WO2020107376A1

WO2020107376A1 - Image processing method, device, and storage medium

Info

Publication number: WO2020107376A1
Application number: PCT/CN2018/118430
Authority: WO
Inventors: 张良平; 朱涛; 杨小虎
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2018-11-30
Filing date: 2018-11-30
Publication date: 2020-06-04
Also published as: CN110785994A

Abstract

Embodiments of the present invention provide an image processing method, a device, and a storage medium. The method comprises: obtaining an image captured by a photographing device; determining a target region image comprising a target object in the image; and using a first encoding mode to encode the target region image, and using a second encoding mode to encode a region image other than the target region image in the image, wherein the encoding quality of the first encoding mode is higher than the encoding quality of the second encoding mode. In the embodiments of the present invention, the target region image is encoded by using an encoding mode with high encoding quality, and the region image other than the target region image in the image is encoded by using an encoding mode with low encoding quality, thereby reducing the distortion of the target region image, so that after decoding the encoded image, a ground control terminal may accurately identify the target object in the decoded image.

Description

Image processing method, device and storage medium

Technical field

Embodiments of the present invention relate to the field of image technology, and in particular, to an image processing method, device, and storage medium.

Background technique

In the prior art, a shooting device mounted on a mobile platform (such as an unmanned aerial vehicle) can be used to capture images. The mobile platform can send the image captured by the shooting device to a ground control terminal such as a remote control.

Usually, the mobile platform needs to encode and compress the image captured by the shooting device to obtain the encoded image, and then send the encoded image to the ground control terminal. When the ground control terminal receives the encoded image, it needs to Decode the encoded image to obtain a decoded image.

After the image is encoded and compressed, there will be certain distortion, which results in the image obtained by the ground control terminal being decoded inconsistent with the original image captured by the shooting device, so that the ground control terminal cannot accurately identify the target object in the image.

Summary of the invention

Embodiments of the present invention provide an image processing method, device, and storage medium, so that the ground control terminal accurately recognizes the target object in the image sent by the movable platform to the ground control terminal.

A first aspect of an embodiment of the present invention is to provide an image processing method, which is applied to a movable platform, where the movable platform includes a photographing device, including:

Acquiring images captured by the shooting device;

Determining a target area image including a target object in the image, wherein the target object is an object recognized by a ground control terminal communicatively connected to the movable platform;

Encoding the target area image using a first encoding method, and encoding the area image other than the target area image in the image using a second encoding method, wherein the encoding quality of the first encoding method Higher encoding quality than the second encoding mode;

Sending the encoded image to the ground control terminal.

A second aspect of an embodiment of the present invention is to provide an image processing method, which is applied to a ground control terminal. The method includes:

Receiving the encoded image sent by the movable platform, the encoded image is obtained by encoding the image captured by the shooting device on the movable platform;

Decoding the encoded image to obtain a decoded image;

Identify the target object in the decoded image;

Wherein, the encoded image includes first encoded data and second encoded data, and the first encoded data is obtained by encoding the target area image including the target object in the image using a first encoding method, The second encoded data is obtained by encoding a region image other than the target region image in the image using a second encoding method, and the encoding quality of the first encoding method is higher than that of the second encoding method Coding quality.

A third aspect of the embodiments of the present invention is to provide a movable platform, including: a shooting device, a processor, and a communication interface;

The shooting equipment is used to collect images;

The processor is used for:

Acquiring images captured by the shooting device;

The encoded image is sent to the ground control terminal through the communication interface.

A fourth aspect of the embodiments of the present invention is to provide a ground control terminal, including: a communication interface and a processor;

The communication interface is used to receive the encoded image sent by the mobile platform, and the encoded image is obtained by encoding the image captured by the shooting device on the mobile platform;

The processor is used for:

Decoding the encoded image to obtain a decoded image;

Identify the target object in the decoded image;

A fifth aspect of the embodiments of the present invention is to provide a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the method of the first aspect or the second aspect.

