Deep confidence map processing method and device, storage medium and electronic equipment

Abstract

The present disclosure provides a depth confidence map processing method, a depth confidence map processing device, a computer readable storage medium and an electronic device, and relates to the technical field of computers. The depth confidence map processing method comprises: determining a target region on a depth map, the target region being a region of interest of a user; determining an average value of pixel depth values in the target region; adjusting the pixel depth values of each pixel point in the depth map based on the average value to obtain a confidence weight map; and optimizing an initial depth confidence map using the confidence weight map. The present disclosure can improve the accuracy of the depth confidence map.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a depth confidence map processing method, a depth confidence map processing apparatus, a computer-readable storage medium, and an electronic device. Background Technology

[0002] Depth maps reflect the distances from various points in a shooting scene to the shooting device, playing a crucial role in 3D reconstruction and image processing scenarios such as portrait blurring and image enhancement. Depth confidence maps, as an indispensable part of depth image acquisition, significantly impact the quality of depth images.

[0003] Currently, there is a problem of inaccurate depth confidence maps to some extent, which in turn affects the quality of depth images. Summary of the Invention

[0004] This disclosure provides a depth confidence map processing method, a depth confidence map processing apparatus, a computer-readable storage medium, and an electronic device, thereby overcoming, at least to some extent, the problem of inaccurate depth confidence maps.

[0005] According to a first aspect of this disclosure, a depth confidence map processing method is provided, comprising: determining a target region on a depth map, wherein the target region is a region of interest to a user; determining the average value of pixel depth values ​​within the target region; adjusting the pixel depth values ​​of each pixel in the depth map based on the average value to obtain a confidence weight map; and optimizing the initial depth confidence map using the confidence weight map.

[0006] According to a second aspect of this disclosure, a depth confidence map processing apparatus is provided, comprising: a region determination module for determining a target region on a depth map, wherein the target region is a region of interest to a user; an average value determination module for determining the average value of pixel depth values ​​within the target region; a weight map generation module for adjusting the pixel depth values ​​of each pixel in the depth map based on the average value to obtain a confidence weight map; and a confidence map optimization module for optimizing an initial depth confidence map using the confidence weight map.

[0007] According to a third aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the depth confidence map processing method described above.

[0008] According to a fourth aspect of this disclosure, an electronic device is provided, including a processor; and a memory for storing one or more programs, which, when executed by the processor, cause the processor to implement the depth confidence map processing method described above.

[0009] In some embodiments of this disclosure, the average pixel depth value within a target region on the depth map is determined. Based on this average value, the pixel depth value of each pixel in the depth map is adjusted to obtain a confidence weight map. This confidence weight map is then used to optimize the initial depth confidence map. This disclosure configures weights for the depth confidence map, which can accurately focus on the target region of interest to the user, thus improving the accuracy of the depth confidence map to some extent. Furthermore, in scenarios where the optimized depth confidence map is combined with the depth map for subsequent processing, the optimized depth confidence map can specifically improve the quality of the depth map, thereby enhancing the algorithmic processing performance in these subsequent scenarios.

[0010] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0012] Figure 1 A schematic diagram illustrating the application stages of the depth confidence map processing scheme according to an embodiment of the present disclosure is shown.

[0013] Figure 2 The diagram illustrates the input and output of the depth confidence map processing procedure according to an embodiment of the present disclosure.

[0014] Figure 3 A flowchart illustrating a depth confidence map processing method according to an exemplary embodiment of the present disclosure is shown schematically.

[0015] Figure 4 The flowchart illustrating the entire processing procedure of the depth confidence map processing scheme according to an embodiment of the present disclosure is shown in the illustration.

[0016] Figure 5 A block diagram of a depth confidence map processing apparatus according to an exemplary embodiment of the present disclosure is shown schematically;

[0017] Figure 6 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown schematically. Detailed Implementation

[0018] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0019] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0020] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all steps. For example, some steps may be broken down, while others may be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances. Furthermore, all the terms "first" and "second" used below are for distinction purposes only and should not be construed as limiting the scope of this disclosure.

