Image processing method, device and electronic system

Abstract

The present invention provides an image processing method, device and electronic system, which obtains a plurality of images to be processed whose exposure corresponding to a target scene is lower than a preset exposure threshold and whose exposure is the same; performs image registration processing on the plurality of images to be processed; and performs image fusion processing on the plurality of images to be processed after image registration to obtain an image processing result. In this method, in a scene with insufficient lighting such as at night, a plurality of images to be processed whose exposure is lower than a preset exposure threshold and whose exposure is the same are captured, and the plurality of images to be processed are processed by image registration and image fusion. This method can keep the image brightness of the plurality of images to be processed consistent, which is conducive to improving the image registration effect, avoiding ghosting of the fused image, and thus improving the overall image effect.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image processing method, device and electronic system. Background Art

[0002] In scenes with insufficient lighting, such as at night, the images captured by the camera are generally dark and of poor quality. In order to improve the quality of the image, multiple images of different exposures can be obtained for the same scene, and the images of different exposures can be fused; during the fusion process, the areas with lower brightness are processed with images of higher exposure, and the areas with higher brightness are processed with images of lower exposure, thereby outputting an image with a high dynamic range. However, this method has the following defects: due to the different exposures of the images, the brightness of the images is inconsistent, and in addition, the camera shakes and the scene moves during the shooting process, which makes the image registration effect poor, resulting in the final fused image being prone to ghosting. Summary of the invention

[0003] In view of this, an object of the present invention is to provide an image processing method, device and electronic system to improve the image registration effect, avoid the generation of ghost images, and further improve the overall image effect.

[0004] In a first aspect, an embodiment of the present invention provides an image processing method, the method comprising: acquiring multiple images to be processed corresponding to a target scene; wherein the exposure of the multiple images to be processed is lower than a preset exposure threshold, and the exposure of the multiple images to be processed is the same; performing image registration processing on the multiple images to be processed; performing image fusion processing on the multiple images to be processed after image registration to obtain an image processing result.

[0005] Furthermore, the step of performing image registration processing on the multiple images to be processed includes: determining a reference image from the multiple images to be processed; and performing image registration processing on the images other than the reference image among the multiple images to be processed based on the reference image.

[0006] Furthermore, before the step of performing image fusion processing on the multiple images to be processed after image registration to obtain the image processing result, the method also includes: obtaining a standard image of a specified exposure corresponding to the target scene; performing image fusion processing on the multiple images to be processed after image registration to obtain the image processing result, including: performing image fusion processing on the multiple images to be processed after image registration according to the standard image to obtain the image processing result.

[0007] Furthermore, the specified exposure is EV0; the exposure of the plurality of images to be processed is less than the specified exposure.

[0008] Furthermore, according to the standard image, the multiple images to be processed after image registration are subjected to image fusion processing to obtain the image processing result, including: based on the reference image in the multiple images to be processed, the standard image is subjected to image registration processing to obtain the registered standard image; the registered standard image is subjected to overexposure detection to obtain the first detection result; according to the registered standard image and the first detection result, the multiple images to be processed after image registration are subjected to image fusion processing to obtain the image processing result.

[0009] Furthermore, based on the reference image among the multiple images to be processed, the standard image is subjected to image registration processing to obtain the registered standard image, including: adjusting the brightness of the standard image according to the brightness parameters of the reference image among the multiple images to be processed to obtain an intermediate image; performing image registration processing on the intermediate image and the reference image among the multiple images to be processed to obtain a registration offset; based on the registration offset, performing image registration processing on the standard image to obtain a registered standard image.

[0010] Furthermore, based on the aligned standard image and the first detection result, the multiple images to be processed after the image alignment are subjected to image fusion processing to obtain the step of image processing results, including: for each pixel position, superimposing the pixel values ​​at the pixel position in the multiple images to be processed after the image alignment to obtain an initial result; performing overexposure detection on the initial result to obtain a second detection result; and determining the image processing result based on the aligned standard image, the first detection result, the second detection result, and the initial result.

[0011] Furthermore, before the step of superimposing the pixel values ​​at the pixel position in the multiple images to be processed after image registration to obtain the initial result for each pixel position, the method also includes: taking each image except the reference image in the multiple images to be processed as the current image, performing the following operations: for each pixel position, determining whether the absolute value of the difference between the pixel value at the pixel position of the current image and the pixel value at the pixel position of the reference image is greater than a preset pixel value threshold; if greater than the pixel value threshold, adjusting the pixel value at the pixel position of the current image so that the absolute value is less than or equal to the pixel value threshold.

[0012] Furthermore, the step of determining the image processing result according to the aligned standard image, the first detection result, the second detection result, and the initial result includes: for each pixel position in the initial result, performing the following operations to obtain a final pixel value at each pixel position, and determining the final pixel value at each pixel position as the image processing result: if both the first detection result and the second detection result indicate that the pixel position is overexposed, determining the final pixel value at the pixel position according to a preset value and the pixel value at the pixel position in the reference image; if the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, determining the final pixel value at the pixel position according to the pixel values ​​at the pixel position in the aligned standard image and the reference image; if the second detection result indicates that the pixel position is not overexposed, determining the pixel value at the pixel position in the initial result as the final pixel value at the pixel position.

[0013] Furthermore, if both the first detection result and the second detection result indicate that the pixel position is overexposed, the step of determining the final pixel value at the pixel position according to the preset value and the pixel value at the pixel position in the reference image includes: if both the first detection result and the second detection result indicate that the pixel position is overexposed, looping the following operations until a first preset number of operations is reached, and determining the final pixel value at the pixel position according to the operation result obtained from each operation: determining the first number of images to be superimposed according to the preset value and the pixel value at the pixel position in the reference image; determining the first number of images to be superimposed from the multiple images to be processed after image registration; and superimposing the pixel values ​​at the pixel position in the determined images to be processed to obtain the operation result.

[0014] Further, if the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, the step of determining the final pixel value at the pixel position according to the pixel value at the pixel position in the aligned standard image and the reference image comprises: if the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, looping the following operations until a second preset number of operations is reached, and determining the final pixel value at the pixel position according to the operation result obtained from each operation: determining the second number of images to be superimposed according to the pixel value at the pixel position in the aligned standard image and the reference image; determining the second number of images to be superimposed from the multiple images to be processed after the image alignment; and superimposing the pixel values ​​at the pixel position in the determined images to be processed to obtain the operation result.