The image processing method, device, and storage medium provided in this embodiment determine that the image captured by the shooting device mounted on the mobile platform includes the target area image of the target object, and perform encoding on the target area image using a higher encoding quality encoding method. Encoding, and using a lower encoding quality encoding method to encode the area image in the image other than the target area image, thereby reducing the distortion of the target area image, so that the ground control terminal decodes the encoded image, Can accurately identify the target object in the decoded image.

BRIEF DESCRIPTION

In order to more clearly explain the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without paying any creative labor, other drawings can also be obtained based on these drawings.

FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present invention;

2 is a flowchart of an image processing method provided by an embodiment of the present invention;

3 is a schematic diagram of image processing provided by an embodiment of the present invention;

4 is a schematic diagram of image processing provided by an embodiment of the present invention;

5 is a flowchart of an image processing method according to another embodiment of the present invention;

6 is a structural diagram of a movable platform provided by an embodiment of the present invention;

7 is a structural diagram of a ground control terminal provided by an embodiment of the present invention.

Reference mark:

10: Unmanned aerial vehicle; 11: shooting equipment; 12: PTZ;

13: communication interface; 14: ground control terminal; 15: processor;

31: image; 32: target area; 41: target area;

60: mobile platform; 61: shooting equipment; 62: processor;

63: communication interface; 70: ground control terminal; 71: communication interface;

72: processor.

detailed description

The technical solutions in the embodiments of the present invention will be described clearly below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without making creative efforts fall within the protection scope of the present invention.

It should be noted that when a component is said to be "fixed" to another component, it can be directly on another component or it can also exist in a centered component. When a component is considered to be "connected" to another component, it can be directly connected to another component or there can be centered components at the same time.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention. The terminology used in the description of the present invention herein is for the purpose of describing specific embodiments, and is not intended to limit the present invention. The term "and/or" as used herein includes any and all combinations of one or more related listed items.

The following describes some embodiments of the present invention in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and the features in the embodiments can be combined with each other.

An embodiment of the present invention provides an image processing method. The image processing method can be applied to a movable platform, and the movable platform may specifically be a movable robot, an unmanned aerial vehicle, or the like. The movable platform includes a shooting device, and the shooting device is used for shooting images and/or videos. The shooting device may specifically be a camera, a camera, or the like. Taking an unmanned aerial vehicle as a movable platform as an example for a schematic description, as shown in FIG. Connected, the UAV 10 can send the image captured by the shooting device 11 to the ground control terminal 14 through the communication interface 13. Specifically, the UAV 10 encodes the image captured by the shooting device 11 to obtain an encoded image, and encodes the encoded image Send to the ground control terminal 14. After receiving the coded image, the ground control terminal 14 decodes the coded image. After the image is encoded, there will be a certain distortion, resulting in the inconsistency between the image decoded by the ground control terminal and the original image captured by the shooting device, so that the ground control terminal cannot accurately identify the target object in the decoded image. To solve this problem, an embodiment of the present invention provides an image processing method. The following uses an unmanned aerial vehicle as an example to illustrate the image processing method provided by the embodiment of the present invention. It can be understood that the unmanned aerial vehicle in the later part of this article Both can be replaced with movable objects.

2 is a flowchart of an image processing method provided by an embodiment of the present invention. As shown in FIG. 2, the method in this embodiment may include:

Step S201: Acquire an image captured by the shooting device.

As shown in FIG. 1, the UAV 10 further includes a processor 15, which may specifically be a general-purpose or special-purpose processor. The processor 15 may acquire the image captured by the shooting device 11 in real time and determine whether the image exists A target object, the target object includes at least one of the following: a two-dimensional code, a barcode, and a human face. The target object is specifically an object that needs to be recognized by the ground control terminal 14 that is in communication with the UAV 10, optionally, the target object is an object selected by the user through the ground control terminal 14, optionally, the ground control terminal 14 An application program is installed, such as WeChat, Douyin, Facebook, etc. The target object is specifically an object that the application program needs to recognize. In this embodiment, a two-dimensional code is used as an example.

Step S202: Determine a target area image that includes a target object in the image, where the target object is an object identified by a ground control terminal that is communicatively connected to the movable platform.

