Image processing method and device, computer readable storage medium and electronic device

By using the image captured by the first camera with a large amount of light in a dark environment, the problem of poor image noise reduction effect is solved and the image quality is significantly improved.

CN113538462BActive Publication Date: 2024-11-01GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110800986.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-15
Publication Date
2024-11-01
Estimated Expiration
2041-07-15

AI Technical Summary

Technical Problem

The prior art has poor image noise reduction effect in dark light environments, resulting in poor image quality.

Method used

By acquiring the first image taken by the first camera with the light input greater than the second camera in the same scene, the second image is segmented and noise-reduced using the first image to improve segmentation accuracy and noise reduction Effect.

Benefits of technology

Improve image noise reduction effect, especially in dark light environments, and improve image texture clarity and noise removal capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113538462B_ABST
    Figure CN113538462B_ABST
Patent Text Reader

Abstract

The present disclosure provides an image processing method, an image processing device, a computer-readable storage medium and an electronic device, and relates to the field of image processing technology. The image processing method comprises: obtaining a first image and a second image taken for the same scene; wherein the first image is taken by a first camera, the second image is taken by a second camera, and the amount of light entering the first camera is greater than the amount of light entering the second camera; using the first image to perform region segmentation on the second image to obtain at least one first object region of the second image; performing noise reduction processing on the first object region to obtain a second object region corresponding to the first object region. The present disclosure can improve image quality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of image processing, and in particular to an image processing method, an image processing device, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the popularity of electronic devices with shooting functions, more and more users use electronic devices to obtain images. However, due to the shooting method or shooting environment of the camera module, especially the influence of low light, the obtained image will have noise. Although some image noise reduction solutions have emerged, there is still a problem of poor noise reduction effect. Summary of the invention

[0003] The present disclosure provides an image processing method, an image processing device, a computer-readable storage medium and an electronic device, thereby overcoming the problem of poor image noise reduction effect at least to a certain extent.

[0004] According to a first aspect of the present disclosure, there is provided an image processing method, comprising: acquiring a first image and a second image taken for the same scene; wherein the first image is taken by a first camera, the second image is taken by a second camera, and the amount of light entering the first camera is greater than the amount of light entering the second camera; using the first image to perform region segmentation on the second image to obtain at least one first object region of the second image; and performing noise reduction processing on the first object region to obtain a second object region corresponding to the first object region.

[0005] According to a second aspect of the present disclosure, there is provided an image processing device, comprising: an image acquisition module, for acquiring a first image and a second image taken for the same scene; wherein the first image is taken by a first camera, the second image is taken by a second camera, and the amount of light entering the first camera is greater than the amount of light entering the second camera; an image segmentation module, for performing regional segmentation on the second image using the first image to obtain at least one first object region of the second image; and a regional noise reduction module, for performing noise reduction processing on the first object region to obtain a second object region corresponding to the first object region.

[0006] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned image processing method is implemented.

[0007] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising a processor; and a memory for storing one or more programs, wherein when the one or more programs are executed by the processor, the processor implements the above-mentioned image processing method.

[0008] In the technical solutions provided by some embodiments of the present disclosure, a first image captured by a first camera and a second image captured by a second camera for the same scene are obtained, the amount of light entering the first camera is greater than the amount of light entering the second camera, the second image is segmented by the first image to obtain at least one first object region, and the first object region is subjected to noise reduction processing to obtain a corresponding second object region. Given that the amount of light entering the first camera is greater than the amount of light entering the second camera, the texture details of the first image are richer than those of the second image, and the noise of the first image is less than that of the second image. The segmentation accuracy of the first object region can be improved by segmenting the second image by the first image, which is helpful for the noise reduction process of the divided regions and improves the noise reduction effect of the second image.