[0021] Figure 1 A schematic diagram illustrating the application stages of the depth confidence map processing scheme according to an embodiment of this disclosure is shown. (See reference...) Figure 1 In scenarios where depth data is required to perform corresponding algorithm tasks, the terminal device first executes a depth estimation algorithm to obtain a depth map and an initial depth confidence map. Next, the terminal device executes the depth confidence map processing procedure of this disclosure to obtain an optimized depth confidence map. Subsequently, the terminal device uses the depth map and the optimized depth confidence map to perform subsequent processing procedures, including but not limited to portrait blurring, image enhancement, 3D reconstruction, and virtual object localization in AR (Augmented Reality) scenes. This disclosure does not limit the process of performing subsequent algorithms using the optimized depth confidence map.

[0022] The depth confidence map processing scheme of this disclosure can be implemented by a terminal device. That is, each step of the depth confidence map processing method of this disclosure can be executed by a terminal device, and the depth confidence map processing apparatus described below can be configured in the terminal device. This disclosure does not limit the type of terminal device, and it may include, but is not limited to, smartphones, tablets, smart wearable devices, desktop computers, servers, etc.

[0023] Figure 2 A schematic diagram illustrating the input and output of the depth confidence map processing procedure according to an embodiment of this disclosure is shown. (Reference) Figure 2 The input to the depth confidence map processing procedure in this embodiment may include a depth map, an initial depth confidence map, and information about the region of interest (ROI) for the user. The depth map and the initial depth confidence map can be obtained by a depth estimation algorithm, and the ROI information can refer to the location information of the region of interest on the depth map, such as, but not limited to, the area of ​​the focus frame, the portrait area, or the area manually selected by the user.

[0024] The output of the depth confidence map processing process in this embodiment can be an optimized depth confidence map. This optimized depth confidence map can focus on the region of interest to the user in the image, which helps to improve the quality of the depth map and thus improve the processing accuracy of subsequent tasks such as portrait blurring, image enhancement, and 3D reconstruction.

[0025] Figure 3 A flowchart illustrating an exemplary embodiment of the depth confidence map processing method of this disclosure is shown schematically. (Reference) Figure 3 The depth confidence map processing method may include the following steps:

[0026] S32. Determine the target region on the depth map, which is the region of interest to the user.

[0027] In some embodiments of this disclosure, the depth map can be determined based on a depth estimation algorithm. For example, the depth map can be determined based on monocular, multi-view, or other depth estimation algorithms. In other embodiments of this disclosure, the terminal device can acquire a depth map corresponding to the scene using devices such as TOF (Time of Flight) or structured light. This disclosure does not limit the method by which the terminal device acquires the depth map.

[0028] The target area in this disclosure can be an area of ​​interest to the user. In one embodiment, the target area can be the area corresponding to the focus frame during shooting. After starting the camera program on the terminal device, the camera program automatically outputs the focus frame information of the captured image. In another embodiment, the target area can be a portrait area (or any pre-specified object) in the captured image. Additionally, the target area can also be an area determined based on the user's selection operation, such as an area selected by the user in the captured image through clicking, swiping, or other operations. This disclosure does not limit the specific location of the target area.

[0029] In other words, in some embodiments, the target area can be determined automatically by the terminal device without user intervention. In other embodiments, the target area can be manually selected by the user according to their wishes.

[0030] Furthermore, this disclosure does not limit the shape of the target area. For example, in an instance where the target area is a focus frame, the shape of the target area can be rectangular. As another example, when the target area is selected by the user, the shape of the target area can be determined based on the user's selection operation; this shape can be regular or irregular.

[0031] If multiple regions are determined based on any of the above methods, these regions can be used as candidate regions, and the user can select one of these candidate regions as the target region, or the terminal device can select one of these candidate regions as the target region itself.

[0032] In an embodiment where the terminal device selects a target region from these candidate regions on its own, the terminal device may use one or more of the following as selection criteria: object type, region clarity, and region size.

[0033] For example, candidate regions containing object types that the user is interested in are selected compared to those that are not. Another example is that candidate regions with high clarity are selected compared to those with low clarity. Yet another example is that candidate regions with large sizes are selected compared to those with small sizes.

[0034] In embodiments where the terminal device selects based on two or more of the following criteria: object type, region clarity, and region size, different weights can be configured for each criterion. For example, object type can be configured as 0.5, region clarity as 0.2, and region size as 0.3. Subsequently, the terminal device can select the region with the highest score from multiple candidate regions as the target region by weighting these criteria. This disclosure does not limit this process.