As shown in FIG. 3, 31 represents an image captured by the shooting device 11, and the image 31 includes an application installed on the ground control terminal 14, such as a two-dimensional code to be recognized by WeChat. The processor 15 determines a target area image including a two-dimensional code in the image 31, and the target area image is specifically a pixel of the two-dimensional code in the corresponding target area in the image 31.

Optionally, the determining a target area image that includes a target object in the image includes: determining position information of the target object in the image; and determining that the target is included in the image according to the position information Image of the target area of the object.

For example, the processor 15 first determines the position information of the two-dimensional code in the image 31, for example, the position information of the target area corresponding to the two-dimensional code in the image 31, and further determines the image based on the position information 31 includes the target area image of the two-dimensional code.

Optionally, the determining position information of the target object in the image includes: inputting the image into a preset neural network for identifying the target object to determine whether the target object is Location information in the image.

As shown in FIG. 3, the image 31 is input into a preset neural network for identifying a two-dimensional code, and the neural network may specifically be a network model obtained by training based on a large number of two-dimensional code sample images in advance. The neural network can recognize the two-dimensional code in the image 31 and output the position information of the two-dimensional code in the image 31, for example, output the two-dimensional code in the image 31 corresponding to the upper left of the target area 32 Corner and lower right corner location information. The pixels in the target area 32 can be used as the target area image including the two-dimensional code in the image 31.

In other embodiments, a target area slightly larger than the target area 32 may be determined outside the target area 32, as shown in FIG. 4, and the pixels in the target area 41 may be used as the image 31 The image of the target area including the two-dimensional code.

Step S203: Encode the target area image using a first encoding method, and encode the area image other than the target area image in the image using a second encoding method, where the first encoding method The coding quality of is higher than that of the second coding mode.

As shown in FIG. 3, pixels in the target area 32 are encoded using a first encoding method, and pixels other than the target area 32 in the image 31 are encoded using a second encoding method, wherein the first encoding method Encoding quality is higher than that of the second encoding method, that is to say, when the image captured by the shooting device 11 includes the target object that the ground control terminal 14 needs to identify, different encodings are used for different areas in the image Encoding with a high-quality encoding method. For the image of the target area that includes the target object, such as a two-dimensional code, in the image is encoded with a higher encoding quality. For other areas of the image that do not include the two-dimensional code, the image is used Encoding with low encoding quality.

Similarly, as shown in FIG. 4, the pixels in the target area 41 are encoded using the first encoding method, and the pixels other than the target area 41 in the image 31 are encoded using the second encoding method. The encoding quality of one encoding mode is higher than that of the second encoding mode.

The first encoding method is used to encode the target area image, and the second encoding method is used to encode the area image other than the target area image in the image, including the following feasible implementation methods:

A feasible implementation manner is to use the first quantization parameter to encode the target area image, and the second quantization parameter to encode the area image in the image other than the target area image, the first A quantization parameter is smaller than the second quantization parameter.

It can be understood that when encoding an image, the smaller the quantization parameter, the higher the encoding quality; conversely, the larger the quantization parameter, the lower the encoding quality. Therefore, it is possible to encode pixels in the target area 32 shown in FIG. 3 with a smaller quantization parameter, and pixels other than the target area 32 in the image 31 shown in FIG. 3 with a larger quantization parameter To encode, here, the quantization parameter used when encoding the pixels in the target area 32 is recorded as the first quantization parameter, and the quantization parameter used when encoding the pixels in the image 31 other than the target area 32 is recorded as A second quantization parameter, the first quantization parameter is smaller than the second quantization parameter, so that the encoding quality of pixels in the target area 32 is higher than the encoding quality of pixels in the image 31 except for the target area 32.

Similarly, the first quantization parameter is used to encode the pixels in the target area 41 shown in FIG. 4, and the second quantization parameter is used to encode the pixels in the image 31 shown in FIG. 4 other than the target area 41 , So that the encoding quality of the pixels in the target area 41 is higher than the encoding quality of the pixels in the image 31 except for the target area 41.

