Motion trajectory image generation method and apparatus, storage medium, and electronic device

Abstract

The present application relates to the technical field of image processing, and discloses a motion trajectory image generation method and apparatus, a storage medium, and an electronic device. The method comprises: determining area types on the basis of motion parameters, foreground and background information, and alignment position information; and performing noise reduction on area images on the basis of noise reduction modes corresponding to the area types, so as to obtain a plurality of background noise-reduced images and foreground noise-reduced images which are used for composing a subject motion trajectory image. The present application improves the image quality and trajectory integrity of motion trajectory images.

Description

Motion trajectory image generation method, device, storage medium and electronic device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on November 21, 2023, with application number 2023115584565 and application name “Motion trajectory image generation method, device, storage medium and electronic device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of image processing technology, and in particular to a motion trajectory image generation method, device, storage medium and electronic device. Background Art

[0003] A motion trajectory image is a trajectory image that reflects the motion trajectory of a subject by synthesizing multiple images of the subject into a single image. However, existing technologies for generating motion trajectory images for fast-moving subjects have significant limitations, as follows:

[0004] (1) The rapid movement of the subject will cause motion blur, resulting in obvious subject motion distortion and blurred subject trajectory in the synthesized trajectory photos, which affects the quality of the trajectory photos;

[0005] (2) The captured images are usually limited to a small field of view for large-scale moving subjects due to the limited synthesis method, making it difficult to capture the complete motion process, and the motion trajectory integrity in the generated motion trajectory image is poor. Technical issues

[0006] In the current motion trajectory image generation method, there are problems with the image quality and trajectory integrity of the motion trajectory images generated in most motion scenes, resulting in a poor user experience. Technical Solutions

[0007] The embodiments of the present application provide a motion trajectory image generation solution, which can effectively improve the image quality and trajectory integrity of motion trajectory images generated in most sports scenes, thereby improving user experience.

[0008] The embodiments of this application provide the following technical solutions:

[0009] According to one embodiment of the present application, a motion trajectory image generation method includes: obtaining multiple candidate synthetic images; aligning the multiple candidate synthetic images to a unified coordinate system based on the non-subject background in each of the candidate synthetic images, and obtaining the alignment position information of the subject foreground and non-subject background of each of the candidate synthetic images in the unified coordinate system; determining the region types of different image regions in the unified coordinate system according to the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images; denoising the region images aligned to each of the image regions according to the noise reduction method corresponding to the region type of each of the image regions, and obtaining multiple background noise-reduced images and multiple foreground noise-reduced images, wherein the multiple background noise-reduced images and the multiple foreground noise-reduced images are used to synthesize the subject motion trajectory image.

[0010] In some embodiments of the present application, the region types of different image regions in the unified coordinate system are determined based on the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images, including: obtaining the dynamic and static types, foreground and background types and overlapping and non-overlapping types corresponding to the regional images aligned to each of the image regions based on the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images; obtaining the region type of each image region based on a combination of the dynamic and static types, foreground and background types and overlapping and non-overlapping types corresponding to the regional images in each of the image regions.

[0011] In some embodiments of the present application, the regional images aligned to each of the image areas are denoised according to the noise reduction method corresponding to the region type of each of the image areas to obtain multiple background noise-reduced images and multiple foreground noise-reduced images, including: denoising the regional images in the overlapping image areas by a multi-frame fusion noise reduction method to obtain a fused noise-reduced regional image; denoising the regional images in the non-overlapping image areas by a single-frame fusion noise reduction method to obtain a single-frame noise-reduced regional image; and obtaining the multiple background noise-reduced images and multiple foreground noise-reduced images based on the fused noise-reduced regional image and the single-frame noise-reduced regional image.

[0012] In some embodiments of the present application, obtaining a plurality of candidate composite images includes: obtaining a plurality of images to be processed; obtaining at least one of the focus state, subject position and exposure state corresponding to each of the images to be processed to obtain filtering parameters; and filtering out the images to be processed that meet predetermined conditions from the plurality of images to be processed according to the filtering parameters corresponding to each of the images to be processed to obtain the plurality of candidate composite images, wherein the predetermined conditions include at least one of not being in the focusing process, not being in the exposure convergence process and meeting the subject clarity requirements.

