is a vehicle in a non-target area (preset vehicle feature), or a non-subject object is a person and a vehicle in the non-target area (Preset race characteristics and preset vehicle characteristics).

For example: directly use ethnic characteristics to identify people in non-target areas; directly use vehicle characteristics to identify vehicles in non-target areas; or directly use ethnic characteristics and vehicle characteristics to identify people and vehicles in non-target areas.

Specifically, since the license plate number of a vehicle usually involves personal privacy issues, in this embodiment, it is preset that other object features include vehicle features.

In another practical application, the preset requirements include using specific characteristics of race to distinguish different people, and/or using specific characteristics of other objects to distinguish different objects.

Race-specific features refer to the features that can distinguish different people in the image to be processed, and can include unique features that a person has different from other people, such as facial features, iris features, etc.; also Including the non-unique, short-term stable characteristics attached to the human body, such as: human body posture characteristics, clothing characteristics, jewelry characteristics, etc.

Other object-specific features refer to features that can distinguish different other objects in the image to be processed. For example: license plate number, vehicle color, car model, etc.

In this embodiment, the specific characteristics of race can be used to distinguish different people, the specific characteristics of other objects can be used to distinguish different other objects, or the specific characteristics of race can be used to distinguish different people and the specific characteristics of other objects can be used to distinguish different other objects.

The race-specific features and/or other object-specific features in this embodiment can be applied independently or in combination with the aforementioned race features and/or other object features. The specific instructions are as follows:

When a combination of race-specific features and race-specific features, other object-specific features and other object features are used in combination, refer to Figure 14. In step S102, identifying non-subjects in the non-target area according to preset requirements may include: sub-steps S102a1 and sub-step S102a2.

Sub-step S102a1: According to the preset ethnic characteristics and/or preset other object characteristics, identify all human objects and/or all other objects in the image to be processed that match the preset ethnic characteristics and/or preset other object characteristics Object.

Sub-step S102a2: Obtain the specific features of the subject object, identify all people and/or all other objects that do not match the specific features of the subject object, and mark them as non-subject objects, where the specific features of the subject object include Race-specific characteristics and/or other object-specific characteristics.

In this embodiment, the recognition range is the entire image to be processed. First, use the preset ethnic characteristics and/or preset other object characteristics to identify the matching human object and/or all other objects; then, obtain the specific object of the subject. Features: Identify objects that do not match the specific features of the subject from all human objects and/or all other objects, which are non-subject objects.

For example: first use the preset ethnic characteristics to identify all 4 people (including the subject object) in the entire image to be processed, and then identify the other 3 people that do not match the specific characteristics of the main person from these 4 people. These 3 people are It is a non-subject object.

It should be noted that multiple main characters (such as grandfather, grandma, father, mother, children, close friends, etc.) can be stored in advance, and one or more of them can be selected as the main body in specific application scenarios. character.

When the race-specific features and/or other object-specific features are used separately, in step S102, identifying non-subject objects in the non-target area according to preset requirements may include: acquiring the specific features of the subject object, and identifying the non-subject objects in the non-target area Objects that do not match the specific characteristics of the subject object are marked as non-subject objects, where the specific characteristics of the subject object include race-specific characteristics and/or other object-specific characteristics.

In this embodiment, the recognition range is a non-target area, and a non-subject object is an object in the non-target area that does not match the specific feature of the subject object. Directly use the specific characteristics of the subject object to identify the unmatched object in the non-target area, that is, the non-subject object.

For example: directly use the facial features of the main character to identify the other two people who do not match in the non-target area; directly use the red vehicle to identify the unmatched white vehicle in the non-target area.

Among them, the racial specific features that are commonly used in general include one or more of the face, the posture of the human body, and the clothing. Everyone's face is basically different; the posture of the human body is formed by a long-term habit and is generally stable and not easy to change; clothing is also related to a person's personality, taste and other factors, and is generally stable and not easy to change.

In another practical application, if the subject object is stationary and the non-subject object is moving, another method of identifying non-subject objects can also be used, as described below:

Referring to FIG. 15, in step S102, identifying non-subject objects in the non-target area according to preset requirements may include:

Sub-step S102b1: Extract multiple frames of images to be processed including the subject object according to the preset duration.