Another feasible implementation manner is: encoding the target area image with a first code rate, and encoding the area image other than the target area image in the image with a second code rate, the The first code rate is greater than the second code rate.

It can be understood that when encoding an image, the code rate indicates the size of the coded code stream. The larger the code rate, the higher the encoding quality; otherwise, the smaller the code rate, the lower the encoding quality. Therefore, the pixels in the target area 32 shown in FIG. 3 can be encoded with a larger code rate, and the pixels other than the target area 32 in the image 31 shown in FIG. 3 can be coded with a lower code rate To encode, here, the code rate used when encoding the pixels in the target area 32 is recorded as the first code rate, and the code rate used when encoding the pixels in the image 31 other than the target area 32 is recorded as The second code rate, the first code rate is greater than the second code rate, so that the encoding quality of the pixels in the target area 32 is higher than the encoding quality of the pixels in the image 31 except for the target area 32.

Similarly, the first code rate is used to encode the pixels in the target area 41 shown in FIG. 4, and the second code rate is used to encode the pixels in the image 31 shown in FIG. 4 other than the target area 41 , So that the encoding quality of the pixels in the target area 41 is higher than the encoding quality of the pixels in the image 31 except for the target area 41.

In some embodiments, if the target object does not exist in the image, the image is encoded using the second encoding method. For example, when the image captured by the shooting device 11 does not include a two-dimensional code, the image may be encoded using the second encoding method, that is, when the image captured by the shooting device 11 does not include the ground control terminal 14 that needs to be identified When the target object is used, the image is coded using a coding method with a low coding quality.

Step S204: Send the encoded image to the ground control terminal.

As shown in FIG. 3 or FIG. 4, the image 31 includes a target object that the ground control terminal 14 needs to recognize, such as a two-dimensional code. For the target area image that includes the target object such as a two-dimensional code in the image, a higher coding quality is used. The encoding method is used for encoding. For other areas of the image that do not include the two-dimensional code, after encoding with a lower encoding quality, the encoded image corresponding to the image 31 can be obtained. Further, the processor 15 can communicate through The interface 13 sends the encoded image to the ground control terminal 14.

In this embodiment, by determining that the image captured by the shooting device mounted on the mobile platform includes the target area image of the target object, and using a higher encoding quality encoding method to encode the target area image, and using a lower encoding quality encoding method Encode the area images other than the target area image in the image, thereby reducing the distortion of the target area image, so that the ground control terminal can accurately identify the target in the decoded image after decoding the encoded image Object.

An embodiment of the present invention provides an image processing method. Based on the above embodiment, this embodiment can also reduce the frame rate of an image. A feasible implementation manner is: controlling the shooting device to reduce the frequency of acquiring the image.

For example, the shooting device 11 of the UAV 10 can collect 60 frames of images within 1 second. When the processor 15 of the UAV 10 determines that the image collected by the shooting device 11 includes the target object that the ground control terminal 14 needs to recognize, for example, two In the case of dimension codes, the processor 15 can control the shooting device 11 to reduce the frequency of acquiring images, for example, control the shooting device 11 to acquire 30 frames of images within 1 second. When the target area image including the two-dimensional code in the image is encoded with a higher encoding quality encoding method, the amount of code stream data generated after encoding is larger. When the communication between the UAV 10 and the ground control terminal 14 When the bandwidth is limited, a large number of code streams will consume a large bandwidth. By reducing the frame rate of the image, each frame of the image can be allocated a higher bandwidth resource without changing the bandwidth, so that the encoding quality of each frame of the image can be improved accordingly, which is beneficial to improve The probability that the target object is recognized in the image.

Another feasible implementation manner is: if the target object does not exist in the image, discard the image. For example, when the processor 15 determines that the image collected by the shooting device 11 of the UAV 10 does not include the target object, such as a two-dimensional code, the image may be discarded and only the image including the target object may be encoded to reduce the frame of the image frequency.