[0013] In some embodiments of the present application, the multiple images to be processed are collected according to predetermined exposure parameters; the method also includes: obtaining motion parameters and allowable displacement limits corresponding to each of the images to be processed; determining an allowable exposure time limit based on the motion parameters and allowable displacement limits; obtaining a predetermined preferred exposure time that is less than the allowable exposure time limit based on the scene brightness; and updating the predetermined exposure parameters based on the predetermined preferred exposure time.

[0014] In some embodiments of the present application, the multiple images to be processed are collected according to predetermined focus parameters; the method further includes: calculating a focus area according to a subject position corresponding to each of the images to be processed; and updating the predetermined focus parameters according to the focus area.

[0015] In some embodiments of the present application, after the regional images to be aligned to each of the image areas are denoised according to the denoising method corresponding to the regional type of each of the image areas to obtain multiple background denoised images and multiple foreground denoised images, the method further includes: splicing the multiple background denoised images into an overall background image in the unified coordinate system according to the alignment position information; and fusing the multiple foreground denoised images with the overall background image to obtain a fused trajectory image; and obtaining a subject motion trajectory image based on the fused trajectory image.

[0016] According to one embodiment of the present application, a motion trajectory image generation device includes: an image acquisition unit for acquiring multiple candidate synthetic images; an image alignment unit for aligning the multiple candidate synthetic images to a unified coordinate system based on the non-subject background in each of the candidate synthetic images, and obtaining the alignment position information of the subject foreground and non-subject background of each of the candidate synthetic images in the unified coordinate system; a type classification unit for determining the region types of different image regions in the unified coordinate system according to the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images; an image denoising unit for denoising the region images aligned to each of the image regions according to the denoising method corresponding to the region type of each of the image regions, and obtaining multiple background denoised images and multiple foreground denoised images, wherein the multiple background denoised images and the multiple foreground denoised images are used to synthesize the subject motion trajectory image.

[0017] In some embodiments of the present application, the type division unit is used to: obtain the dynamic and static type, foreground and background type, and overlapping and non-overlapping type corresponding to the regional image aligned to each of the image areas based on the motion parameters, foreground and background information, and the alignment position information corresponding to each of the candidate synthetic images; and obtain the regional type of each image area based on the combination of the dynamic and static type, foreground and background type, and overlapping and non-overlapping type corresponding to the regional image in each of the image areas.

[0018] In some embodiments of the present application, the image denoising unit is used to: perform denoising on the regional images in the overlapping image areas by a multi-frame fusion denoising method to obtain a fused denoised regional image; perform denoising on the regional images in the non-overlapping image areas by a single-frame fusion denoising method to obtain a single-frame denoised regional image; and obtain the multiple background denoised images and the multiple foreground denoised images based on the fused denoised regional image and the single-frame denoised regional image.

[0019] In some embodiments of the present application, the image acquisition unit is used to: acquire multiple images to be processed; acquire at least one of the focus state, subject position and exposure state corresponding to each of the images to be processed to obtain screening parameters; and screen out the images to be processed that meet predetermined conditions from the multiple images to be processed according to the screening parameters corresponding to each of the images to be processed to obtain the multiple candidate composite images, wherein the predetermined conditions include at least one of not being in the focusing process, not being in the exposure convergence process and meeting the subject clarity requirements.

[0020] In some embodiments of the present application, the multiple images to be processed are collected according to predetermined exposure parameters; the device also includes an exposure adjustment unit, which is used to: obtain motion parameters and allowable displacement limits corresponding to each of the images to be processed; determine the allowable exposure time limit based on the motion parameters and allowable displacement limits; obtain a predetermined preferred exposure time that is less than the allowable exposure time limit based on the scene brightness; and update the predetermined exposure parameters based on the predetermined preferred exposure time.

[0021] In some embodiments of the present application, the multiple images to be processed are collected according to predetermined focus parameters; the device also includes a focus adjustment unit, which is used to: calculate the focus area according to the subject position corresponding to each of the images to be processed; and update the predetermined focus parameters according to the focus area.

[0022] In some embodiments of the present application, after the regional images to be aligned to each of the image regions are denoised according to the denoising method corresponding to the region type of each of the image regions to obtain a plurality of background denoised images and a plurality of foreground denoised images, the device further includes a fusion unit for: splicing the plurality of background denoised images into an overall background image in the unified coordinate system according to the alignment position information; and fusing the plurality of foreground denoised images with the overall background image to obtain a fused trajectory image; and obtaining a subject motion trajectory image based on the fused trajectory image.