[0035] S34. Determine the average pixel depth value within the target area.

[0036] After determining the target region on the depth map, the terminal device can add up the depth values ​​of all pixels in the target region and then divide by the total number of pixels in the target region to determine the average depth value of the pixels in the target region.

[0037] Taking the target area as the focus frame as an example, the information of the focus frame can include the coordinates of the top-left corner and the size of the focus frame. Based on the coordinates of the top-left corner and the size of the focus frame, the pixels to be calculated can be defined. By summing the pixel depth values ​​of these pixels and dividing by the number of pixels, the average pixel depth value within the target area can be obtained.

[0038] S36. Adjust the pixel depth values ​​of each pixel in the depth map based on the average value to obtain a confidence weight map.

[0039] First, the terminal device can determine the distance between the pixel depth value of each pixel in the depth map and the average value determined in step S34, and generate a depth distance image DImage based on the calculated distance.

[0040] Specifically, iterate through each pixel in the depth map, calculate the difference between each pixel and the average value, and take the absolute value to obtain the distance between the pixel depth value of each pixel and the average pixel depth value in the target area.

[0041] Next, the terminal device can generate a confidence weight map using the depth-distance image Dimage. Specifically, the depth-distance image Dimage can be linearly normalized to obtain the confidence weight map.

[0042] The distances between pixels in the depth distance image Dimage can be adjusted using a first distance threshold and a second distance threshold to generate a confidence weight map. The first distance threshold is denoted as T1, and the second distance threshold is denoted as T2, where T1 is greater than T2.

[0043] If the distance of a pixel in the depth distance image Dimage is greater than the first distance threshold T1, the terminal device can adjust the distance of that pixel to 0; if the distance of a pixel in the depth distance image Dimage is less than the second distance threshold, the terminal device can adjust the distance of that pixel to 1.

[0044] If the distance between pixels in the depth distance image Dimage is less than or equal to a first distance threshold and greater than or equal to a second distance threshold, the terminal device can adjust the distance of the pixel based on the pixel's distance, the first distance threshold, and the second distance threshold. Specifically, on one hand, the terminal device can obtain a first difference, which is the difference between the pixel's distance and the second distance threshold; on the other hand, the terminal device can obtain a second difference, which is the difference between the first distance threshold and the second distance threshold. Subsequently, the terminal device can determine the quotient of the first difference and the second difference, and subtract the quotient of the first difference and the second difference from 1 to determine the adjusted distance of the pixel.

[0045] It should be noted that the terminal device can perform the above operation for each pixel in the depth distance image Dimage to obtain the confidence weight map Wimage.

[0046] Specifically, the confidence weight map Wimage can be determined using the following formula:

[0047]

[0048] Where i represents the index of each pixel in the depth distance image Dimage.

[0049] It should be noted that the above scheme for determining the confidence weight map based on the distance of pixel depth is only an example. Other different methods can also be used to determine the confidence weight map, such as Gaussian weights, etc. This disclosure does not limit this.

[0050] S38. Optimize the initial depth confidence map using the confidence weight map.

[0051] In an exemplary embodiment of this disclosure, the depth estimation algorithm can output an initial depth confidence map. In an example where a depth map is directly acquired using a device, the device can also output a depth confidence map, denoted as the initial depth confidence map.

[0052] After the confidence weight map is determined in step S38, the terminal device can use the confidence weight map to optimize the initial depth confidence map to generate an optimized depth confidence map.

[0053] Specifically, the terminal device can multiply the confidence weight map with the initial depth confidence map pixel by pixel to generate an optimized depth confidence map.

[0054] The following example uses the focus frame as the target area. Figure 4 The depth confidence map processing method of the present disclosure embodiments will be described.

[0055] In step S402, the terminal device can determine the focus frame in the depth map and calculate the average value of the pixel depth values ​​within the focus frame.

[0056] In step S404, the terminal device can determine the distance between the depth value of each pixel in the depth map and the average value to generate a depth distance image.

[0057] In step S406, the terminal device can perform linear normalization processing on the depth distance image to generate a confidence weight map.

[0058] In step S408, the terminal device can multiply the confidence weight map with the initial depth confidence map to generate an optimized depth confidence map.