In this embodiment, the shooting device is controlled to reduce the frequency of acquiring the image, or when the target object does not exist in the image, the image is discarded to reduce the frame rate of the image, save bandwidth, and improve network resource utilization.

An embodiment of the present invention provides an image processing method. FIG. 5 is a flowchart of an image processing method according to another embodiment of the present invention. The image processing method is applied to the ground control terminal. The ground control terminal may specifically be a remote controller, a mobile phone, a tablet computer, etc. The ground control terminal may be installed with application programs, such as WeChat, Douyin, Facebook, etc. As shown in FIG. 5, the method in this embodiment may include:

Step S501: Receive an encoded image sent by a mobile platform, where the encoded image is obtained by encoding an image captured by a shooting device on the mobile platform.

The movable platform described in this embodiment may specifically be an unmanned aerial vehicle. As shown in FIG. 1, the unmanned aerial vehicle 10 is provided with a shooting device 11. The processor 15 of the unmanned aerial vehicle 10 can acquire the image captured by the shooting device 11 in real time and determine whether there is a target to be recognized by the ground control terminal 14 in the image Object, optionally, the target object includes at least one of the following: a two-dimensional code, a barcode, and a human face.

In this embodiment, a two-dimensional code is used as an example for schematic description. As shown in FIG. 3, 31 represents an image captured by the shooting device 11, and the image 31 includes an application installed on the ground control terminal 14, such as a two-dimensional code to be recognized by WeChat, and pixels in the target area 32 are included in the image 31. Image of the target area of the QR code. The processor 15 of the UAV 10 encodes different regions in the image 31 with different encoding quality encoding methods. Specifically, the processor 15 uses the first encoding method to encode the pixels in the target area 32, and uses the first The second encoding method encodes pixels in the image 31 other than the target area 32, wherein the encoding quality of the first encoding method is higher than the encoding quality of the second encoding method, that is, for the image The image of the target area of the two-dimensional code is coded with a coding method of higher coding quality, and the coding of the other area images that do not include the two-dimensional code in the image is coded with a coding method of lower coding quality. By encoding different regions of the image 31, the encoded image corresponding to the image 31 can be obtained. Further, the processor 15 can send the encoded image to the ground control terminal 14 through the communication interface 13. The ground control terminal 14 receives the encoded image sent by the UAV 10, the encoded image includes the encoded data obtained by the processor 15 encoding the pixels in the target area 32 using the first encoding method, and the processor 15 uses the encoded data The second encoding method encodes data obtained by encoding pixels in the image 31 except the target area 32. Here, the encoded data obtained by the processor 15 using the first encoding method to encode the pixels in the target area 32 is recorded as first encoded data, and the processor 15 is using the second encoding method to divide the target area 32 from the image 31 The encoded data obtained by encoding the external pixels is recorded as second encoded data, that is, the encoded image corresponding to the image 31 received by the ground control terminal 14 from the UAV 10 includes the first encoded data and the second Encode the data.

Step S502: Decode the encoded image to obtain a decoded image.

The ground control terminal 14 decodes the encoded image corresponding to the image 31 to obtain a decoded image.

Step S503: Identify the target object in the decoded image.

Since the encoded image corresponding to the image 31 received by the ground control terminal 14 from the UAV 10 includes the encoded data obtained by the processor 15 encoding the pixels in the target area 32 using a higher encoding quality encoding method, and the processor 15. The encoding data obtained by encoding the pixels in the image 31 except for the target area 32 using a lower encoding quality encoding method, therefore, after the ground control terminal 14 decodes the encoded image, the decoded target can be obtained The pixels in the area 32 and the pixels in the image 31 other than the target area 32 are encoded using a higher encoding quality encoding method. Therefore, the ground control terminal 14 uses the decoded target The pixels in the area 32 can accurately identify the two-dimensional code in the target area 32.

In some embodiments, the quantization parameter corresponding to the first encoding mode is smaller than the quantization parameter corresponding to the second encoding mode.