[0023] According to another embodiment of the present application, a storage medium stores a computer program thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the method described in the embodiment of the present application.

[0024] According to another embodiment of the present application, an electronic device may include: a memory storing a computer program; and a processor reading the computer program stored in the memory to execute the method described in the embodiment of the present application.

[0025] According to another embodiment of the present application, a computer program product or computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various optional implementations described in the embodiments of the present application. Beneficial effects

[0026] In an embodiment of the present application, a plurality of candidate composite images are obtained; based on the non-subject background in each of the candidate composite images, the plurality of candidate composite images are aligned to a unified coordinate system to obtain alignment position information of the subject foreground and non-subject background of each of the candidate composite images in the unified coordinate system; based on the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate composite images, the region types of different image regions in the unified coordinate system are determined; the region images aligned to each of the image regions are denoised according to the denoising method corresponding to the region type of each of the image regions to obtain a plurality of background denoised images and a plurality of foreground denoised images, which are used to synthesize a subject motion trajectory image.

[0027] In this way, after separating multiple candidate composite images by background, the multiple candidate composite images are independently aligned to a unified coordinate system based on the non-subject background, so that the acquisition of the original image can be unrestricted by the field of view, and the image acquisition process can follow the movement of the subject to increase the field of view range, thereby improving the trajectory integrity of the motion trajectory image in a large-scale motion scene; further, by dividing the image area in the unified coordinate system according to the region type, and denoising the regional images aligned to each image area according to the noise reduction method corresponding to the region type of each image area, it is possible to effectively avoid motion blur caused by exposure parameters during rapid motion of the subject, further ensuring the image quality of the synthesized motion trajectory image. Furthermore, the present application as a whole can effectively improve the image quality and trajectory integrity of the motion trajectory images generated in most motion scenes, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0029] FIG1 shows a flow chart of a method for generating a motion trajectory image according to an embodiment of the present application.

[0030] FIG2 shows a block diagram of a device for generating a motion trajectory image by applying an embodiment of the present application in a scenario.

[0031] FIG3 shows a flow chart of generating a motion trajectory image by applying an embodiment of the present application in a scenario.

[0032] FIG4 shows a block diagram of a motion trajectory image generating device according to an embodiment of the present application.

[0033] FIG5 shows a block diagram of an electronic device according to an embodiment of the present application.

[0034] Implementation Methods of the Application

[0035] The present disclosure will be further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the examples provided herein are merely for explaining the present disclosure and are not intended to limit the present disclosure. In addition, the examples provided below are partial examples for implementing the present disclosure, rather than providing all examples for implementing the present disclosure. In the absence of conflict, the technical solutions described in the examples of the present disclosure may be implemented in any combination.

[0036] It should be noted that, in the embodiments of the present disclosure, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a method or apparatus comprising a series of elements includes not only the elements explicitly stated, but also other elements not explicitly listed, or also includes elements inherent to the implementation of the method or apparatus. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other related elements (such as steps in the method or units in the apparatus, for example, a unit may be part of a circuit, part of a processor, part of a program or software, etc.) in the method or apparatus comprising the element.

[0037] For example, the motion trajectory image generation method provided by the embodiment of the present disclosure includes a series of steps, but the motion trajectory image generation method provided by the embodiment of the present disclosure is not limited to the recorded steps. Similarly, the motion trajectory image generation device provided by the embodiment of the present disclosure includes a series of units, but the device provided by the embodiment of the present disclosure is not limited to including the units explicitly recorded, and may also include units that need to be set up to obtain relevant information or perform processing based on the information.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present disclosure pertains. The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the present disclosure.

[0039] Figure 1 schematically illustrates a flow chart of a method for generating a motion trajectory image according to one embodiment of the present application. The method can be executed by any device or server with processing capabilities, such as a television, computer, mobile phone, smartwatch, or household appliance, or by a server such as a cloud server or physical server. In one specific embodiment of the present application, the device executing the method is a mobile phone.

[0040] As shown in FIG. 1 , the motion trajectory image generating method may include steps S110 to S140 .