[0015] In a second aspect, an embodiment of the present invention provides an image processing device, which includes: an acquisition module, used to acquire multiple images to be processed corresponding to a target scene; wherein the exposure of the multiple images to be processed is lower than a preset exposure threshold, and the exposure of the multiple images to be processed is the same; a registration module, used to perform image registration processing on the multiple images to be processed; and a fusion module, used to perform image fusion processing on the multiple images to be processed after image registration to obtain an image processing result.

[0016] In a third aspect, an embodiment of the present invention provides an electronic system, which includes: a processing device and a storage device; the storage device stores a computer program, and the computer program executes the image processing method of any one of the first aspects when the processed device runs.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processing device, the steps of the image processing method as described in any one of the first aspects are executed.

[0018] The embodiments of the present invention bring the following beneficial effects:

[0019] The present invention provides an image processing method, device and electronic system, which obtains a plurality of images to be processed whose exposure corresponding to a target scene is lower than a preset exposure threshold and whose exposure is the same; performs image registration processing on the plurality of images to be processed; and performs image fusion processing on the plurality of images to be processed after image registration to obtain an image processing result. In this method, in a scene with insufficient lighting such as at night, a plurality of images to be processed whose exposure is lower than a preset exposure threshold and whose exposure is the same are captured, and the plurality of images to be processed are processed by image registration and image fusion. This method can keep the image brightness of the plurality of images to be processed consistent, which is conducive to improving the image registration effect, avoiding ghosting of the fused image, and thus improving the overall image effect.

[0020] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A schematic diagram of the structure of an electronic system provided by an embodiment of the present invention;

[0024] Figure 2 A flowchart of an image processing method provided by an embodiment of the present invention;

[0025] Figure 3 A flowchart of another image processing method provided by an embodiment of the present invention;

[0026] Figure 4 A flowchart of another image processing method provided by an embodiment of the present invention;

[0027] Figure 5 A flowchart of another image processing method provided by an embodiment of the present invention;

[0028] Figure 6 A flow chart of a method for determining an image processing result provided by an embodiment of the present invention;

[0029] Figure 7 A flowchart of a specific image processing method provided by an embodiment of the present invention;

[0030] Figure 8 A schematic diagram of the structure of an image processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] At present, the super night scene mode is an important function of the camera device. Its main function is to obtain pure and high dynamic range images in scenes with insufficient lighting such as at night. In order to improve the quality of the image and enhance the user experience, the super night scene algorithm is usually used; the common super night scene algorithm at present usually uses a variety of images with different exposures for fusion, that is, taking images of different exposures for the same target scene, and fusion of the images with different exposures. The basic idea of ​​fusion is to use images with higher exposures for processing areas with lower brightness, and use images with lower exposures for processing areas with higher brightness, so as to output images with high dynamic range. In addition, in order to obtain a purer night scene image, the super night scene algorithm usually performs a certain time domain or spatial domain denoising on the input image before fusion.

[0033] However, the above method has the following defects: due to the different exposure levels of the images, the registration process is more difficult, resulting in inconsistent image brightness and inconsistent noise levels in the images; during actual shooting, there are factors such as jitter and scene motion in the shooting device, which makes the image registration effect poor, resulting in the final fused image being prone to ghosting; in addition, based on the generation mechanism of images with different exposure levels, the noise levels of the input images are inconsistent, and after fusion, there will be problems such as large noise in some places and small noise in other places, which will also make the fusion result unnatural; for example, street lights at night will produce halos in long-exposure images but not in short-exposure images, which will make the fusion result unnatural; and long-exposure images can easily become blurred due to reasons such as jitter of the camera device, so the fusion result will also be unnatural.

[0034] Based on this, an image processing method, device and electronic system provided by an embodiment of the present invention can be applied to devices with camera functions such as computers, smart phones, cameras, tablet computers, etc. The technology can be implemented using relevant software and hardware, and is described below through embodiments. To facilitate understanding of this embodiment, an image processing method disclosed in an embodiment of the present invention is first introduced in detail.

[0035] Embodiment 1:

[0036] First, refer to Figure 1 An exemplary electronic system 100 for implementing the image processing method, apparatus, and electronic system according to the embodiments of the present invention is described.

[0037] like Figure 1 The electronic system 100 includes one or more processing devices 102, one or more storage devices 104, an input device 106, an output device 108, and may also include one or more image acquisition devices 110. These components are interconnected through a bus system 112 and / or other forms of connection mechanisms (not shown). It should be noted that Figure 1 The components and structure of the electronic system 100 shown are merely exemplary and non-limiting. The electronic system may also have other components and structures as required.

[0038] The processing device 102 can be a gateway, or a smart terminal, or a device including a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities. It can process data of other components in the electronic system 100 and control other components in the electronic system 100 to perform desired functions.

[0039] The storage device 104 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processing device 102 may run the program instructions to implement the client functions and / or other desired functions in the embodiments of the present invention (implemented by the processing device) described below. Various applications and various data, such as various data used and / or generated by the application, may also be stored in the computer-readable storage medium.

[0040] The input device 106 may be a device used by a user to input instructions, and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.

[0041] The output device 108 may output various information (eg, images or sounds) to the outside (eg, a user), and may include one or more of a display, a speaker, and the like.

[0042] The image acquisition device 110 can acquire preview video frames or picture data (such as images to be processed or target video frames), and store the acquired preview video frames or image data in the storage device 104 for use by other components.

[0043] Exemplarily, the components in the example electronic system for implementing the image processing method, device and electronic system according to the embodiment of the present invention can be integrated or dispersed, such as integrating the processing device 102, the storage device 104, the input device 106 and the output device 108 into one body, and setting the image acquisition device 110 at a specified position where the image can be acquired. When the components in the above electronic system are integrated, the electronic system can be implemented as a smart terminal such as a camera, a smart phone, a tablet computer, a computer, a vehicle-mounted terminal, a video camera, etc.