It can be understood that when encoding an image, the smaller the quantization parameter, the higher the encoding quality; conversely, the larger the quantization parameter, the lower the encoding quality. Therefore, it is possible to encode pixels in the target area 32 shown in FIG. 3 with a smaller quantization parameter, and pixels other than the target area 32 in the image 31 shown in FIG. 3 with a larger quantization parameter To encode. That is, when the pixels in the target area 32 are encoded using the first encoding method, and the pixels other than the target area 32 in the image 31 are encoded using the second encoding method, the quantization corresponding to the first encoding method The parameter is smaller than the quantization parameter corresponding to the second encoding method, so that the encoding quality of the pixels in the target area 32 is higher than the encoding quality of the pixels in the image 31 except for the target area 32.

In some other embodiments, the code rate corresponding to the first encoding mode is greater than the code rate corresponding to the second encoding mode.

It can be understood that when encoding an image, the code rate indicates the size of the coded code stream. The larger the code rate, the higher the encoding quality; otherwise, the smaller the code rate, the lower the encoding quality. Therefore, the pixels in the target area 32 shown in FIG. 3 can be encoded with a larger code rate, and the pixels other than the target area 32 in the image 31 shown in FIG. 3 can be coded with a lower code rate When encoding, that is, when the first encoding method is used to encode pixels in the target area 32 and the second encoding method is used to encode pixels in the image 31 other than the target area 32, the first encoding method The corresponding code rate is greater than the code rate corresponding to the second encoding method, so that the encoding quality of the pixels in the target area 32 is higher than the encoding quality of the pixels in the image 31 except for the target area 32.

An embodiment of the present invention provides a movable platform. 6 is a structural diagram of a movable platform provided by an embodiment of the present invention. As shown in FIG. 6, the movable platform 60 includes: a photographing device 61, a processor 62, and a communication interface 63; wherein, the photographing device 61 is used to collect images; The processor 62 is configured to: acquire an image captured by the shooting device; determine an image of a target area including a target object in the image, wherein the target object is an object identified by a ground control terminal communicatively connected to the movable platform ; Use the first encoding method to encode the target area image, and use the second encoding method to encode the area image in the image other than the target area image, wherein, the first encoding method encoding The quality is higher than the encoding quality of the second encoding mode; the encoded image is sent to the ground control terminal through the communication interface 63.

Optionally, the processor 62 is further configured to: if the target object does not exist in the image, use the second encoding method to encode the image.

Optionally, when the processor 62 determines a target area image including a target object in the image, it is specifically used to: determine the position information of the target object in the image; determine the image in the image according to the position information The target area image including the target object.

Optionally, when the processor 62 determines the position information of the target object in the image, it is specifically used to: input the image into a preset neural network for identifying the target object to determine The position information of the target object in the image.

Optionally, when the processor 62 encodes the target area image by using the first encoding method and encodes the area image other than the target area image by using the second encoding method, it is specifically used : Use the first quantization parameter to encode the target area image, and use the second quantization parameter to encode the area image in the image except the target area image, the first quantization parameter is less than the first Two quantitative parameters.

Optionally, when the processor 62 encodes the target area image by using the first encoding method and encodes the area image other than the target area image by using the second encoding method, it is specifically used : Use the first code rate to encode the target area image, and use the second code rate to encode the area image in the image except the target area image, the first code rate is greater than the first Two bit rate.

Optionally, the processor 62 is further configured to: control the shooting device to reduce the frequency of acquiring the image.

Optionally, the processor 62 is further configured to: if the target object does not exist in the image, discard the image.

Optionally, the target object includes at least one of the following: a two-dimensional code, a barcode, and a human face.

Optionally, the movable platform includes an unmanned aerial vehicle. The structure diagram of the unmanned aerial vehicle is shown in FIG. 1 and will not be repeated here.

The specific principles and implementation manners of the movable platform provided by the embodiments of the present invention are similar to the foregoing embodiments, and details are not described herein again.