[0009] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0011] Figure 1 A schematic diagram showing an exemplary system architecture of an image processing solution according to an embodiment of the present disclosure;

[0012] Figure 2 A schematic diagram of the structure of an electronic device suitable for implementing an embodiment of the present disclosure is shown;

[0013] Figure 3 A flowchart schematically shows an image processing method according to an exemplary embodiment of the present disclosure;

[0014] Figure 4 A flowchart for optimizing an object area to be optimized according to an embodiment of the present disclosure is schematically shown;

[0015] Figure 5 A flowchart schematically shows the entire process of image processing according to an embodiment of the present disclosure;

[0016] Figure 6 A block diagram schematically shows an image processing apparatus according to an exemplary embodiment of the present disclosure;

[0017] Figure 7 A block diagram of an image processing apparatus according to another exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0018] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0019] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0020] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the steps. For example, some steps may be decomposed, while some steps may be combined or partially combined, so the actual execution order may change according to the actual situation. In addition, all the terms "first", "second", and "third" below are only for the purpose of distinction and should not be used as limitations of the present disclosure.

[0021] At present, image recognition is often not accurate enough for identifying dark objects, resulting in poor subsequent noise reduction effect and poor image quality. In view of this, the present disclosure provides a new image processing solution.

[0022] Figure 1 A schematic diagram showing an exemplary system architecture of an image processing solution according to an embodiment of the present disclosure.

[0023] like Figure 1 As shown, the system architecture may include a terminal device 1100 and a server 1200. The terminal device 1100 and the server 1200 may be connected via a network, and the connection type of the network may include, for example, a wired or wireless communication link or an optical fiber cable.

[0024] It should be understood that the number of terminal devices 1100 and servers 1200 is only illustrative. According to implementation requirements, there may be any number of terminal devices and servers. For example, the server 1200 may be a server cluster composed of multiple servers. The server 1200 may also be referred to as a cloud or cloud server.

[0025] The terminal device 1100 can interact with the server 1200 through the network to receive or send messages, etc. Figure 1 In the figure, a smart phone is used as an example, however, the terminal device 1100 also includes a tablet computer, a smart wearable device, a personal computer and other devices with a shooting function. Among them, the terminal device 1100 can also be called a terminal, a mobile terminal, a mobile terminal, a smart terminal, etc.

[0026] When the terminal device 1100 performs the image processing process of the exemplary embodiment of the present disclosure, first, the terminal device 1100 may obtain a first image captured by a first camera and a second image captured by a second camera for the same scene, wherein the amount of light entering the first camera is greater than the amount of light entering the second camera.

[0027] Next, the terminal device 1100 can use the first image as a reference to perform region segmentation on the second image to obtain at least one first object region of the second image, and perform noise reduction processing on the first object region to obtain a second object region corresponding to the first object region. Thus, the determined second object region can be used for image stitching to obtain a denoised image corresponding to the second image.

[0028] In addition, if the obtained second object region is the object region to be optimized, the terminal device 1100 can use the first image to perform optimization processing on the object to be optimized, and finally generate a processed image corresponding to the second image.

[0029] When the image processing process of the exemplary embodiment of the present disclosure is performed by the server 1200, first, the server 1200 may obtain a first image captured by a first camera and a second image captured by a second camera for the same scene from the terminal device 1100. The amount of light entering the first camera is greater than the amount of light entering the second camera.

[0030] Next, the server 1200 can use the first image to perform region segmentation on the second image to obtain at least one first object region of the second image, and perform noise reduction processing on the first object region to obtain a second object region corresponding to the first object region. Thus, the determined second object region can be used to perform image stitching to obtain a denoised image corresponding to the second image.

[0031] In addition, if the obtained second object region is the object region to be optimized, the server 1200 may use the first image to perform optimization processing on the object to be optimized, and finally generate a processed image corresponding to the second image.

[0032] Subsequently, the server 1200 may also feed back the generated processed image to the terminal device 1100 for display and / or storage.