[0044] Embodiment 2:

[0045] This embodiment provides an image processing method, such as Figure 2 As shown, the method comprises the following steps:

[0046] Step S202, obtaining a plurality of images to be processed corresponding to the target scene; wherein the exposure of the plurality of images to be processed is lower than a preset exposure threshold, and the exposure of the plurality of images to be processed is the same;

[0047] Among them, the above-mentioned target scene can be a scene with insufficient lighting, such as a road with street lights at night; the above-mentioned image to be processed can be taken by the front camera of a mobile phone, or by the rear camera of a mobile phone, or by other camera devices; wherein the multiple images to be processed can be multiple images of the same exposure obtained by quickly and continuously shooting by the same camera device; the above-mentioned exposure can include the exposure value (Exposure Value, EV) of shooting the image to be processed, such as exposure time, aperture of the camera device, etc.; the above-mentioned preset exposure threshold is usually set according to the actual target scene, for example, the exposure value is 0, namely EV0, or it can be -2, namely EV-2; usually, the lower the exposure value, the darker the brightness of the corresponding image to be processed; the brightness of the image to be processed corresponding to EV0 is the brightest, and the images to be processed corresponding to EV-2 and EV-4 are darker than the brightness of the image to be processed corresponding to EV0.

[0048] Step S204, performing image registration processing on a plurality of images to be processed;

[0049] The multiple images to be processed are taken by the same camera device. During the shooting process, there may be differences between the pixel positions of different images to be processed due to the shaking of the camera device during the shooting process. In order to eliminate the position differences between the pixels in the multiple images to be processed, the multiple images to be processed can be image registered. In addition, the image registration process can be performed on all the images in the multiple images to be processed, or on some of the images in the multiple images to be processed.

[0050] The above-mentioned image registration processing usually refers to the process of matching and superimposing two or more images acquired at different times, with different sensors (imaging devices) or under different conditions (weather, illumination, camera position and angle, etc.); in addition, the above-mentioned image registration processing process may include various registration methods, such as optical flow method, MeshFlow (interactive visualization of mesh construction sequence), Patch-Based (based on block matching) and other methods; in this embodiment, specifically, one image to be processed can be selected from multiple images to be processed as a reference image, and other images to be processed can be registered with the reference image, wherein the coordinate system of the pixels in each image to be processed can be arbitrary; a control grid can also be pre-defined, and all images to be processed are registered relative to the control grid, that is, the geometric correction of each image to be processed is completed respectively, so as to achieve the unification of the element coordinate system in each image to be processed, and complete the image registration processing.

[0051] Step S206, performing image fusion processing on the multiple images to be processed after image registration to obtain an image processing result.

[0052] The above-mentioned image fusion usually refers to extracting the useful information from each image to the maximum extent through image processing and computer technology, and finally synthesizing it into a high-quality image to improve the image quality. Specifically, since the exposure of multiple images to be processed is lower than a preset exposure threshold, the image corresponding to the preset exposure threshold and the pixel information of the image can be used to guide the multiple images to be processed, and the image processing result can be obtained by adjusting, superimposing, fusing, averaging, and calculating differences in pixel values. The image processing result can be a pure high dynamic range image.

[0053] The embodiment of the present invention provides an image processing method, which obtains a plurality of images to be processed whose exposure corresponding to a target scene is lower than a preset exposure threshold and whose exposure is the same; performs image registration processing on the plurality of images to be processed; and performs image fusion processing on the plurality of images to be processed after image registration to obtain an image processing result. In this method, in a scene with insufficient lighting such as at night, a plurality of images to be processed whose exposure is lower than a preset exposure threshold and whose exposure is the same are captured, and the plurality of images to be processed are processed by image registration and image fusion. This method can keep the image brightness of the plurality of images to be processed consistent, which is conducive to improving the image registration effect, avoiding ghosting of the fused image, and thus improving the overall image effect.

[0054] Embodiment three:

[0055] This embodiment provides another image processing method, which is implemented on the basis of the above embodiment. This embodiment focuses on the specific implementation process of the step of performing image registration processing on multiple images to be processed (implemented by steps S304-S306), and the implementation process of the step of performing image fusion processing on the multiple images to be processed after image registration to obtain the image processing result (implemented by steps S308-S310), as shown in FIG. Figure 3 As shown, the method comprises the following steps:

[0056] Step S302, obtaining a plurality of images to be processed corresponding to the target scene; wherein the exposure of the plurality of images to be processed is lower than a preset exposure threshold, and the exposure of the plurality of images to be processed is the same;

[0057] Step S304, determining a reference image from a plurality of images to be processed;

[0058] Specifically, an image to be processed may be randomly selected from multiple images to be processed as a reference image; or edge information of each image to be processed may be extracted to determine an image to be processed with the clearest edge information and the most detail information as a reference image.

[0059] Step S306, using the reference image as a reference, performing image registration processing on the images to be processed except the reference image;

[0060] Specifically, a relative registration method can be used to register the images other than the reference image in multiple images to be processed with the reference image as a benchmark; the registration method can perform template matching and pattern recognition on the reference image and the images other than the reference image, calculate the cross-correlation value between the reference image and the image to be processed, and register the image to be processed according to the cross-correlation value; the residual sum between the reference image and the images other than the reference image at a certain pixel point can be calculated according to the sequential similarity detection matching method, and the image to be processed can be registered according to the residual sum; the image to be processed can also be registered according to the transform domain method through image translation, rotation, affine and other transformations; finally, the coordinates of the object in the image to be processed are made the same as the coordinates of the same object in the reference image; in addition, the multiple images to be processed after the above-mentioned image registration can also include the reference image.

[0061] Step S308, obtaining a standard image of a specified exposure corresponding to the target scene;

[0062] The above-mentioned specified exposure can be set according to the actual target scene, which can be exposure values ​​such as EV-2, EV0, EV2, etc.; the above-mentioned standard image is shot by the same shooting device as the aforementioned multiple images to be processed, and they are all images shot by one shooting device; wherein the shooting method can be rapid and continuous shooting by one shooting device.

[0063] Preferably, the above-mentioned specified exposure is EV0; the exposure of the plurality of images to be processed is less than the specified exposure;

[0064] Generally, the image to be processed with an exposure less than EV0 is darker than the specified image with an exposure of EV0; the exposure of the above-mentioned multiple images to be processed may be EV-2, EV-4 or other EV levels.

[0065] Step S310: performing image fusion processing on the multiple images to be processed after image registration according to the standard image to obtain an image processing result.