An embodiment of the present invention provides a ground control terminal. 7 is a structural diagram of a ground control terminal provided by an embodiment of the present invention. As shown in FIG. 7, the ground control terminal 70 includes: a communication interface 71 and a processor 72. The communication interface 71 is used to receive the encoded image sent by the mobile platform, the encoded image is obtained by encoding the image captured by the shooting device on the mobile platform; the processor 72 is used to: Decoding the encoded image to obtain a decoded image; identifying the target object in the decoded image; wherein the encoded image includes first encoded data and second encoded data, the first encoded data is The first encoding method is used to encode the target area image that includes the target object in the image, and the second encoded data is the second encoding method for the image except the target area image in the image After the region image is encoded, the encoding quality of the first encoding method is higher than the encoding quality of the second encoding method.

Optionally, the quantization parameter corresponding to the first encoding mode is smaller than the quantization parameter corresponding to the second encoding mode.

Optionally, the code rate corresponding to the first coding mode is greater than the code rate corresponding to the second coding mode.

In addition, this embodiment also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the image processing method described in the above embodiment.

In the several embodiments provided by the present invention, it should be understood that the disclosed device and method may be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a division of logical functions. In actual implementation, there may be other divisions, for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.

The above integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium. The above software functional units are stored in a storage medium, and include several instructions to enable a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute the method described in each embodiment of the present invention Partial steps. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

Those skilled in the art can clearly understand that, for convenience and conciseness of description, only the above-mentioned division of each functional module is used as an example for illustration. In practical applications, the above-mentioned functions can be allocated by different functional modules according to needs, that is, the device The internal structure of is divided into different functional modules to complete all or part of the functions described above. For the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiments, and details are not described herein again.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, rather than limiting it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features can be equivalently replaced; and these modifications or replacements do not deviate from the essence of the corresponding technical solutions of the technical solutions of the embodiments of the present invention. range.

Claims

An image processing method is applied to a movable platform, wherein the movable platform includes a photographing device, and is characterized by including:

Acquiring images captured by the shooting device;

Determining a target area image including a target object in the image, wherein the target object is an object recognized by a ground control terminal communicatively connected to the movable platform;

Encoding the target area image using a first encoding method, and encoding the area image other than the target area image in the image using a second encoding method, wherein the encoding quality of the first encoding method Higher encoding quality than the second encoding mode;

Sending the encoded image to the ground control terminal.
The method according to claim 1, wherein the method further comprises:

If the target object does not exist in the image, the image is encoded using the second encoding method.
The method according to claim 1 or 2, wherein the determining of the target area image including the target object in the image includes:

Determining the position information of the target object in the image;

Based on the position information, it is determined that a target area image including the target object in the image is included.
The method according to claim 3, wherein the determining position information of the target object in the image includes:

The image is input into a preset neural network for identifying the target object to determine the position information of the target object in the image.
The method according to any one of claims 1 to 4, wherein the first encoding method is used to encode the target area image, and the second encoding method is used to remove the target area from the image Encode images outside the image, including:

Using a first quantization parameter to encode the target area image, and using a second quantization parameter to encode the area image in the image except the target area image, the first quantization parameter is less than the second Quantization parameters.
The method according to any one of claims 1 to 4, wherein the first encoding method is used to encode the target area image, and the second encoding method is used to remove the target area from the image Encode images outside the image, including:

Encoding the target area image with a first code rate, and encoding the area image other than the target area image in the image with a second code rate, the first code rate is greater than the second Code rate.
The method according to any one of claims 1-6, wherein the method further comprises:

Control the shooting device to reduce the frequency of acquiring the image.
The method according to any one of claims 1-7, wherein the method further comprises:

If the target object does not exist in the image, the image is discarded.
The method according to any one of claims 1-8, wherein the target object includes at least one of the following:

QR code, barcode, face.
The method according to any one of claims 1-9, wherein the movable platform includes an unmanned aerial vehicle.
An image processing method, applied to the ground control terminal, characterized by including:

Receiving the encoded image sent by the movable platform, the encoded image is obtained by encoding the image captured by the shooting device on the movable platform;

Decoding the encoded image to obtain a decoded image;

Identify the target object in the decoded image;