[0041] Step S110, obtaining multiple candidate composite images; Step S120, aligning the multiple candidate composite images to a unified coordinate system based on the non-subject background in each of the candidate composite images, and obtaining the alignment position information of the subject foreground and non-subject background of each of the candidate composite images in the unified coordinate system; Step S130, determining the region types of different image regions in the unified coordinate system according to the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate composite images; Step S140, denoising the region images aligned to each of the image regions according to the denoising method corresponding to the region type of each of the image regions, and obtaining multiple background denoised images and multiple foreground denoised images, which are used to synthesize the subject motion trajectory image.

[0042] The multiple candidate composite images are images used to synthesize the subject's motion trajectory image. In some scenarios, the multiple candidate composite images can be images from a sequence of images captured by a device in real time of a moving subject (e.g., a moving person). Thus, based on embodiments of the present application, motion trajectory images can be generated online in real time. In other scenarios, the multiple candidate composite images can be images from a pre-stored sequence of images. Thus, based on embodiments of the present application, motion trajectory images can be generated offline.

[0043] From each candidate composite image, the subject foreground (ie, the area where the subject is located in the candidate composite image) and the non-subject background (ie, the area outside the subject foreground in the candidate composite image) can be separated.

[0044] Based on the non-subject background in each candidate composite image, multiple candidate composite images can be mapped and aligned to a unified coordinate system to obtain the alignment position information of the subject foreground and non-subject background in each candidate composite image in the unified coordinate system. The alignment position information may include the coordinate positions of the pixel points in the subject foreground and non-subject background in the unified coordinate system.

[0045] Multiple candidate synthetic images are mapped and aligned to a unified coordinate system, thereby mapping the image of the moving subject moving over a large range to the unified coordinate system to obtain a large-range motion range image. Multiple candidate synthetic images are independently aligned to the unified coordinate system based on the non-subject background, so that the acquisition of the original image is not restricted by the field of view, and the image acquisition process can follow the movement of the subject to improve the field of view.

[0046] A large-scale motion range image in a unified coordinate system can be divided into different image areas according to a predetermined division method. According to the motion parameters, foreground and background information and alignment position information corresponding to each candidate synthetic image, the dynamic and static types, foreground and background types and overlapping and non-overlapping types of the partial area images aligned to each image area can be obtained, thereby determining the area types of different image areas in the unified coordinate system.

[0047] Among them, the motion parameters can specifically be the motion state of each pixel in the candidate synthetic image, which can be obtained through motion detection; the foreground-background information can specifically be the information describing whether each pixel in the candidate synthetic image belongs to the foreground or background; the alignment position information can specifically be the coordinate position of each pixel in the candidate synthetic image in a unified coordinate system.

[0048] The regional images aligned to each image area are denoised according to the preset denoising method corresponding to the region type of each image area to obtain the denoised regional images in each image area. The denoised regional images of the subject foreground and non-subject background in each candidate synthetic image can be re-stitched to obtain the denoised subject foreground (i.e., foreground denoised image) and the denoised non-subject background (i.e., background denoised image), thereby obtaining multiple background denoised images and multiple foreground denoised images.

[0049] Multiple foreground noise reduction images are clear moving images of the moving subject after noise reduction. The subject motion trajectory image of the moving subject can be synthesized based on multiple background noise reduction images and multiple foreground noise reduction images. The subject motion trajectory image can clearly present the subject motion trajectory of a moving subject in a large range.

[0050] In this way, based on steps S110 to S140, after separating multiple candidate composite images by background, the multiple candidate composite images are independently aligned to a unified coordinate system based on the non-subject background, so that the acquisition of the original image can be unrestricted by the field of view, and the image acquisition process can follow the movement of the subject to increase the field of view range, thereby improving the trajectory integrity of the motion trajectory image in a large-scale motion scene; further, by dividing the image area under the unified coordinate system according to the region type, and denoising the regional images aligned to each image area according to the noise reduction method corresponding to the region type of each image area, it is possible to effectively avoid motion blur caused by exposure parameters during rapid motion of the subject, further ensuring the image quality of the synthesized motion trajectory image. Furthermore, the present application as a whole can effectively improve the image quality and trajectory integrity of the motion trajectory images generated in most motion scenes, thereby improving the user experience.