[0059] In the process of applying depth data to portrait blurring, the quality of the depth image has a significant impact on the final blurring result, and the depth confidence map plays a crucial role in improving the quality of the depth image. The depth confidence map processing scheme of this disclosure assigns a weight to each pixel on the depth confidence map, enabling the algorithm to focus on regions of interest to the user. This helps to improve the quality of the depth image, thereby optimizing the portrait blurring result.

[0060] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0061] Furthermore, this example embodiment also provides a depth confidence map processing apparatus.

[0062] Figure 5 A block diagram of a depth confidence map processing apparatus 5 according to an exemplary embodiment of the present disclosure is shown schematically. (Refer to...) Figure 5 The depth confidence map processing apparatus 5 according to an exemplary embodiment of the present disclosure may include a region determination module 51, an average value determination module 53, a weight map generation module 55, and a confidence map optimization module 57.

[0063] Specifically, the region determination module 51 can be used to determine the target region on the depth map, which is the region of interest to the user; the average value determination module 53 can be used to determine the average value of the pixel depth values ​​within the target region; the weight map generation module 55 can be used to adjust the pixel depth values ​​of each pixel in the depth map based on the average value to obtain a confidence weight map; and the confidence map optimization module 57 is used to optimize the initial depth confidence map using the confidence weight map.

[0064] According to an exemplary embodiment of the present disclosure, the weight map generation module 55 may be configured to perform: determining the distance between the pixel depth value of each pixel in the depth map and the average value, and generating a depth distance image based on the calculated distance; and generating a confidence weight map using the depth distance image.

[0065] According to an exemplary embodiment of the present disclosure, the weight map generation module 55 can be configured to perform: adjusting the distance between each pixel in the depth distance image using a first distance threshold and a second distance threshold to generate a confidence weight map.

[0066] According to an exemplary embodiment of this disclosure, the weighted map generation module 55 can be configured to perform: if the distance of a pixel in the depth distance image is greater than a first distance threshold, then adjust the distance of the pixel to 0; if the distance of a pixel in the depth distance image is less than a second distance threshold, then adjust the distance of the pixel to 1; if the distance of a pixel in the depth distance image is less than or equal to the first distance threshold and greater than or equal to the second distance threshold, then adjust the distance of the pixel based on the distance of the pixel, the first distance threshold, and the second distance threshold.

[0067] According to an exemplary embodiment of this disclosure, the weight map generation module 55 can be configured to perform: obtaining a first difference, the first difference being the difference between the distance of a pixel and a second distance threshold; obtaining a second difference, the second difference being the difference between the first distance threshold and a second distance threshold; determining the quotient of the first difference and the second difference, and determining the result of subtracting the quotient of the first difference and the second difference from 1 as the adjusted distance of the pixel.

[0068] According to an exemplary embodiment of the present disclosure, the confidence map optimization module 57 can be configured to perform: multiplying the confidence weight map with the initial depth confidence map pixel by pixel to generate an optimized depth confidence map.

[0069] According to an exemplary embodiment of the present disclosure, the region determination module 51 can be configured to perform: determining a focus frame and determining the region corresponding to the focus frame as a target region on the depth map.

[0070] Since the functional modules of the depth confidence map processing apparatus in this embodiment are the same as those in the above-described method embodiments, they will not be described again here.

[0071] Figure 6 A schematic diagram is shown that is suitable for implementing exemplary embodiments of the present disclosure. The terminal device of the exemplary embodiments of the present disclosure can be configured as follows: Figure 6 In the form of. It should be noted that, Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0072] The electronic device disclosed herein includes at least a processor and a memory, the memory being used to store one or more programs, which, when executed by the processor, enable the processor to implement the depth confidence map processing method of the exemplary embodiments of this disclosure.

[0073] Specifically, such as Figure 6 As shown, the electronic device 60 may include: a processor 610, an internal memory 621, an external memory interface 622, a Universal Serial Bus (USB) interface 630, a charging management module 640, a power management module 641, a battery 642, antenna 1, antenna 2, a mobile communication module 650, a wireless communication module 660, an audio module 670, a sensor module 680, a display screen 690, a camera module 691, an indicator 692, a motor 693, buttons 694, and a Subscriber Identification Module (SIM) card interface 695, etc. The sensor module 680 may include a depth sensor, a pressure sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer, a distance sensor, a proximity sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, and a bone conduction sensor, etc.