Wherein, the encoded image includes first encoded data and second encoded data, and the first encoded data is obtained by encoding the target area image including the target object in the image using a first encoding method, The second encoded data is obtained by encoding a region image other than the target region image in the image using a second encoding method, and the encoding quality of the first encoding method is higher than that of the second encoding method Coding quality.
The method according to claim 11, wherein the quantization parameter corresponding to the first encoding mode is smaller than the quantization parameter corresponding to the second encoding mode.
The method according to claim 11, wherein the code rate corresponding to the first coding mode is greater than the code rate corresponding to the second coding mode.
The method according to any one of claims 11-13, wherein the target object includes at least one of the following:

QR code, barcode, face.
A movable platform is characterized by comprising: shooting equipment, processor and communication interface;

The shooting equipment is used to collect images;

The processor is used for:

Acquiring images captured by the shooting device;

Determining a target area image including a target object in the image, wherein the target object is an object recognized by a ground control terminal communicatively connected to the movable platform;

Encoding the target area image using a first encoding method, and encoding the area image other than the target area image in the image using a second encoding method, wherein the encoding quality of the first encoding method Higher encoding quality than the second encoding mode;

The encoded image is sent to the ground control terminal through the communication interface.
The mobile platform according to claim 15, wherein the processor is further configured to:

If the target object does not exist in the image, the image is encoded using the second encoding method.
The movable platform according to claim 15 or 16, wherein when the processor determines that the image of the target area including the target object in the image is specifically used for:

Determining the position information of the target object in the image;

Based on the position information, it is determined that a target area image including the target object in the image is included.
The mobile platform according to claim 17, wherein the processor is specifically used to determine the position information of the target object in the image:

The image is input into a preset neural network for identifying the target object to determine the position information of the target object in the image.
The mobile platform according to any one of claims 15 to 18, wherein the processor uses a first encoding method to encode the target area image, and uses a second encoding method to divide the image When encoding an area image other than the target area image, it is specifically used for:

Using a first quantization parameter to encode the target area image, and using a second quantization parameter to encode the area image in the image except the target area image, the first quantization parameter is less than the second Quantization parameters.
The mobile platform according to any one of claims 15 to 18, wherein the processor uses a first encoding method to encode the target area image, and uses a second encoding method to divide the image When encoding an area image other than the target area image, it is specifically used for:

Encoding the target area image with a first code rate, and encoding the area image other than the target area image in the image with a second code rate, the first code rate is greater than the second Code rate.
The mobile platform according to any one of claims 15-20, wherein the processor is further used to:

Control the shooting device to reduce the frequency of acquiring the image.
The mobile platform according to any one of claims 15-21, wherein the processor is further used to:

If the target object does not exist in the image, the image is discarded.
The movable platform according to any one of claims 15-22, wherein the target object includes at least one of the following:

QR code, barcode, face.
The movable platform according to any one of claims 15 to 23, wherein the movable platform includes an unmanned aerial vehicle.
A ground control terminal, which is characterized by comprising: a communication interface and a processor;

The communication interface is used to receive the encoded image sent by the mobile platform, and the encoded image is obtained by encoding the image captured by the shooting device on the mobile platform;

The processor is used for:

Decoding the encoded image to obtain a decoded image;

Identify the target object in the decoded image;

Wherein, the encoded image includes first encoded data and second encoded data, and the first encoded data is obtained by encoding the target area image including the target object in the image using a first encoding method, The second encoded data is obtained by encoding a region image other than the target region image in the image using a second encoding method, and the encoding quality of the first encoding method is higher than that of the second encoding method Coding quality.
The ground control terminal according to claim 25, wherein the quantization parameter corresponding to the first encoding mode is smaller than the quantization parameter corresponding to the second encoding mode.
The ground control terminal according to claim 25, wherein the code rate corresponding to the first coding mode is greater than the code rate corresponding to the second coding mode.
The ground control terminal according to any one of claims 25 to 27, wherein the target object includes at least one of the following:

QR code, barcode, face.
A computer-readable storage medium, characterized in that a computer program is stored thereon, the computer program is executed by a processor to implement the method according to any one of claims 1-14.