[0033] It should be noted that any of the above steps of processing the image can be executed by the terminal device 1100 or the server 1200, and the present disclosure does not impose any limitation on this.

[0034] Figure 2 Schematic diagram of an electronic device suitable for implementing the exemplary embodiment of the present disclosure is shown. The terminal device of the exemplary embodiment of the present disclosure may be configured as follows Figure 2 It should be noted that Figure 2 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0035] The electronic device of the present disclosure includes at least a processor and a memory, wherein the memory is used to store one or more programs. When the one or more programs are executed by the processor, the processor can implement the image processing method of the exemplary embodiment of the present disclosure.

[0036] Specifically, Figure 2 As shown, the electronic device 200 may include: a processor 210, an internal memory 221, an external memory interface 222, a Universal Serial Bus (USB) interface 230, a charging management module 240, a power management module 241, a battery 242, an antenna 1, an antenna 2, a mobile communication module 250, a wireless communication module 260, an audio module 270, a speaker 271, a receiver 272, a microphone 273, an earphone interface 274, a sensor module 280, a display screen 290, a camera module 291, an indicator 292, a motor 293, a button 294, and a Subscriber Identification Module (SIM) card interface 295, etc. The sensor module 280 may include a depth sensor, a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, and a bone conduction sensor, etc.

[0037] It is to be understood that the structure illustrated in the embodiment of the present disclosure does not constitute a specific limitation on the electronic device 200. In other embodiments of the present disclosure, the electronic device 200 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0038] The processor 210 may include one or more processing units, for example, the processor 210 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor and / or a neural network processor (NPU). Different processing units may be independent devices or integrated into one or more processors. In addition, a memory may be provided in the processor 210 for storing instructions and data.

[0039] The electronic device 200 can realize the shooting function through the ISP, the camera module 291, the video codec, the GPU, the display screen 290 and the application processor. In some embodiments, the electronic device 200 may include 1 or N camera modules 291, N is a positive integer greater than 1, and if the electronic device 200 includes N cameras, one of the N cameras is a main camera. In the embodiment of the present disclosure, the electronic device 200 may include at least two cameras, and the amount of light entering one camera is greater than the amount of light entering the other camera. For example, the electronic device 200 may include a visible light camera and a near infrared camera, and the amount of light entering the near infrared camera is greater than the amount of light entering the visible light camera.

[0040] The internal memory 221 can be used to store computer executable program codes, which include instructions. The internal memory 221 can include a program storage area and a data storage area. The external memory interface 222 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 200.

[0041] The present disclosure also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or may exist independently without being assembled into the electronic device.

[0042] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0043] Computer-readable storage media can send, propagate or transmit programs for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0044] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device implements the method described in the following embodiments.

[0045] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0046] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0047] The following describes the steps of the image processing method of the present disclosure executed by a terminal device. In this case, the image processing apparatus of the embodiment of the present disclosure can be configured in the terminal device.

[0048] Figure 3 The flowchart of the image processing method according to the exemplary embodiment of the present disclosure is schematically shown. Figure 3 , the image processing method may include the following steps:

[0049] S32. Acquire a first image and a second image taken for the same scene; wherein the first image is taken by a first camera, the second image is taken by a second camera, and the amount of light entering the first camera is greater than the amount of light entering the second camera.

[0050] In an exemplary embodiment of the present disclosure, the terminal device is configured with at least two cameras, including a first camera and a second camera. The first camera and the second camera can shoot the same scene, and when shooting, the amount of light entering the first camera is greater than the amount of light entering the second camera.

[0051] For the convenience of description, the present disclosure records the image captured by the first camera as the first image, and the image captured by the second camera as the second image. Given that the amount of light entering the first camera is greater than the amount of light entering the second camera, the texture details of the first image are richer than those of the second image, and the noise of the first image is usually less than that of the second image. One of the purposes of the embodiments of the present disclosure is to use the first image as a reference to perform noise reduction and optimization processing on the second image to obtain a processed image corresponding to the second image.