[0066] Since the standard image is brighter and has better image quality than other images to be processed, the standard image can be used as a reference to perform image fusion processing on the multiple images to be processed after image registration. Specifically, according to the pixel value of each pixel in the standard image and pixel information, by comparing the pixel values ​​of the pixels at the corresponding positions in the image to be processed after image registration, the pixel values ​​of the pixels in the multiple images to be processed after image registration can be adjusted to correct the pixel values ​​of the pixels in the image to be processed after image registration, and finally the image processing result can be obtained by superposition, averaging, etc.; the image registration can also be performed first The multiple images to be processed are fused by superposition, matching, etc. to obtain an initial image processing result. By comparing the pixel values ​​of each pixel in the standard image and the pixel information, the pixel values ​​of the pixels in the initial image processing result are adjusted to finally obtain the image processing result. It is also possible to use a preset threshold value and a threshold judgment method to determine whether the pixel value of each pixel in the initial image processing result is greater than the threshold value. According to the judgment result, the pixel value of the pixel in the standard image is used to adjust the pixel value of the pixel in the initial image processing result to finally obtain the image processing result. Among them, the preset threshold value can be set according to the actual target scene.

[0067] In this method, with the reference image as a benchmark, image registration processing is performed on the images other than the reference image among the multiple images to be processed; a standard image of a specified exposure corresponding to the target scene is obtained; and the exposure of the multiple images to be processed is less than the specified exposure; according to the standard image, the multiple images to be processed after image registration are subjected to image fusion processing to obtain image processing results; this implementation method, in scenes with insufficient lighting such as night, uses a standard image with a specified exposure of EV0 to guide the fusion processing of the multiple images to be processed after image registration, to generate a high-dynamic night scene image, thereby avoiding the problem of overexposure of highlights; using images with the same exposure for image fusion can make the image brightness of the multiple images to be processed consistent, which is beneficial to improving the image registration effect, avoiding the generation of ghost images in the fused image, and thereby improving the overall image effect.

[0068] Embodiment 4:

[0069] This embodiment provides another image processing method, which is implemented on the basis of the above embodiment. This embodiment focuses on describing the specific implementation process of the step of performing image fusion processing on multiple images to be processed after image registration according to the standard image to obtain the image processing result (implemented by steps S410-S414), such as Figure 4 As shown, the method comprises the following steps:

[0070] Step S402, obtaining a plurality of images to be processed corresponding to the target scene; wherein the exposure of the plurality of images to be processed is lower than a preset exposure threshold, and the exposure of the plurality of images to be processed is the same;

[0071] Step S404, determining a reference image from a plurality of images to be processed;

[0072] Step S406, using the reference image as a reference, performing image registration processing on the images to be processed except the reference image;

[0073] Step S408, obtaining a standard image of a specified exposure corresponding to the target scene;

[0074] Step S410, performing image registration processing on the standard image based on the reference image among the multiple images to be processed to obtain a registered standard image;

[0075] Specifically, taking the reference image as a benchmark, the standard image can be registered according to the cross-correlation method, sequential similarity detection matching method, transform domain method, optical flow method, meshflow, patch-based and other methods to obtain the registered standard image; finally, the coordinates of the objects in the standard image are made the same as the coordinates of the same objects in the reference image.

[0076] With respect to the above step S410, the step of performing image registration processing on the standard image based on the reference image among the multiple images to be processed to obtain the registered standard image includes:

[0077] Step A1, adjusting the brightness of the standard image according to the brightness parameter of the reference image among the multiple images to be processed to obtain an intermediate image;

[0078] Step A2, registering the intermediate image with a reference image among the multiple images to be processed to obtain a registration offset; and performing image registration on the standard image based on the registration offset to obtain a registered standard image.

[0079] Specifically, the standard image or the histogram of a certain area in the standard image can be matched to the reference image according to the histogram matching method, and the brightness of the reference image and the intermediate image can be kept consistent by adjusting the brightness of the standard image; wherein, before the reference image and the intermediate image are matched, their histogram forms are usually kept consistent. The standard image after brightness adjustment, i.e., the intermediate image, is image registered with the reference image in the multiple images to be processed to obtain the registration offset of the intermediate image; according to the obtained registration offset of the intermediate image, the pixel coordinates of the standard image are adjusted to obtain the registered standard image.

[0080] It should be noted that by adjusting the standard image using histogram matching, the pixel brightness of the standard image and the reference image of the image to be processed can be kept at the same level to improve the accuracy of registration. In addition, the brightness of the registered standard image has not changed, only the spatial coordinates have been adjusted.

[0081] Step S412, performing overexposure detection on the registered standard image to obtain a first detection result;

[0082] Among them, overexposure detection may include methods such as threshold judgment method or morphological filtering; the above-mentioned first detection result includes a mask image corresponding to the registered standard image, the pixel value of the pixels in the overexposed area in the mask image is 1, and the pixel value of the pixels in the non-overexposed area is 0; for example, through the threshold judgment method, for the pixel value of each pixel in the standard image, if the pixel value of the pixel is greater than the preset threshold, the pixel is an overexposed pixel, and the pixel value of the pixel is determined to be 1; if the pixel value of the pixel is less than or equal to the preset threshold, the pixel is a non-overexposed pixel, and the pixel value of the pixel is determined to be 0; the first detection result finally obtained can be the mask image corresponding to the registered image, and the mask image can be represented as mask1.

[0083] Step S414, performing image fusion processing on the multiple images to be processed after image registration according to the registered standard image and the first detection result to obtain an image processing result.

[0084] Specifically, it is possible to judge whether the pixel at the position is overexposed based on the pixel value of the pixel in the first detection result, and based on the judgment result, adjust the pixel value of the pixel in the multiple images to be processed after the image registration by using the pixel value of the pixel position in the registered standard image to correct the pixel value of the pixel in the image to be processed after the image registration, and finally obtain the image processing result by superposition, averaging, etc.; it is also possible to first fuse the multiple images to be processed after the image registration by superposition, matching, etc. to obtain an initial image processing result, and judge whether the pixel point is overexposed based on the pixel value of the pixel in the first detection result, and based on the judgment result, The pixel value of the pixel at the corresponding position in the registered standard image and the pixel value of the pixel in some of the multiple images to be processed are used to adjust the pixel value of the pixel in the initial image processing result, and finally the image processing result is obtained; the pixel value of each pixel in the initial image processing result can also be judged by a preset threshold value through a threshold judgment method to determine whether the pixel value of the pixel is greater than the threshold, and at the same time, the pixel value of the pixel in the first detection result can be used to determine whether the pixel point is overexposed. According to the judgment result, the pixel value of the pixel in the standard image is used to adjust the pixel value of the pixel in the initial image processing result, and finally the image processing result is obtained.