Sub-step S102b2: judging the moving object from multiple frames of images to be processed, and marking the moving object as a non-subject object.

In this embodiment, the subject object is static, the non-subject object is a moving object, and the moving object is moving and moving. Its position in each frame of image is changing, which is in each frame of image. The background of is also changing. Based on this, the moving object can be determined through multiple frames of images to be processed. Specifically, for example, using frame difference, optical flow, background subtraction, etc., it can be determined through multiple frames of images to be processed Out the moving object.

Among them, non-subject objects that are usually used more often include one or two of moving people and cars. The flow of people involves the issue of portrait rights, and the flow of cars involves the issue of personal privacy, which is a non-subject object that is usually concerned in image processing.

In an actual application, when the ambient brightness is insufficient, the quality of the acquired image to be processed is poor. In order to obtain better image quality, before acquiring the image to be processed in step S101, the method further includes:

The brightness of the current environment is detected, and the exposure mode is determined according to the brightness. Different brightness corresponds to different exposure modes. Specifically, when the ambient light is insufficient, it corresponds to the long exposure mode; when the ambient light is sufficient, it corresponds to the automatic exposure mode. In this way, when the ambient brightness is insufficient, the advantages of the long exposure mode can be fully utilized to obtain better image quality.

In an application scenario, such as shooting, in step S101, before obtaining the target area corresponding to the main object in the image to be processed, it may further include: a time period for prompting the user to stand still.

At this time, in step S102, the identification of non-subject objects in the non-target area according to the preset requirements is completed within the time period when the user is quietly standing, that is, during the time when the user is quietly standing, the non-subject objects are identified according to the preset requirements. Non-subject objects in the target area.

In the existing shooting scene, the user is prompted for the time period when the user needs to stand still. This is a normal operation. The user has developed the corresponding shooting habit. This embodiment uses the shooting habit to complete the identification of non-subjects during the time period when the user is still standing. The flow of the object. In this way, the user can obtain the target image including the subject object and the non-subject object after the blur processing after issuing the shooting instruction, so that the user does not have time to wait for image processing, thereby improving the user experience.

Refer to Figure 16, which is a schematic structural diagram of an embodiment of an image processing device of the present application. It should be noted that the image processing device of this embodiment can execute the steps in the above-mentioned image processing method. For a detailed description of related content, please refer to The part of the image processing method mentioned above will not be repeated here.

The image processing device 10 includes: a memory 11 and a processor 12; the memory 11 and the processor 12 are connected through a bus 13.

Among them, the processor 12 may be a micro control unit, a central processing unit, or a digital signal processor, and so on.

Among them, the memory 11 may be a Flash chip, a read-only memory, a magnetic disk, an optical disk, a U disk or a mobile hard disk, etc.

The memory 11 is used to store computer programs; the memory 11 can also store pre-entered racial characteristic data, other object characteristic data, racial specific characteristic data (such as face data, etc.), and other object specific characteristic data according to actual needs. , Etc., and provide the processor 12 for matching identification.

The processor 12 is used to execute a computer program and, when executing the computer program, implement the following steps:

Obtain the image to be processed, and obtain the target area corresponding to the subject object in the image to be processed; identify the non-subject object in the non-target area according to preset requirements, and the non-target area is the area outside the target area in the image to be processed; for non-subjects The object is subjected to blur processing to obtain a target image including the subject object and the non-subject object after the blur processing.

Wherein, when the processor executes the computer program, the following steps are implemented: acquiring the target area corresponding to the subject object in the multiple frames of images to be processed.

Among them, when the processor executes the computer program, it implements the following steps: obtain the target area corresponding to the subject object in one frame of the to-be-processed image; use the corresponding area of the target area in one of the to-be-processed images as the other multiple frames of the to-be-processed image The target area corresponding to the main object in the middle.

Among them, when the processor executes the computer program, it implements the following steps: recognize the subject object in the image to be processed according to the object recognition algorithm; generate and display the original object frame according to the subject object; if the number of the original object frame is one, the original object The frame is used as the target object frame, and the corresponding area of the target object frame in the image to be processed is taken as the target area.

Among them, when the processor executes the computer program, the following steps are implemented: if the number of original object frames is more than two, obtain the user's selection operation on one of the original object frames in the image to be processed; generate and display according to the selection operation Target object frame; the area corresponding to the target object frame in the image to be processed is taken as the target area.