[0051] The following describes further optional specific embodiments of each step performed when generating the motion trajectory image in the embodiment of FIG. 1 .

[0052] In one embodiment, obtaining a plurality of candidate composite images includes: obtaining a plurality of images to be processed; obtaining at least one of the focus state, subject position and exposure state corresponding to each of the images to be processed to obtain filtering parameters; and filtering out the images to be processed that meet predetermined conditions from the plurality of images to be processed according to the filtering parameters corresponding to each of the images to be processed to obtain the plurality of candidate composite images, wherein the predetermined conditions include at least one of not being in the focusing process, not being in the exposure convergence process and meeting the subject clarity requirements.

[0053] The multiple images to be processed can be a sequence of images taken in real time of a moving subject (such as a moving person). In this case, each image to be processed can be automatically focused to obtain the focus status (used to reflect whether the image to be processed is an image in the focusing process) and the subject position (i.e., the position of the moving subject) corresponding to each image to be processed; at the same time, the exposure status of each image to be processed can be detected (used to reflect whether the image to be processed is an image in the exposure convergence process).

[0054] The multiple images to be processed may also be a pre-stored image sequence. When storing the multiple images to be processed, the corresponding motion parameters, exposure status, focus status, subject position and other information of the images to be processed may be packaged and stored frame by frame.

[0055] At least one of the focus state, subject position and exposure state corresponding to each image to be processed is obtained to obtain the screening parameters corresponding to each image to be processed; according to the screening parameters corresponding to each image to be processed, images to be processed that meet predetermined conditions can be screened out from multiple images to be processed to obtain multiple candidate composite images, wherein the predetermined conditions include at least one of not being in the focusing process, not being in the exposure convergence process and meeting the subject clarity requirements.

[0056] The focus state can be used to determine whether the image being processed is in focus, thereby filtering out images that are not in focus. The exposure state can be used to determine whether the image being processed is in the exposure convergence process, thereby filtering out images that are not in the exposure convergence process. The subject clarity in the image being processed can be analyzed based on whether the subject is located at the center or edge, as well as the subject's position ratio, thereby filtering out images that meet the subject clarity requirements.

[0057] Furthermore, the multiple candidate composite images are images to be processed that are screened out from the multiple images to be processed and meet at least one of the requirements of not being in the focusing process, not being in the exposure convergence process, and meeting the subject clarity requirements. The screened candidate composite images meet the predetermined conditions, that is, the image quality of the candidate composite images is high. Synthesizing the subject motion trajectory image based on the screened candidate composite images can further improve the image quality of the motion trajectory image.

[0058] It is understandable that in other embodiments, multiple images to be processed may be acquired and directly used as multiple candidate composite images without screening.

[0059] Furthermore, in one embodiment, the multiple images to be processed are collected according to predetermined exposure parameters; the method also includes: obtaining motion parameters and allowable displacement limits corresponding to each of the images to be processed; determining an allowable exposure time limit based on the motion parameters and allowable displacement limits; obtaining a predetermined preferred exposure time that is less than the allowable exposure time limit based on the scene brightness; and updating the predetermined exposure parameters based on the predetermined preferred exposure time.

[0060] Multiple images to be processed are actually collected according to predetermined exposure parameters. For example, a sequence of multiple images to be processed is obtained by real-time shooting using a device. Appropriate exposure parameters are selected based on motion parameters and allowable displacement limits to update the predetermined exposure parameters. This can reduce motion distortion and blur in subsequently collected images to be processed, ensure the stability of the image exposure effect, and further improve the image quality of the motion trajectory image as a whole.

[0061] The motion parameters and allowable displacement limits corresponding to each image to be processed can be obtained by, for example, using a motion detection algorithm to estimate the motion speed of each point in the static and dynamic regions of the image frame by frame based on the changes in optical flow information between adjacent image frames, and then matching the motion speed with the image frames to obtain the motion speed (i.e., motion parameter) corresponding to the pixel points in each image to be processed. Furthermore, the allowable displacement limit can be a pre-set maximum allowable displacement of the image without motion distortion or blur.