[0085] In this method, image registration processing is performed on the standard image according to the reference image, and the brightness of the registered standard image is adjusted to obtain the adjusted standard image; overexposure detection is performed on the adjusted standard image to obtain the first detection result; and image fusion processing is performed on the multiple images to be processed after image registration according to the registered standard image and the first detection result to obtain the image processing result. In this implementation method, in scenes with insufficient lighting such as night, the adjusted standard image with a specified exposure of EV0 and the first detection result are used to guide the fusion processing of multiple images to be processed after image registration to generate a high-dynamic night scene image, thereby avoiding the problem of overexposure of highlights; using images with the same exposure for image fusion can reduce the difficulty of image registration, keep the brightness of multiple images to be processed consistent, and help improve the image registration effect, avoid ghosting of the fused image, and thus improve the overall image effect.

[0086] Embodiment five:

[0087] This embodiment provides another image processing method, which is implemented on the basis of the above embodiment. This embodiment focuses on describing the specific implementation process of the step of performing image fusion processing on multiple images to be processed after image registration according to the registered standard image and the first detection result to obtain the image processing result (implemented by steps S514-S520), such as Figure 5 As shown, the method comprises the following steps:

[0088] Step S502, obtaining a plurality of images to be processed corresponding to the target scene; wherein the exposure of the plurality of images to be processed is lower than a preset exposure threshold, and the exposure of the plurality of images to be processed is the same;

[0089] Step S504, determining a reference image from a plurality of images to be processed;

[0090] Step S506, using the reference image as a reference, performing image registration processing on the images to be processed except the reference image;

[0091] Step S508, obtaining a standard image of a specified exposure corresponding to the target scene;

[0092] Step S510, performing image registration processing on the standard image based on the reference image among the multiple images to be processed to obtain a registered standard image;

[0093] Step S512, performing overexposure detection on the registered standard image to obtain a first detection result;

[0094] Step S514, for each image except the reference image among the multiple images to be processed, as the current image, the following operations are performed: for each pixel position, determine whether the absolute value of the difference between the pixel value of the pixel position of the current image and the pixel value of the pixel position of the reference image is greater than a preset pixel value threshold; if it is greater than the pixel value threshold, adjust the pixel value of the pixel position of the current image so that the absolute value is less than or equal to the pixel value threshold;

[0095] For multiple images to be processed corresponding to the target scene, if there are moving objects in the target scene, such as walking people, moving cars, etc., the multiple registered images to be processed are directly superimposed, and ghost images may appear in the superimposed images. In order to avoid ghost images, motion detection can be performed on the multiple registered images to be processed. The above current image is the registered image to be processed; the above preset pixel value threshold can be set according to the actual target scene. For example, if the target scene is a person walking normally, the threshold can be set according to the walking speed of the person; for another example, if the target scene is a car driving at high speed, the threshold can be set according to the speed of the car. Generally, the faster the object moves, the larger the threshold, and vice versa.

[0096] Specifically, for the pixel position of each pixel, determine whether the absolute value of the difference between the pixel value of the pixel position of the currently registered image to be processed and the pixel value of the pixel position of the reference image is greater than a preset pixel value threshold; if it is greater than the pixel value threshold, the pixel value of the pixel position of the current image can be corrected, for example, by adding or subtracting a random value from the pixel value of the pixel position of the reference image, which random value falls within the preset pixel value threshold range, so that the absolute value is ultimately less than or equal to the pixel value threshold.

[0097] Step S516, for each pixel position, superimposing the pixel values ​​at the pixel position in the plurality of images to be processed after image registration to obtain an initial result;

[0098] Since the multiple images to be processed have undergone the aforementioned image registration processing, motion detection and other processing, the position of each pixel in each image to be processed after processing can correspond to each other; for each pixel position, the pixel values ​​at the pixel position in the multiple images to be processed after image registration are directly added to obtain an initial result; since the exposure of the multiple images to be processed is less than the specified exposure, the image brightness of the initial result obtained after the addition processing will be brighter.

[0099] Step S518, performing overexposure detection on the initial result to obtain a second detection result;

[0100] Among them, overexposure detection may include methods such as threshold judgment method or morphological filtering; the above-mentioned second detection result includes a mask image corresponding to the initial result, and the pixel values ​​of pixels in the overexposed area in the mask image are 1, and the pixel values ​​of pixels in the non-overexposed area are 0; for example, through the threshold judgment method, for the pixel value of each pixel in the initial result, if the pixel value of the pixel is greater than the preset threshold, the pixel is an overexposed pixel, and the pixel value of the pixel is determined to be 1; if the pixel value of the pixel is less than or equal to the preset threshold, the pixel is a non-overexposed pixel, and the pixel value of the pixel is determined to be 0; the final second detection result may be the mask image corresponding to the initial result, and the mask image may be represented as mask2.

[0101] Step S520, determining an image processing result according to the registered standard image, the first detection result, the second detection result, and the initial result.

[0102] Specifically, whether the pixel at the position point is overexposed can be judged based on the pixel values ​​of the pixels in the first detection result and the second detection result, respectively; based on the judgment result, the pixel value of the pixel at the pixel position in the registered standard image is used to adjust the pixel value of the pixel in the initial result to correct the pixel value of the overexposed pixel in the initial result, and obtain the pixel value of the pixel in the image processing result; or, based on the judgment result, the pixel value of the pixel in the initial image is directly determined as the pixel value of the pixel in the image processing result; and finally the image processing result is obtained.