Among them, object recognition algorithms include face recognition algorithms.

Among them, when the processor executes the computer program, it implements the following steps: obtain the size modification operation performed by the user on the target object frame in the image to be processed; generate and display the modified object frame according to the size modification operation; change the modified object frame As the target object frame again.

Among them, when the processor executes the computer program, it implements the following steps: obtain the user's frame selection operation on the subject object in the image to be processed; generate and display the target object frame according to the frame selection operation; correspond the target object frame in the image to be processed As the target area.

Among them, when the processor executes the computer program, it implements the following steps: obtain the contour modification operation performed by the user on the contour of the target object frame in the image to be processed; generate and display the modified object frame according to the contour modification operation to make the modified object frame The outline of the object frame matches the outline of the main object; the modified object frame is used as the target object frame again.

Among them, the contour of the target area matches the contour of the main object.

Among them, the preset requirements include using ethnic characteristics to distinguish people from objects other than people, and/or using other object characteristics to distinguish other objects from people.

Wherein, when the processor executes the computer program, the following steps are implemented: according to the preset ethnic characteristics and/or the preset other object characteristics, it is recognized that the non-target area matches the preset ethnic characteristics and/or the preset other object characteristics Object and mark it as a non-subject object.

Among them, the preset other object features include vehicle features.

Among them, the preset requirements include using specific characteristics of race to distinguish different people, and/or using specific characteristics of other objects to distinguish different other objects.

Wherein, when the processor executes the computer program, the following steps are implemented: according to the preset ethnic characteristics and/or the preset other object characteristics, it is recognized that the image to be processed matches the preset ethnic characteristics and/or the preset other object characteristics The owner object and/or all other objects; obtain the specific characteristics of the subject object, identify all objects and/or all other objects that do not match the specific characteristics of the subject object, and mark them as non-subject objects, Among them, the specific characteristics of the subject object include the specific characteristics of race and/or the specific characteristics of other objects.

Among them, when the processor executes the computer program, it implements the following steps: obtain the specific features of the subject object, identify the objects in the non-target area that do not match the specific features of the subject object, and mark them as non-subject objects, where the Specific characteristics include race-specific characteristics and/or other object-specific characteristics.

Among them, the ethnic specific characteristics include one or more of the face, the posture of the human body, and the clothing.

Among them, the main object is static, and the non-main object is moving.

Among them, when the processor executes the computer program, it implements the following steps: extracts multiple frames of to-be-processed images including the subject object according to the preset duration; judges the moving object through the multiple-frames of to-be-processed image, and marks the moving object as non Subject object.

Among them, non-subject objects include one or two of moving people and cars.

Wherein, when the processor executes the computer program, the following steps are implemented: detecting the brightness of the current environment, and determining the exposure mode according to the brightness, and different brightnesses correspond to different exposure modes.

Among them, when the ambient light is insufficient, it corresponds to the long exposure mode; when the ambient light is sufficient, it corresponds to the automatic exposure mode.

Wherein, when the processor executes the computer program, the following steps are implemented: transition processing on the edge of the target area; obtaining a target image including a subject object after the transition processing on the edge of the target area and a non-subject object after blur processing.

Wherein, when the processor executes the computer program, it implements the following steps: performing one or more processing of feathering, sharpening, liquefying, and enhancing contrast on the edge of the target area.

Wherein, when the processor executes the computer program, the following steps are implemented: selecting one or more frames of images to be processed, and performing blur processing on one or more frames of images to be processed.

Among them, the blur processing includes one or more blur processing including horizontal blur, vertical blur, radial blur, oblique blur, mosaic, area filling, and background coverage.

Among them, when the processor executes the computer program, it implements the following steps: prompting the user for a period of time when the user needs to stand still.

Wherein, when the processor executes the computer program, the following steps are implemented: during the time period when the user is quietly standing, the non-subject objects in the non-target area are identified according to preset requirements.

The present application also provides a photographing device that can execute the steps in the above-mentioned image processing method. For detailed descriptions of related content, please refer to the above-mentioned image processing method part, which will not be repeated here. The photographing device in the embodiment of the present application includes, but is not limited to, a digital camera, a mobile device equipped with a camera module, and so on. The photographing device includes: a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and when the computer program is executed, the following steps are implemented:

Among them, object recognition algorithms include face recognition algorithms.