[0052] In addition, it can be understood that the first image and the second image can be a frame of image in a video or a separate photo, and the present disclosure does not limit this.

[0053] For example, the first camera is a near infrared camera, and the second camera is a visible light camera. In this case, the first image is a near infrared image, and the second image is a visible light image.

[0054] According to some embodiments of the present disclosure, the terminal device may simultaneously acquire the first image and the second image. For example, the terminal device may acquire the first image and the second image in response to a user's shooting operation, where the shooting operation may be an operation of waking up the second camera and clicking a shooting button.

[0055] According to some other embodiments of the present disclosure, first, the terminal device may acquire the second image. For example, the terminal device may acquire the second image in response to the operation of waking up the second camera and clicking a capture button.

[0056] When determining to acquire the second image, the terminal device can determine the current ambient light intensity. For example, the terminal device can determine the current ambient light intensity through the brightness detected by the light sensor, or can determine the current ambient light intensity through photosensitivity parameters such as ISO, and the present disclosure does not impose any restrictions on this.

[0057] Next, the terminal device may compare the current ambient light intensity with an ambient light intensity threshold. The present disclosure does not limit the specific value of the ambient light intensity threshold.

[0058] If the current ambient light intensity is less than the ambient light intensity threshold, it means that the current environment is dark. In this case, the first camera is started to obtain the first image.

[0059] If the current ambient light intensity is greater than or equal to the ambient light threshold, it means that the current environment is bright light. In this case, the second image can be directly output or the second image can be output after noise reduction using an existing noise reduction scheme.

[0060] In addition, after the first image and the second image are determined, an alignment operation may be performed on the first image and the second image. Specifically, the alignment operation includes but is not limited to brightness alignment, image alignment, and the like.

[0061] S34. Use the first image to perform region segmentation on the second image to obtain at least one first object region of the second image.

[0062] After acquiring the first image and the second image, the terminal device may perform region segmentation on the second image using the first image. Specifically, the second image may be segmented using the first image as a reference to obtain at least one first object region of the second image.

[0063] According to some embodiments of the present disclosure, first, the terminal device can perform object recognition on the first image, and identify the objects contained in the first image, such as the sky, trees, buildings, portraits, animals, etc. Specifically, an image recognition algorithm such as a convolutional neural network can be used to perform object recognition, and the present disclosure does not limit the process of identifying the object. In addition, it is easy to understand that the determined object can be identified with a label.

[0064] Through object recognition, the contour coordinates of the object in the first image can be determined.

[0065] Next, the terminal device can perform region segmentation on the second image according to the determined contour coordinates to obtain at least one first object region. Specifically, the terminal device can determine the contour coordinates on the second image, and the area surrounded by the contour coordinates is the area obtained by segmenting the second image, that is, the first object area. The present disclosure does not limit the number of segmented first object areas.

[0066] According to some other embodiments of the present disclosure, first, the terminal device may perform object recognition on the first image, determine the contour coordinates of the object in the first image as the first contour coordinates, and perform object recognition on the second image, determine the contour coordinates of the object in the second image as the second contour coordinates.

[0067] Next, the terminal device can calculate the difference between the first contour coordinates and the second contour coordinates, and determine whether the difference is greater than a difference threshold. If the differences corresponding to several coordinate points in the second contour coordinates are greater than the difference threshold, the corresponding coordinate points in the first contour coordinates are used for correction, for example, directly replacing these coordinate points in the second contour coordinates, or replacing these coordinate points by taking the average value. The present disclosure does not impose any restrictions on this.

[0068] After the second contour coordinates are corrected, the second image may be segmented according to the corrected coordinates to obtain at least one first object region.

[0069] S36. Perform noise reduction processing on the first object area to obtain a second object area corresponding to the first object area.