[0062] Based on the motion parameters and the allowable displacement limit, a maximum allowable exposure time can be calculated as the allowable exposure time limit. Based on the scene brightness (i.e., the ambient brightness of the environment in which the image to be processed is captured), a plurality of predetermined exposure times less than the allowable exposure time limit can be obtained, and the one that matches the scene brightness can be used as the predetermined preferred exposure time.

[0063] Based on the predetermined preferred exposure time, the predetermined exposure parameters are updated for shooting the image to be processed, which ensures that when shooting the image to be processed when synthesizing the motion trajectory image, the image to be processed is free of motion distortion and blur and the exposure effect is consistent under different motion states, further ensuring the clarity and consistency of the motion trajectory image effect after splicing and fusion.

[0064] Furthermore, in some embodiments, while updating the predetermined exposure parameters based on the predetermined preferred exposure duration, the brightness compensation gain of the image to be processed can be adjusted simultaneously to further ensure the clarity and consistency of the resulting stitched and fused motion trajectory image. The brightness compensation gain can be a predetermined gain corresponding to the motion speed.

[0065] Furthermore, in one embodiment, the plurality of images to be processed are collected according to predetermined focus parameters; the method further includes: calculating a focus area according to a subject position corresponding to each of the images to be processed; and updating the predetermined focus parameters according to the focus area.

[0066] The focus area in the image can be calculated based on the subject position corresponding to each image to be processed. The predetermined focus parameters are updated based on the focus area, which can further ensure that the focus is locked on the moving subject during shooting, and the moving subject does not appear out of focus or blur, further improving the image quality of the motion trajectory image, wherein the moving subject can be actively specified by the user or automatically selected based on the target recognition algorithm.

[0067] Furthermore, in one embodiment, the region types of different image regions in the unified coordinate system are determined based on the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images, including: obtaining the dynamic and static types, foreground and background types and overlapping and non-overlapping types corresponding to the regional images aligned to each of the image regions based on the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images; obtaining the region type of each image region based on a combination of the dynamic and static types, foreground and background types and overlapping and non-overlapping types corresponding to the regional images in each of the image regions.

[0068] A large-scale motion image in a unified coordinate system can be divided into different image regions according to a predetermined division method. Based on the motion parameters, foreground and background information, and alignment position information corresponding to each candidate composite image, the motion and static types, foreground and background types, and overlapping and non-overlapping types of the partial images aligned to each image region can be obtained. The motion and static types can include motion areas and static areas, the foreground and background types can include foreground and background, and the overlapping and non-overlapping types can include overlapping areas and non-overlapping areas.

[0069] Thus, according to the combination of the dynamic and static types, foreground and background types, and overlapping and non-overlapping types corresponding to the regional images in each image area, the regional type of each image area can be obtained. The regional type may include foreground dynamic area, foreground static overlapping area, foreground static non-overlapping area, background dynamic overlapping area, background dynamic non-overlapping area, background static overlapping area, and background static non-overlapping area. Among them, the foreground dynamic area, i.e., the combination of foreground and motion area, corresponds to the regional type, the foreground static overlapping area, i.e., the combination of foreground, static area and overlapping area, corresponds to the regional type, and so on.

[0070] Furthermore, in one embodiment, performing noise reduction on the regional images aligned to the respective image regions according to the noise reduction method corresponding to the region type of each image region to obtain multiple background noise-reduced images and multiple foreground noise-reduced images may include:

[0071] The regional images in the overlapping image areas are subjected to denoising by a multi-frame fusion noise reduction method to obtain a fused noise-reduced regional image; the regional images in the non-overlapping image areas are subjected to denoising by a single-frame fusion noise reduction method to obtain a single-frame noise-reduced regional image; and the multiple background noise-reduced images and the multiple foreground noise-reduced images are obtained based on the fused noise-reduced regional image and the single-frame noise-reduced regional image.

[0072] The overlapping type image area is an image area whose corresponding combination of area types includes an overlapping area, and the non-overlapping type image area is an image area whose corresponding combination of area types includes a non-overlapping area.

[0073] Performing noise reduction on the regional images in overlapping image regions using a multi-frame fusion noise reduction method to obtain a fused noise-reduced regional image; performing noise reduction on the regional images in non-overlapping image regions using a single-frame fusion noise reduction method to obtain a single-frame noise-reduced regional image. This can effectively prevent motion blur caused by exposure parameters and other factors during rapid subject movement, further ensuring the image quality of the synthesized motion trajectory image. The multi-frame fusion noise reduction method and the single-frame fusion noise reduction method can utilize existing frame fusion noise reduction methods and single-frame fusion noise reduction methods.