Among them, the preset other object features include vehicle features.

Among them, the main object is static, and the non-main object is moving.

Among them, non-subject objects include one or two of moving people and cars.

The blur processing includes one or more blur processing including horizontal blur, vertical blur, radial blur, oblique blur, mosaic, area filling, and background coverage.

Among them, when the processor executes the computer program, it implements the following steps: prompting the user for a period of time for a quiet station.

The present application also provides a movable platform. The movable platform includes a photographing device. The photographing device in this embodiment can be any one of the above-mentioned photographing devices. For detailed descriptions of related content, please refer to the above-mentioned photographing device section, which will not be repeated here. . The photographing device includes: a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and, when the computer program is executed, realize the image processing method as described above.

Among them, the movable platform refers to various platforms that can move automatically or under controlled conditions, including but not limited to one or more of pan/tilt, unmanned aerial vehicle or unmanned vehicle.

This application also provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the processor implements the image processing method as described above. For a detailed description of the relevant content, please refer to the above image processing method section, which is not repeated here.

Wherein, the computer-readable storage medium may be an internal storage unit of any of the foregoing image processing devices, such as a hard disk or memory of the image processing device. The computer-readable storage medium may also be an external storage device of the image processing device, such as a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, etc., equipped on the image processing device.

It should be understood that the terms used in the description of this application are only for the purpose of describing specific embodiments and are not intended to limit the application.

It should also be understood that the term "and/or" used in the specification and appended claims of this application refers to any combination of one or more of the items listed in the associated and all possible combinations, and includes these combinations.

The above are only specific embodiments of this application, but the scope of protection of this application is not limited to this. Any person skilled in the art can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

An image processing method, characterized by comprising:

Acquiring the image to be processed, and acquiring the target area corresponding to the subject object in the image to be processed;

Identifying a non-subject object in a non-target area according to preset requirements, where the non-target area is an area outside the target area in the image to be processed;

Blur processing is performed on the non-subject object to obtain a target image including the subject object and the non-subject object after the blur processing.
The image processing method according to claim 1, wherein said obtaining the target area corresponding to the subject object in the image to be processed comprises:

Acquire the target area corresponding to the subject object in the multiple frames of the image to be processed.
The image processing method according to claim 2, wherein said acquiring a target area corresponding to a subject object in the image to be processed in multiple frames comprises:

Acquiring a target area corresponding to the subject object in one of the frames of the image to be processed;

The area corresponding to the target area in one frame of the image to be processed is used as the target area corresponding to the subject object in the other frames of the image to be processed.
The image processing method according to claim 1, wherein said obtaining the target area corresponding to the subject object in the image to be processed comprises:

Identifying the subject object in the image to be processed according to an object recognition algorithm;

Generating and displaying an original object frame according to the main object;

If the number of the original object frame is one, the original object frame is taken as the target object frame, and the area corresponding to the target object frame in the image to be processed is taken as the target area.
The image processing method according to claim 4, wherein the method further comprises:

If the number of the original object frames is more than two, acquiring a selection operation performed by the user on one of the original object frames in the image to be processed;

Generating and displaying a target object frame according to the selection operation;

The area corresponding to the target object frame in the image to be processed is taken as the target area.
The image processing method according to claim 4, wherein the object recognition algorithm comprises a face recognition algorithm.
The image processing method according to any one of claims 4-5, wherein the step of using the target object frame in the image to be processed in the corresponding region as the target region comprises:

Acquiring the size modification operation performed by the user on the target object frame in the image to be processed;

Generate and display the modified object frame according to the size modification operation;

Re-use the modified object frame as the target object frame.
The image processing method according to claim 1, wherein said obtaining the target area corresponding to the subject object in the image to be processed comprises:

Acquiring a user's frame selection operation on the subject object in the to-be-processed image;

Generating and displaying a target object frame according to the frame selection operation;

The area corresponding to the target object frame in the image to be processed is taken as the target area.
8. The image processing method according to any one of claims 4-8, wherein before using the target object frame in the image to be processed in the corresponding area as the target area, the method comprises:

Acquiring the contour modification operation performed by the user on the contour of the target object frame in the image to be processed;

Generating and displaying a modified object frame according to the contour modification operation, so that the contour of the modified object frame matches the contour of the main object;

Re-use the modified object frame as the target object frame.
The image processing method according to claim 1, wherein the contour of the target area matches the contour of the main object.
The image processing method according to claim 1, wherein the preset requirements include distinguishing people from objects other than people by racial characteristics, and/or distinguishing other objects and people by characteristics of other objects.
The image processing method according to claim 11, wherein the identifying the non-subject object in the non-target area according to a preset requirement comprises:

According to the preset ethnic characteristics and/or the preset other object characteristics, objects in the non-target area that match the preset ethnic characteristics and/or the preset other object characteristics are identified and marked as non-subject objects.
The image processing method according to claim 12, wherein the preset other object characteristics include vehicle characteristics.
The image processing method according to claim 1 or 11, wherein the preset requirements include using specific characteristics of race to distinguish different people, and/or using specific characteristics of other objects to distinguish different other objects.
The image processing method according to claim 14, wherein the identifying the non-subject object in the non-target area according to a preset requirement comprises:

According to preset ethnic characteristics and/or preset other object characteristics, identify all human objects and/or all other objects in the image to be processed that match the preset ethnic characteristics and/or preset other object characteristics Object

Obtain the specific feature of the subject object, identify the object that does not match the specific feature of the subject object among the human object and/or all other objects, and mark it as a non-subject object, wherein the subject object The specific characteristics of includes race-specific characteristics and/or other object-specific characteristics.
The image processing method according to claim 14, wherein the identifying the non-subject object in the non-target area according to a preset requirement comprises:

Acquire the specific feature of the subject object, identify the object in the non-target area that does not match the specific feature of the subject object, and mark it as a non-subject object, wherein the specific feature of the subject object includes race-specific Features and/or other object specific features.
The image processing method according to claim 14, wherein the ethnic specific characteristics include one or more of a human face, a human body posture, and clothing.
The image processing method according to claim 2, wherein the subject object is static and the non-subject object is moving.
The image processing method according to claim 18, wherein the identifying a non-subject object in a non-target area according to a preset requirement comprises:

Extracting multiple frames of to-be-processed images including the subject object according to a preset time length;

The moving object is determined from the multiple frames of images to be processed, and the moving object is marked as a non-subject object.
The image processing method according to claim 18, wherein the non-subject object includes one or two of moving people and traffic.
The image processing method according to claim 1, wherein before the acquiring the image to be processed, the method further comprises:

The brightness of the current environment is detected, and the exposure mode is determined according to the brightness, and different brightnesses correspond to different exposure modes.
22. The image processing method of claim 21, wherein when the ambient light is insufficient, the long exposure mode is corresponding; when the ambient light is sufficient, the automatic exposure mode is corresponding.
The image processing method according to claim 1, wherein before obtaining the target image including the subject object and the non-subject object after blur processing, the method further comprises:

Performing transition processing on the edge of the target area;

The obtaining the target image including the subject object and the non-subject object after the blur processing includes:

Obtain the target image including the subject object after the transition processing on the edge of the target area and the non-subject object after the blur processing.
22. The image processing method according to claim 23, wherein the performing transition processing on the edge of the target area comprises:

One or more of feathering, sharpening, liquefaction, and contrast enhancement are performed on the edge of the target area.
The image processing method according to claim 1, wherein said blurring said non-subject object comprises:

One or more frames of images to be processed are selected, and blur processing is performed on the one or more frames of images to be processed.
The image processing method according to claim 1, wherein the blur processing includes one or more of horizontal blur, vertical blur, radial blur, oblique blur, mosaic, area filling, and background coverage. Blur processing.
The image processing method according to claim 1, wherein before said acquiring the target area corresponding to the subject object in the image to be processed, the method further comprises:

Prompt the user to stop the time period.
The image processing method according to claim 27, wherein the identifying the non-subject object in the non-target area according to a preset requirement comprises:

During the time when the user is standing still, the non-subject objects in the non-target area are identified according to preset requirements.
An image processing device, characterized in that the image processing device includes: a memory and a processor;

The memory is used to store computer programs;