[0070] In an exemplary embodiment of the present disclosure, for each first object area determined in step S34, first, the terminal device may determine the texture complexity of the first object area. For example, the pixel values ​​of the pixels of the first object area may be determined, the variance of the pixel values ​​may be calculated, and the variance may be used to characterize the texture complexity.

[0071] Next, the terminal device may determine the noise reduction intensity of the first object area according to the texture complexity of the first object area. The texture complexity is negatively correlated with the noise reduction intensity. For example, a higher noise reduction intensity may be configured for the sky to achieve the effect of a pure sky; for another example, a lower noise reduction intensity may be configured for leaves, lawns, etc. to achieve the effect of maintaining texture details.

[0072] In addition, a mapping relationship table between the object region type and the noise reduction strength may be pre-configured, and the noise reduction strength of the first object region may be determined through the mapping relationship table.

[0073] After determining the noise reduction strength of the first object area, the noise reduction strength can be used to perform noise reduction processing on the first object area to obtain a second object area corresponding to the first object area. The present disclosure does not limit the specific noise reduction algorithm, for example, it can include high-tech filtering, guided filtering, etc. It can be understood that no matter what kind of noise reduction algorithm is used, its noise reduction strength can be determined using the above method.

[0074] After each first object region is subjected to noise reduction processing and second object regions corresponding to each first object region are obtained, the determined second object regions may be used to perform image stitching to obtain a denoised image corresponding to the second image.

[0075] For example, if the second image is segmented into multiple first object areas, the determined second object areas can be stitched according to the positions of the first object areas in the second image to obtain a denoised image corresponding to the second image. For another example, in addition to the first object areas, the second image may also include a background area remaining after the first object areas are segmented. In this case, the determined second object areas can be stitched with the background area according to the positions of the first object areas in the second image to obtain a denoised image corresponding to the second image.

[0076] In addition, after obtaining the second object region, if the second object region is the object region to be optimized, the object region to be optimized is optimized using the first image to generate a processed image corresponding to the second image. The processed image here refers to an image obtained after denoising and then optimization.

[0077] In an exemplary embodiment of the present disclosure, the object region to be optimized is an object region of a predetermined type. For example, portraits, animals, and trees may be preconfigured as objects to be optimized. It should be noted that the object region to be optimized is the region that has undergone the noise reduction process in step S36.

[0078] In addition, the following description takes optimization of brightness as an example, however, the optimization processing described in the present disclosure may also include other aspects, such as saturation optimization, detail restoration, detail enhancement, etc., and the present disclosure does not limit this.

[0079] refer to Figure 4 An example of optimizing the brightness of the target area will be described.

[0080] In step S402, the terminal device may use the second image to perform brightness correction and / or image alignment operations on the first image to obtain a third image.

[0081] Specifically, for brightness correction, also called brightness alignment, a brightness alignment algorithm such as histogram matching may be used to implement brightness correction, and the present disclosure does not impose any limitation on this.

[0082] For image alignment, the image alignment may be achieved by, for example, extracting features (such as SIFT features) and matching features, and the present disclosure does not impose any limitation on this.

[0083] After the first image undergoes brightness correction and / or image alignment operations, a third image may be obtained.

[0084] In step S404, the terminal device may obtain the position coordinates of the object area to be optimized, and determine the target object area from the third image based on the position coordinates, wherein the target object area is the object area in the third image corresponding to the object area to be optimized.

[0085] In step S406, the terminal device may determine the brightness information of the target object area and the brightness information of the object area to be optimized.

[0086] In step S408, the terminal device may perform weighted fusion on the brightness information of the target object area and the brightness information of the object area to be optimized, thereby implementing the optimization process.

[0087] Specifically, if the brightness of the object area to be optimized is recorded as L1, and the brightness of the pixel points on the target object area is recorded as L2, the brightness Lout of the area after optimization can be obtained by the following formula:

[0088] Lout=(L1*α+L2*β) / (α+β)

[0089] Among them, α and β are adjustable optimization fusion coefficients.