[0103] For the above step S520, refer to Figure 6 The flowchart of the method for determining the image processing result is as follows. The step of determining the image processing result according to the registered standard image, the first detection result, the second detection result, and the initial result includes:

[0104] For each pixel position in the initial result, perform the following operations to obtain the final pixel value at each pixel position, and determine the final pixel value at each pixel position as the image processing result:

[0105] Step S602, if both the first detection result and the second detection result indicate that the pixel position is overexposed, determining a final pixel value at the pixel position according to a preset value and a pixel value at the pixel position in a reference image;

[0106] The above-mentioned preset value can be set according to the actual target scene, for example, it can be set to 128, etc.; specifically, it can be determined whether the pixel position is overexposed based on the pixel value of each pixel in the first detection result and the second detection result, for example, a pixel value equal to 1 indicates that the pixel position is overexposed; at this time, the number of images to be processed that participate in the calculation of the final pixel value at the pixel position can be determined based on the preset value and the pixel value at the pixel position in the reference image; the number of intermediate images can be selected randomly or in a specified manner from multiple images to be processed, and the final pixel value at the pixel position is determined based on multiple pixel values ​​of the pixel in the intermediate image.

[0107] A preferred implementation:

[0108] If both the first detection result and the second detection result indicate that the pixel position is overexposed, the following operations are performed cyclically until a first preset number of operations is reached, and a final pixel value at the pixel position is determined according to the operation result obtained by each operation:

[0109] For example, the average value of the operation results obtained by multiple operations can be used as the final pixel value at the pixel position, wherein each operation includes the following sub-steps: determining the first number of images to be superimposed according to a preset value and the pixel value at the pixel position in the reference image; determining the first number of images to be superimposed from the multiple images to be processed after image registration; and superimposing the pixel values ​​at the pixel position in the determined images to be processed to obtain the operation result.

[0110] The first preset number of operations can be set to three times, or four times, etc. In this embodiment, the first preset number of operations is taken as an example for explanation, the preset value can be expressed as Value, the first number of images to be superimposed can be expressed as Nnew1, and the pixel value at the pixel position in the reference image can be expressed as x; in actual implementation, the specific calculation of the first number of images to be superimposed can be Nnew1=round(Value / x); wherein the round() function returns a value, which is the result of rounding according to the specified number of decimal places; then randomly select Nnew1 images to be processed from the multiple images to be processed after image registration, wherein the Nnew1 images to be processed include the reference image; add the pixel values ​​of the pixel in the Nnew1 images to be processed to obtain the first operation result; in the same way, calculate the second operation result and the third operation result; calculate the average value of the first operation result, the second operation result and the third operation result, and determine the average value as the final pixel value at the pixel position.

[0111] Step S604, if the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, determining a final pixel value at the pixel position according to the pixel values ​​at the pixel position in the registered standard image and the reference image;

[0112] Specifically, whether the pixel position is overexposed can be determined based on the pixel value of each pixel in the first detection result and the second detection result. For example, a pixel value equal to 1 indicates that the pixel position is overexposed, and a pixel value equal to 0 indicates that the pixel position is not overexposed. At this time, the number of images to be processed that participate in the calculation of the final pixel value at the pixel position can be determined based on the pixel values ​​at the pixel position in the aligned standard image and the reference image. The number of intermediate images can be selected randomly or in a specified manner from multiple images to be processed, and the final pixel value at the pixel position can be determined based on multiple pixel values ​​of the pixel in the intermediate image.

[0113] A preferred implementation:

[0114] If the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, the following operations are performed in a loop until a second preset number of operations is reached, and a final pixel value at the pixel position is determined according to the operation result obtained by each operation:

[0115] For example, the average value of the operation results obtained by multiple operations can be used as the final pixel value at the pixel position, wherein each operation includes the following sub-steps: determining the second number of images to be superimposed according to the pixel value at the pixel position in the registered standard image and the reference image; determining the second number of images to be superimposed from the multiple images to be processed after the image registration; and superimposing the pixel values ​​at the pixel position in the determined images to be processed to obtain the operation result.

[0116] The second preset number of times can be set to three times, or four times, etc. In this embodiment, the second preset number of operations is taken as three times as an example for explanation, the pixel value at the pixel position in the above-mentioned registered standard image can be expressed as InValue, the second number of images to be superimposed can be expressed as Nnew2, and the pixel value at the pixel position in the above-mentioned reference image can be expressed as y; in actual implementation, the specific calculation of the second number of images to be superimposed can be Nnew2=round(InValue / y); wherein the round() function returns a value, which is the result of rounding according to the specified number of decimal places; then randomly select Nnew2 images to be processed from the multiple images to be processed after image registration, wherein the Nnew2 images to be processed include the reference image; add the pixel values ​​of the pixel in the Nnew2 images to be processed to obtain the first operation result; in the same way, calculate the second operation result and the third operation result; calculate the average value of the first operation result, the second operation result and the third operation result, and determine the average value as the final pixel value at the pixel position.

[0117] Step S606: If the second detection result indicates that the pixel position is not overexposed, the pixel value at the pixel position in the initial result is determined as the final pixel value at the pixel position.

[0118] If the pixel value of the pixel in the second detection result is 0, it indicates that the pixel position is not overexposed; at this time, regardless of whether the pixel position is overexposed in the first detection result, the pixel value at the pixel position in the initial result is directly determined as the final pixel value at the pixel position.

[0119] In this method, in scenes with insufficient lighting such as night, the adjusted standard image with a specified exposure of EV0, the first detection result, the second detection result, and the initial result are used to guide the initial result to perform special processing in the overexposed area, and a high-dynamic night scene image is generated by direct superposition, thereby avoiding the problem of overexposure of highlights; in addition, the noise of the current image is detected according to the similarity of the reference image through motion detection and other methods, that is, the absolute value of the difference between the pixel value of the pixel position of the current image and the pixel value of the pixel position of the reference image, and the area is corrected according to the reference image plus random noise, and the motion area between the images to be processed with the same exposure is detected and corrected, thereby reducing the appearance of ghost images in the result image; in addition, the noise suppression processing of the highly exposed area in the initial result is based on multiple registered images to be processed and the reference image, and the noise intensity is reduced by superposition and time domain mean filtering and other operations; this method can make the image brightness of multiple images to be processed consistent, which is conducive to improving the image registration effect, avoiding the generation of ghost images in the fused image, and thus improving the overall image effect.