The processor is used to execute the computer program and when executing the computer program, implement the following steps:

Acquiring the image to be processed, and acquiring the target area corresponding to the subject object in the image to be processed;

Identifying a non-subject object in a non-target area according to preset requirements, where the non-target area is an area outside the target area in the image to be processed;

Blur processing is performed on the non-subject object to obtain a target image including the subject object and the non-subject object after the blur processing.
The image processing device according to claim 29, wherein the processor implements the following steps when executing the computer program:

Acquire the target area corresponding to the subject object in the multiple frames of the image to be processed.
The image processing device according to claim 30, wherein the processor implements the following steps when executing the computer program:

Acquiring a target area corresponding to the subject object in one of the frames of the image to be processed;

The area corresponding to the target area in one frame of the image to be processed is used as the target area corresponding to the subject object in the other frames of the image to be processed.
The image processing device according to claim 29, wherein the processor implements the following steps when executing the computer program:

Identifying the subject object in the image to be processed according to an object recognition algorithm;

Generating and displaying an original object frame according to the main object;

If the number of the original object frame is one, the original object frame is taken as the target object frame, and the area corresponding to the target object frame in the image to be processed is taken as the target area.
The image processing device according to claim 32, wherein the processor implements the following steps when executing the computer program:

If the number of the original object frames is more than two, acquiring a selection operation performed by the user on one of the original object frames in the image to be processed;

Generating and displaying a target object frame according to the selection operation;

The area corresponding to the target object frame in the image to be processed is taken as the target area.
The image processing device according to claim 32, wherein the object recognition algorithm comprises a face recognition algorithm.
The image processing device according to any one of claims 32-33, wherein the processor implements the following steps when executing the computer program:

Acquiring the size modification operation performed by the user on the target object frame in the image to be processed;

Generate and display the modified object frame according to the size modification operation;

Use the modified object frame as the target object frame again.
The image processing device according to claim 29, wherein the processor implements the following steps when executing the computer program:

Acquiring a user's frame selection operation on the subject object in the to-be-processed image;

Generating and displaying a target object frame according to the frame selection operation;

The area corresponding to the target object frame in the image to be processed is taken as the target area.
The image processing device according to any one of claims 32-36, wherein the processor implements the following steps when executing the computer program:

Acquiring the contour modification operation performed by the user on the contour of the target object frame in the image to be processed;

Generating and displaying a modified object frame according to the contour modification operation, so that the contour of the modified object frame matches the contour of the main object;

Re-use the modified object frame as the target object frame.
The image processing device according to claim 29, wherein the contour of the target area matches the contour of the main object.
28. The image processing device according to claim 29, wherein the preset requirements include distinguishing people from objects other than people by racial characteristics, and/or distinguishing other objects from people by characteristics of other objects.
The image processing device according to claim 39, wherein said processor implements the following steps when executing said computer program:

According to the preset ethnic characteristics and/or the preset other object characteristics, objects in the non-target area that match the preset ethnic characteristics and/or the preset other object characteristics are identified and marked as non-subject objects.
The image processing device according to claim 40, wherein the preset other object characteristics include vehicle characteristics.
The image processing device according to claim 29 or 39, wherein the preset requirements include using specific characteristics of race to distinguish different people, and/or using specific characteristics of other objects to distinguish different other objects.
The image processing device according to claim 42, wherein the processor implements the following steps when executing the computer program:

According to preset ethnic characteristics and/or preset other object characteristics, identify all human objects and/or all other objects in the image to be processed that match the preset ethnic characteristics and/or preset other object characteristics Object

Obtain the specific feature of the subject object, identify the object that does not match the specific feature of the subject object among the human object and/or all other objects, and mark it as a non-subject object, wherein the subject object The specific characteristics of includes race-specific characteristics and/or other object-specific characteristics.
The image processing device according to claim 42, wherein the processor implements the following steps when executing the computer program:

Acquire the specific feature of the subject object, identify the object in the non-target area that does not match the specific feature of the subject object, and mark it as a non-subject object, wherein the specific feature of the subject object includes race-specific Features and/or other object specific features.
The image processing device according to claim 42, wherein the ethnic specific characteristics include one or more of a human face, a human posture, and clothing.
The image processing device according to claim 30, wherein the subject object is static and the non-subject object is moving.
The image processing device according to claim 46, wherein the processor implements the following steps when executing the computer program:

Extracting multiple frames of to-be-processed images including the subject object according to a preset time length;

The moving object is determined from the multiple frames of images to be processed, and the moving object is marked as a non-subject object.
The image processing device according to claim 46, wherein the non-subject object includes one or two of moving people and cars.
The image processing device according to claim 29, wherein the processor implements the following steps when executing the computer program:

The brightness of the current environment is detected, and the exposure mode is determined according to the brightness, and different brightnesses correspond to different exposure modes.
The image processing device according to claim 49, wherein when the ambient light is insufficient, it corresponds to the long exposure mode; when the ambient light is sufficient, it corresponds to the automatic exposure mode.
The image processing device according to claim 29, wherein the processor implements the following steps when executing the computer program:

Performing transition processing on the edge of the target area;

Obtain the target image including the subject object after the transition processing on the edge of the target area and the non-subject object after the blur processing.
The image processing device according to claim 51, wherein the processor implements the following steps when executing the computer program:

One or more of feathering, sharpening, liquefaction, and contrast enhancement are performed on the edge of the target area.
The image processing device according to claim 29, wherein the processor implements the following steps when executing the computer program:

One or more frames of images to be processed are selected, and blur processing is performed on the one or more frames of images to be processed.
The image processing device according to claim 29, wherein the blur processing includes one or more of horizontal blur, vertical blur, radial blur, oblique blur, mosaic, area filling, and background coverage. Blur processing.
The image processing device according to claim 29, wherein the processor implements the following steps when executing the computer program:

Prompt the user to stop the time period.
The image processing device according to claim 55, wherein the processor implements the following steps when executing the computer program:

During the time when the user is standing still, the non-subject objects in the non-target area are identified according to preset requirements.
A photographing device, characterized in that the photographing device comprises: a memory and a processor;

The memory is used to store computer programs;

The processor is used to execute the computer program, and when executing the computer program, implement the following steps:

Acquiring the image to be processed, and acquiring the target area corresponding to the subject object in the image to be processed;

Identifying a non-subject object in a non-target area according to preset requirements, where the non-target area is an area outside the target area in the image to be processed;

Blur processing is performed on the non-subject object to obtain a target image including the subject object and the non-subject object after the blur processing.
The photographing device according to claim 57, wherein the processor implements the following steps when executing the computer program:

Acquire the target area corresponding to the subject object in the multiple frames of the image to be processed.
The photographing device according to claim 58, wherein the processor implements the following steps when executing the computer program:

Acquiring a target area corresponding to the subject object in one of the frames of the image to be processed;

The area corresponding to the target area in one frame of the image to be processed is used as the target area corresponding to the subject object in the other frames of the image to be processed.
The photographing device according to claim 57, wherein the processor implements the following steps when executing the computer program:

Identifying the subject object in the image to be processed according to an object recognition algorithm;

Generating and displaying an original object frame according to the main object;

If the number of the original object frame is one, the original object frame is taken as the target object frame, and the area corresponding to the target object frame in the image to be processed is taken as the target area.
The photographing device according to claim 60, wherein the processor implements the following steps when executing the computer program:

If the number of the original object frames is more than two, acquiring a selection operation performed by the user on one of the original object frames in the image to be processed;

Generating and displaying a target object frame according to the selection operation;

The area corresponding to the target object frame in the image to be processed is taken as the target area.
The photographing device according to claim 60, wherein the object recognition algorithm comprises a face recognition algorithm.
The photographing device according to any one of claims 60-61, wherein the processor implements the following steps when executing the computer program:

Acquiring the size modification operation performed by the user on the target object frame in the image to be processed;

Generate and display the modified object frame according to the size modification operation;

Re-use the modified object frame as the target object frame.
The photographing device according to claim 57, wherein the processor implements the following steps when executing the computer program:

Acquiring a user's frame selection operation on the subject object in the to-be-processed image;

Generating and displaying a target object frame according to the frame selection operation;

The area corresponding to the target object frame in the image to be processed is taken as the target area.
The photographing device according to any one of claims 60-64, wherein the processor implements the following steps when executing the computer program:

Acquiring the contour modification operation performed by the user on the contour of the target object frame in the image to be processed;