[0090] After the object area to be optimized is optimized, a processed image corresponding to the second image may be obtained, so that the user can view an output image with less noise and clear texture.

[0091] Reference below Figure 5 The entire process of image processing according to the embodiment of the present disclosure is exemplified.

[0092] In step S502, the terminal device obtains a first image captured by a first camera. In step S504, the terminal device obtains a second image captured by a second camera. The amount of light entering the first camera is greater than the amount of light entering the second camera.

[0093] In step S506, the terminal device performs object recognition on the first image to determine contour information of the object.

[0094] In step S508, the terminal device performs region segmentation on the second image using contour information of the object on the first image, and may obtain a plurality of first object regions.

[0095] In step S510, the terminal device may determine the texture complexity of the first object region. In step S512, the terminal device may perform noise reduction processing on the first object region using a noise reduction intensity corresponding to the texture complexity.

[0096] In step S514, the terminal device traverses all the first object areas to determine whether all the first object areas have been subjected to the noise reduction process. If there are first object areas that have not been subjected to the noise reduction process, the terminal device returns to step S510 to continue to perform the noise reduction process on the first object areas. If all the first object areas have been subjected to the noise reduction process, step S516 is performed.

[0097] In step S516, the terminal device may determine whether there is an object region to be optimized in the object region after noise reduction. If not, step S520 is executed to output the result after noise reduction as a processed image corresponding to the second image. If there is an object region to be optimized, step S518 is executed.

[0098] In step S518, the target area to be optimized is optimized using the first image. In this case, in step S520, the result of the optimization process is output as a processed image corresponding to the second image.

[0099] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0100] Furthermore, this exemplary embodiment also provides an image processing device.

[0101] Figure 6 FIG. 1 schematically shows a block diagram of an image processing apparatus according to an exemplary embodiment of the present disclosure. Figure 6 According to an exemplary embodiment of the present disclosure, the image processing device 6 may include an image acquisition module 61 , an image segmentation module 63 , and a regional noise reduction module 65 .

[0102] Specifically, the image acquisition module 61 can be used to acquire a first image and a second image taken for the same scene; wherein the first image is taken by a first camera, the second image is taken by a second camera, and the amount of light entering the first camera is greater than the amount of light entering the second camera; the image segmentation module 63 can be used to use the first image to perform regional segmentation on the second image to obtain at least one first object area of ​​the second image; the regional noise reduction module 65 can be used to perform noise reduction processing on the first object area respectively to obtain a second object area corresponding to the first object area.

[0103] According to an exemplary embodiment of the present disclosure, the image segmentation module 63 may be configured to perform: object recognition on the first image to determine the contour coordinates of the object in the first image; and region segmentation on the second image according to the contour coordinates.

[0104] According to an exemplary embodiment of the present disclosure, the regional noise reduction module 65 can be configured to perform: determining the texture complexity of the first object area; determining the noise reduction strength of the first object area based on the texture complexity of the first object area; and performing noise reduction processing on the first object area using the noise reduction strength of the first object area.

[0105] According to an exemplary embodiment of the present disclosure, the texture complexity is negatively correlated with the noise reduction strength.

[0106] According to an exemplary embodiment of the present disclosure, referring to Figure 7 Compared with the image processing device 6 , the image processing device 7 may further include a region optimization module 71 .

[0107] Specifically, the region optimization module 71 is used for, if the second object region is the object region to be optimized, using the first image to perform optimization processing on the object region to be optimized, so as to generate a processed image corresponding to the second image.

[0108] According to an exemplary embodiment of the present disclosure, the region optimization module 71 can be configured to perform: determining a target object region corresponding to the object region to be optimized based on the first image; determining brightness information of the target object region and brightness information of the object region to be optimized; and performing weighted fusion of the brightness information of the target object region and the brightness information of the object region to be optimized.