[0120] A specific implementation method, refer to Figure 7 A flowchart of a specific image processing method is shown, in which a sequence of N identical low-exposure images corresponds to the aforementioned multiple images to be processed; 1 EV0 image corresponds to the aforementioned standard image; the reference frame corresponds to the aforementioned reference image; mask1 corresponds to the aforementioned first detection result; mask2 corresponds to the aforementioned second detection result; threshlod corresponds to the aforementioned preset pixel value threshold; output1 corresponds to the aforementioned initial result; and output corresponds to the aforementioned image processing result.

[0121] Specifically, N identical low-exposure image sequences and one EV0 image are continuously photographed by the same camera device; a reference frame is randomly selected from the N low-exposure images, or a frame with the most edge information details among the N low-exposure images is selected as the reference frame; based on the reference frame, N-1 low-exposure images other than the reference frame are registered, so that the pixel position coordinates of the same object in the N-1 low-exposure images are the same; based on the reference frame, the EV0 image is histogram- and image-registered to obtain the registered EV0 image, and then the registered EV0 image is subjected to transition exposure detection to obtain mask1, and the low-exposure image sequence is guided by mask1 and EV0. The stacking and fusion are performed to obtain a pure high dynamic range image; specifically, for each pixel x in the reference frame, the absolute value of the difference between the pixel value yi of the pixel position in the N-1 low-exposure images after registration and x is determined. If the absolute value is greater than the threshold threshlod, yi is corrected to avoid ghosting during stacking and fusion; the registered and corrected low-exposure image sequence is directly stacked to obtain image output1, and overexposure detection is performed on output1 to obtain mask2; according to mask1, mask2, the registered EV0 image, output1 is corrected to obtain the final output image output.

[0122] The image processing method provided by the embodiment of the present invention has the same technical features as the image processing method provided by the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0123] Embodiment 6

[0124] Corresponding to the above method embodiment, see Figure 8 A structural schematic diagram of an image processing device is shown, the device comprising:

[0125] An acquisition module 81 is used to acquire a plurality of images to be processed corresponding to a target scene; wherein the exposure of the plurality of images to be processed is lower than a preset exposure threshold, and the exposure of the plurality of images to be processed is the same;

[0126] A registration module 82, used for performing image registration processing on a plurality of images to be processed;

[0127] The fusion module 83 is used to perform image fusion processing on the multiple images to be processed after image registration to obtain image processing results.

[0128] The present invention provides an image processing device, which obtains a plurality of images to be processed whose exposure corresponding to a target scene is lower than a preset exposure threshold and whose exposure is the same; performs image registration processing on the plurality of images to be processed; and performs image fusion processing on the plurality of images to be processed after image registration to obtain an image processing result. In this method, in a scene with insufficient lighting such as at night, a plurality of images to be processed whose exposure is lower than a preset exposure threshold and whose exposure is the same are captured, and the plurality of images to be processed are processed by image registration and image fusion. This method can keep the image brightness of the plurality of images to be processed consistent, which is conducive to improving the image registration effect, avoiding ghosting of the fused image, and thus improving the overall image effect.

[0129] Furthermore, the registration module is also used to: determine a reference image from the multiple images to be processed; and perform image registration processing on the images other than the reference image among the multiple images to be processed based on the reference image.

[0130] Furthermore, the above-mentioned device is also used to: obtain a standard image of a specified exposure corresponding to the target scene; the above-mentioned fusion module is also used to: perform image fusion processing on multiple images to be processed after image registration according to the standard image to obtain an image processing result.

[0131] Furthermore, the above-mentioned specified exposure is EV0; the exposure of the plurality of images to be processed is less than the specified exposure.

[0132] Furthermore, the above-mentioned fusion module is also used to: perform image registration processing on the standard image based on the reference image in the multiple images to be processed to obtain the registered standard image; perform overexposure detection on the registered standard image to obtain the first detection result; perform image fusion processing on the multiple images to be processed after image registration according to the registered standard image and the first detection result to obtain the image processing result.

[0133] Furthermore, the above-mentioned fusion module is also used to: adjust the brightness of the standard image according to the brightness parameters of the reference image in the multiple images to be processed to obtain an intermediate image; perform registration processing on the intermediate image and the reference image in the multiple images to be processed to obtain a registration offset; based on the registration offset, perform image registration processing on the standard image to obtain a registered standard image.

[0134] Furthermore, the above-mentioned fusion module is also used to: for each pixel position, superimpose the pixel values ​​at the pixel position in multiple images to be processed after image registration to obtain an initial result; perform overexposure detection on the initial result to obtain a second detection result; and determine the image processing result based on the registered standard image, the first detection result, the second detection result, and the initial result.

[0135] Furthermore, the above-mentioned device is also used to: for each image except the reference image among the multiple images to be processed, as the current image, perform the following operations: for each pixel position, determine whether the absolute value of the difference between the pixel value of the pixel position of the current image and the pixel value of the pixel position of the reference image is greater than a preset pixel value threshold; if it is greater than the pixel value threshold, adjust the pixel value of the pixel position of the current image so that the absolute value is less than or equal to the pixel value threshold.

[0136] Furthermore, the above-mentioned fusion module is also used to: perform the following operations for each pixel position in the initial result to obtain a final pixel value at each pixel position, and determine the final pixel value at each pixel position as the image processing result: if the first detection result and the second detection result both indicate that the pixel position is overexposed, determine the final pixel value at the pixel position according to a preset value and the pixel value at the pixel position in the reference image; if the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, determine the final pixel value at the pixel position according to the pixel values ​​at the pixel position in the aligned standard image and the reference image; if the second detection result indicates that the pixel position is not overexposed, determine the pixel value at the pixel position in the initial result as the final pixel value at the pixel position.

[0137] Furthermore, the above-mentioned fusion module is also used for: if both the first detection result and the second detection result indicate that the pixel position is overexposed, loopingly performing the following operations until a first preset number of operations is reached, and determining the final pixel value at the pixel position according to the operation result obtained for each operation: determining the first number of images to be superimposed according to the preset value and the pixel value at the pixel position in the reference image; determining the first number of images to be superimposed from the multiple images to be processed after image registration; and superimposing the pixel values ​​at the pixel position in the determined images to be processed to obtain the operation result.

[0138] Furthermore, the above-mentioned fusion module is also used for: if the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, looping the following operations until a second preset number of operations is reached, and determining the final pixel value at the pixel position according to the operation result obtained by each operation: determining the second number of images to be superimposed according to the pixel value at the pixel position in the aligned standard image and the reference image; determining the second number of images to be superimposed from the multiple images to be processed after the image alignment; and superimposing the pixel values ​​at the pixel position in the determined images to be processed to obtain the operation result.