[0074] It is understood that the structures illustrated in the embodiments of this disclosure do not constitute a specific limitation on the electronic device 60. In other embodiments of this disclosure, the electronic device 60 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0075] Processor 610 may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors. Additionally, processor 610 may include memory for storing instructions and data.

[0076] The electronic device 60 can implement shooting functions through an ISP, camera module 691, video codec, GPU, display screen 690, and application processor. In some embodiments, the electronic device 60 may include one or N camera modules 691, where N is a positive integer greater than 1. If the electronic device 60 includes N cameras, one of the N cameras is the main camera.

[0077] Internal memory 621 can be used to store executable program code, including instructions. Internal memory 621 may include a program storage area and a data storage area. External memory interface 622 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of electronic device 60.

[0078] This disclosure also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device.

[0079] Computer-readable storage media can be, for example—but not limited to—electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0080] A computer-readable storage medium can be sent, propagated, or transmitted for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.

[0081] A computer-readable storage medium carries one or more programs that, when executed by an electronic device, cause the electronic device to perform the methods described in the embodiments of this disclosure.

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0083] The units described in the embodiments of this disclosure can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the unit itself.

[0084] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0085] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0086] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0087] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0088] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for processing depth confidence maps, characterized in that, include: Determine the target region on the depth map, where the target region is the area of ​​interest to the user; Determine the average pixel depth value within the target region; The distance between the pixel depth value of each pixel in the depth map and the average value is determined, and a depth distance image is generated based on the calculated distance. The depth distance image is then linearly normalized to obtain a confidence weight map. The initial depth confidence map is optimized using the aforementioned confidence weight map.

2. The depth confidence map processing method according to claim 1, characterized in that, The process of obtaining the confidence weight map includes: The distances between each pixel in the depth distance image are adjusted using a first distance threshold and a second distance threshold to generate the confidence weight map.

3. The depth confidence map processing method according to claim 2, characterized in that, Adjusting the distance between pixels in the depth distance image using a first distance threshold and a second distance threshold includes: If the distance between pixels in the depth distance image is greater than the first distance threshold, then the distance between the pixels is adjusted to 0; If the distance between pixels in the depth distance image is less than the second distance threshold, then the distance between the pixels is adjusted to 1; If the distance between pixels in the depth distance image is less than or equal to the first distance threshold and greater than or equal to the second distance threshold, then the distance between the pixels is adjusted based on the distance between the pixels, the first distance threshold, and the second distance threshold.

4. The depth confidence map processing method according to claim 3, characterized in that, Adjusting the distance of the pixels based on the distance between pixels, the first distance threshold, and the second distance threshold includes: Obtain a first difference, which is the difference between the distance of the pixel and the second distance threshold; Obtain a second difference, which is the difference between the first distance threshold and the second distance threshold; The quotient of the first difference and the second difference is determined, and the result of subtracting the quotient of the first difference and the second difference from 1 is determined as the adjusted distance of the pixel.

5. The depth confidence map processing method according to claim 1, characterized in that, Optimizing the initial depth confidence map using the aforementioned confidence weight map includes: The confidence weight map is multiplied pixel by pixel with the initial depth confidence map to generate an optimized depth confidence map.

6. The depth confidence map processing method according to claim 1, characterized in that, Determining the target region on the depth map includes: Determine the focus frame, and define the area corresponding to the focus frame as the target area on the depth map.

7. A depth confidence map processing device, characterized in that, include: The region determination module is used to determine the target region on the depth map, wherein the target region is the region of interest to the user; An average value determination module is used to determine the average value of pixel depth values ​​within the target area; The weight map generation module is used to determine the distance between the pixel depth value of each pixel in the depth map and the average value, generate a depth distance image based on the calculated distance, and perform linear normalization processing on the depth distance image to obtain a confidence weight map. The confidence map optimization module is used to optimize the initial depth confidence map using the confidence weight map.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the depth confidence map processing method as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: processor; A memory for storing one or more programs, which, when executed by the processor, cause the processor to implement the depth confidence map processing method as described in any one of claims 1 to 6.

Images