Generating and displaying a modified object frame according to the contour modification operation, so that the contour of the modified object frame matches the contour of the main object;

Re-use the modified object frame as the target object frame.
The photographing device according to claim 57, wherein the contour of the target area matches the contour of the main object.
The photographing device according to claim 57, wherein the preset requirements include distinguishing people from other objects other than people by racial characteristics, and/or distinguishing other objects from people by other object characteristics.
The photographing device according to claim 67, wherein the processor implements the following steps when executing the computer program:

According to the preset ethnic characteristics and/or the preset other object characteristics, objects in the non-target area that match the preset ethnic characteristics and/or the preset other object characteristics are identified and marked as non-subject objects.
The photographing device according to claim 68, wherein the preset other object characteristics include vehicle characteristics.
The photographing device according to claim 57 or 67, wherein the preset requirements include using specific characteristics of race to distinguish different people, and/or using specific characteristics of other objects to distinguish different other objects.
The photographing device according to claim 70, wherein the processor implements the following steps when executing the computer program:

According to preset ethnic characteristics and/or preset other object characteristics, identify all human objects and/or all other objects in the image to be processed that match the preset ethnic characteristics and/or preset other object characteristics Object

Obtain the specific feature of the subject object, identify the object that does not match the specific feature of the subject object among the human object and/or all other objects, and mark it as a non-subject object, wherein the subject object The specific characteristics of includes race-specific characteristics and/or other object-specific characteristics.
The photographing device according to claim 70, wherein the processor implements the following steps when executing the computer program:

Acquire the specific feature of the subject object, identify the object in the non-target area that does not match the specific feature of the subject object, and mark it as a non-subject object, wherein the specific feature of the subject object includes race-specific Features and/or other object specific features.
The photographing device according to claim 70, wherein the ethnic specific characteristics include one or more of a human face, a human posture, and clothing.
The photographing device according to claim 58, wherein the main object is stationary and the non-main object is moving.
The photographing device according to claim 74, wherein the processor implements the following steps when executing the computer program:

Extracting multiple frames of to-be-processed images including the subject object according to a preset time length;

The moving object is determined from the multiple frames of images to be processed, and the moving object is marked as a non-subject object.
The photographing device according to claim 74, wherein the non-subject object comprises one or two of moving people and traffic.
The photographing device according to claim 57, wherein the processor implements the following steps when executing the computer program:

The brightness of the current environment is detected, and the exposure mode is determined according to the brightness, and different brightnesses correspond to different exposure modes.
The photographing device according to claim 77, wherein when the ambient light is insufficient, the long exposure mode corresponds; when the ambient light is sufficient, the automatic exposure mode corresponds.
The photographing device according to claim 57, wherein the processor implements the following steps when executing the computer program:

Performing transition processing on the edge of the target area;

Obtain the target image including the subject object after the transition processing on the edge of the target area and the non-subject object after the blur processing.
The photographing device according to claim 79, wherein the processor implements the following steps when executing the computer program:

One or more of feathering, sharpening, liquefaction, and contrast enhancement are performed on the edge of the target area.
The photographing device according to claim 57, wherein the processor implements the following steps when executing the computer program:

One or more frames of images to be processed are selected, and blur processing is performed on the one or more frames of images to be processed.
The photographing device according to claim 57, wherein the blur processing includes one or more blurs including horizontal blur, vertical blur, radial blur, oblique blur, mosaic, area filling, and background coverage. deal with.
The photographing device according to claim 57, wherein the processor implements the following steps when executing the computer program:

Prompt the user to stop the time period.
The photographing device according to claim 83, wherein the processor implements the following steps when executing the computer program:

During the time when the user is standing still, the non-subject objects in the non-target area are identified according to preset requirements.
A movable platform, characterized in that the movable platform includes a photographing device, and the photographing device includes a memory and a processor;

The memory is used to store computer programs;

The processor is used to execute the computer program and, when executing the computer program, implement the image processing method according to any one of claims 1 to 28.
The movable platform of claim 85, wherein the movable platform comprises one or more of a pan-tilt, an unmanned aerial vehicle, or an unmanned vehicle.
A computer-readable storage medium, characterized in that, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor realizes any one of claims 1 to 28 Image processing method.