[0139] The image processing device provided by the embodiment of the present invention has the same technical features as the image processing method provided by the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0140] Embodiment seven:

[0141] An embodiment of the present invention provides an electronic system, which includes: an image acquisition device, a processing device and a storage device; the image acquisition device is used to obtain preview video frames or image data; a computer program is stored on the storage device, and the computer program executes the steps of the above-mentioned image processing method when the processed device is running.

[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the electronic system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0143] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processing device, the steps of the above-mentioned image processing method are executed.

[0144] The computer program products of the image processing methods, devices, and electronic systems provided in the embodiments of the present invention include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments, which will not be repeated here.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0146] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0147] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0148] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0149] Finally, it should be noted that the above embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An image processing method, characterized in that: The method comprises: Acquire multiple images to be processed corresponding to the target scene; wherein the exposure of the multiple images to be processed is lower than a preset exposure threshold, and the exposure of the multiple images to be processed is the same; Performing image registration processing on the multiple images to be processed; Acquire a standard image of a specified exposure corresponding to the target scene; perform image registration processing on the standard image based on a reference image among the multiple images to be processed to obtain the registered standard image; perform overexposure detection on the registered standard image to obtain a first detection result; perform image fusion processing on the multiple images to be processed after image registration based on the registered standard image and the first detection result to obtain an image processing result.

2. The method according to claim 1, characterized in that The step of performing image registration processing on the plurality of images to be processed comprises: Determining a reference image from the plurality of images to be processed; Taking the reference image as a benchmark, image registration processing is performed on the images among the multiple images to be processed except the reference image.

3. The method according to claim 1, characterized in that The specified exposure is EV0; the exposure of the multiple images to be processed is less than the specified exposure.

4. The method according to claim 1, characterized in that: The step of performing image registration processing on the standard image based on the reference image among the multiple images to be processed to obtain the registered standard image includes: According to the brightness parameter of the reference image among the plurality of images to be processed, the brightness of the standard image is adjusted to obtain an intermediate image; The intermediate image and a reference image among the multiple images to be processed are registered to obtain a registration offset; based on the registration offset, the standard image is registered to obtain the registered standard image.

5. The method according to claim 1, characterized in that: The step of performing image fusion processing on the plurality of images to be processed after image registration according to the registered standard image and the first detection result to obtain an image processing result comprises: For each pixel position, superimposing the pixel values ​​at the pixel position in the plurality of images to be processed after image registration to obtain an initial result; Performing an overexposure detection on the initial result to obtain a second detection result; An image processing result is determined according to the registered standard image, the first detection result, the second detection result, and the initial result.

6. The method according to claim 5, characterized in that Before the step of superimposing the pixel values ​​at each pixel position in the plurality of images to be processed after image registration to obtain an initial result, the method further comprises: For each of the multiple images to be processed, except the reference image, as a current image, the following operations are performed: For each pixel position, determining whether an absolute value of a difference between a pixel value at the pixel position of the current image and a pixel value at the pixel position of the reference image is greater than a preset pixel value threshold; If it is greater than the pixel value threshold, adjust the pixel value of the pixel position of the current image so that the absolute value is less than or equal to the pixel value threshold.

7. The method according to claim 5, characterized in that The step of determining an image processing result according to the registered standard image, the first detection result, the second detection result, and the initial result comprises: For each pixel position in the initial result, the following operations are performed to obtain a final pixel value at each pixel position, and the final pixel value at each pixel position is determined as the image processing result: If both the first detection result and the second detection result indicate that the pixel position is overexposed, determining a final pixel value at the pixel position according to a preset value and a pixel value at the pixel position in the reference image; If the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, determining a final pixel value at the pixel position according to the pixel values ​​at the pixel position in the registered standard image and the reference image; If the second detection result indicates that the pixel position is not overexposed, the pixel value at the pixel position in the initial result is determined as the final pixel value at the pixel position.

8. The method according to claim 7, characterized in that If both the first detection result and the second detection result indicate that the pixel position is overexposed, the step of determining a final pixel value at the pixel position according to a preset value and a pixel value at the pixel position in the reference image comprises: If both the first detection result and the second detection result indicate that the pixel position is overexposed, the following operations are performed in a loop until a first preset number of operations is reached, and a final pixel value at the pixel position is determined according to the operation result obtained by each operation: Determining the number of first images to be superimposed according to a preset value and a pixel value at the pixel position in the reference image; Determine the first number of images to be superimposed from the plurality of images to be processed after image registration; The pixel values ​​at the pixel position in the determined image to be processed are superimposed to obtain an operation result.

9. The method according to claim 7, characterized in that: If the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, the step of determining a final pixel value at the pixel position according to the pixel values ​​at the pixel position in the registered standard image and the reference image comprises: If the first detection result indicates that the pixel position is not overexposed, and the second detection result indicates that the pixel position is overexposed, the following operations are performed in a loop until a second preset number of operations is reached, and a final pixel value at the pixel position is determined according to the operation result obtained by each operation: Determining the number of second images to be superimposed according to the pixel value at the pixel position in the registered standard image and the reference image; Determine the second number of images to be processed from the plurality of images to be processed after image registration; The pixel values ​​at the pixel position in the determined image to be processed are superimposed to obtain an operation result.

10. An image processing device, characterized in that: The device comprises: An acquisition module, used for acquiring a plurality of images to be processed corresponding to a target scene; wherein the exposure of the plurality of images to be processed is lower than a preset exposure threshold, and the exposure of the plurality of images to be processed is the same; A registration module, used for performing image registration processing on the multiple images to be processed; A fusion module is used to obtain a standard image of a specified exposure corresponding to the target scene; based on a reference image among the multiple images to be processed, perform image registration processing on the standard image to obtain the registered standard image; perform overexposure detection on the registered standard image to obtain a first detection result; and based on the registered standard image and the first detection result, perform image fusion processing on the multiple images to be processed after image registration to obtain an image processing result.

11. An electronic system, characterized in that: The electronic system includes: a processing device and a storage device; The storage device stores a computer program, which, when executed by the processing device, executes the image processing method according to any one of claims 1 to 9.

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

Images