[0109] According to an exemplary embodiment of the present disclosure, the process of determining the target object area by the region optimization module 71 can be configured to execute: using the second image to perform brightness correction and / or image alignment operations on the first image to obtain a third image; obtaining the position coordinates of the object area to be optimized; and determining the target object area from the third image based on the position coordinates.

[0110] According to an exemplary embodiment of the present disclosure, the image acquisition module 61 can be configured to perform: acquiring a second image; determining a current ambient light intensity and comparing the current ambient light intensity with an ambient light intensity threshold; and acquiring a first image if the current ambient light intensity is less than the ambient light intensity threshold.

[0111] According to an exemplary embodiment of the present disclosure, the first camera is a near-infrared camera, and the second camera is a visible light camera.

[0112] Since the functional modules of the image processing device in the embodiment of the present disclosure are the same as those in the above-mentioned method embodiment, they will not be described in detail here.

[0113] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0114] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0115] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0116] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing what is disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be considered merely as exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

[0117] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An image processing method, characterized in that: include: Acquire a first image and a second image taken for the same scene; wherein the first image is taken by a first camera, the second image is taken by a second camera, and the amount of light entering the first camera is greater than the amount of light entering the second camera; Performing object recognition on the first image to determine contour coordinates of the object in the first image, and performing region segmentation on the second image according to the contour coordinates to obtain at least one first object region of the second image; Performing noise reduction processing on the first object area to obtain a second object area corresponding to the first object area; Performing noise reduction processing on the first object area includes: determining a texture complexity of the first object region; determining a denoising intensity of the first object area according to a texture complexity of the first object area; The first object area is subjected to noise reduction processing by using the noise reduction strength of the first object area.

2. The image processing method according to claim 1, characterized in that: The texture complexity is negatively correlated with the noise reduction strength.

3. The image processing method according to claim 1, characterized in that: The image processing method further comprises: If the second object region is the object region to be optimized, the object region to be optimized is optimized using the first image to generate a processed image corresponding to the second image.

4. The image processing method according to claim 3, characterized in that: Optimizing the object area to be optimized using the first image includes: determining a target object region corresponding to the object region to be optimized based on the first image; Determining brightness information of the target object area and brightness information of the object area to be optimized; The brightness information of the target object area and the brightness information of the object area to be optimized are weightedly fused.

5. The image processing method according to claim 4, characterized in that: Determining a target object region corresponding to the object region to be optimized based on the first image includes: Using the second image, performing brightness correction and / or image alignment operations on the first image to obtain a third image; Obtain the position coordinates of the object area to be optimized; The target object region is determined from the third image based on the position coordinates.

6. The image processing method according to claim 1, characterized in that: Acquiring a first image and a second image captured for the same scene includes: acquiring the second image; Determining a current ambient light intensity, and comparing the current ambient light intensity with an ambient light intensity threshold; If the current ambient light intensity is less than the ambient light intensity threshold, the first image is acquired.

7. The image processing method according to any one of claims 1 to 6, characterized in that: The first camera is a near-infrared camera, and the second camera is a visible light camera.

8. An image processing device, characterized in that: include: An image acquisition module, used to acquire a first image and a second image taken for the same scene; wherein the first image is taken by a first camera, the second image is taken by a second camera, and the amount of light entering the first camera is greater than the amount of light entering the second camera; An image segmentation module, configured to perform object recognition on the first image, determine contour coordinates of the object in the first image, and perform region segmentation on the second image according to the contour coordinates to obtain at least one first object region of the second image; A regional noise reduction module, configured to perform noise reduction processing on the first object region to obtain a second object region corresponding to the first object region; Among them, the regional denoising module is used to determine the texture complexity of the first object area; determine the denoising strength of the first object area according to the texture complexity of the first object area; and perform denoising on the first object area using the denoising strength of the first object area.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the image processing method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; A memory for storing one or more programs, which, when executed by the processor, enables the processor to implement the image processing method according to any one of claims 1 to 7.