[0074] According to the fused denoised area image and the single-frame denoised area image, the denoised area images of the subject foreground and the non-subject background in each candidate synthetic image can be re-stitched to obtain the denoised subject foreground (i.e., the foreground denoised image) and the denoised non-subject background (i.e., the background denoised image), thereby obtaining multiple background denoised images and multiple foreground denoised images.

[0075] Furthermore, in one embodiment, after performing noise reduction on the regional images aligned to the respective image regions according to the noise reduction method corresponding to the region type of each image region to obtain a plurality of background noise-reduced images and a plurality of foreground noise-reduced images, the method further includes:

[0076] According to the alignment position information, the multiple background noise reduction images are spliced ​​into an overall background image in the unified coordinate system; and the multiple foreground noise reduction images are fused with the overall background image to obtain a fused trajectory image; and a subject motion trajectory image is obtained based on the fused trajectory image.

[0077] Based on the alignment position information, multiple background denoised images can be cropped and stitched together in a unified coordinate system to create a complete background image covering the entire motion range of the moving subject. Subsequently, multiple foreground denoised images are fused with the complete background image, so that the moving subject in the multiple foreground denoised images is combined with the complete background image, resulting in a complete fused trajectory image. Based on the fused trajectory image, a subject motion trajectory image is obtained, representing the subject's trajectory.

[0078] The subject motion trajectory image is obtained based on the fused trajectory image. Specifically, the fused trajectory image can be used as the obtained subject motion trajectory image; or the fused trajectory image is smoothed using an image smoothing algorithm to make a natural transition between the foreground and the background to obtain a smoothed image, and then the smoothed image is cropped to generate a motion trajectory photo of a selected area as the final subject motion trajectory image.

[0079] To facilitate better implementation of the motion trajectory image generation method provided in the embodiment of the present application, the aforementioned embodiment is further described below in conjunction with the process of generating a motion trajectory image in a scenario. Referring to Figures 2 and 3, Figure 2 shows a block diagram of a device for generating a motion trajectory image by applying an embodiment of the present application in a scenario, and Figure 3 shows a flow chart of generating a motion trajectory image by applying an embodiment of the present application in a scenario.

[0080] As shown in FIG. 2 , in this scenario, the device for generating a motion trajectory image may include an image acquisition module 210 , an intelligent focus tracking module 220 , a motion detection module 230 , a dynamic exposure module 240 , an image screening module 250 and an image processing module 260 .

[0081] Referring to FIG. 3 , in this scenario, the process of generating the motion trajectory image may include steps S310 to S360 .

[0082] Step S310: Acquire images. Specifically, acquire multiple images to be processed.

[0083] The image acquisition module 210 can acquire images in real time, thereby obtaining a sequence of multiple images to be processed.

[0084] Step S320: Obtain image parameters. Specifically, obtain the focus state, subject position, and exposure state corresponding to each image to be processed.

[0085] Among them, the intelligent focusing module 220 can automatically focus on each image to be processed, and obtain the focus status (used to reflect whether the image to be processed is an image in the focusing process) and subject position (i.e., the position of the moving subject) corresponding to each image to be processed.

[0086] The dynamic exposure module 240 can detect the exposure state of each image to be processed (used to reflect whether the image to be processed is an image in the exposure convergence process).

[0087] Step S330: Image screening. Specifically, based on the screening parameters corresponding to each of the images to be processed, images to be processed that meet predetermined conditions are screened from the plurality of images to be processed to obtain the plurality of candidate composite images, wherein the predetermined conditions include not being in the focusing process, not being in the exposure convergence process, and meeting the subject clarity requirements.

[0088] The image screening module 250 can perform image screening to obtain multiple candidate composite images.

[0089] Step S340: Exposure adjustment. Specifically, the motion parameters and allowable displacement limits corresponding to each image to be processed are obtained; the allowable exposure duration limit is determined based on the motion parameters and allowable displacement limits; a predetermined preferred exposure duration that is less than the allowable exposure duration limit is obtained based on the scene brightness; and the predetermined exposure parameters are updated based on the predetermined preferred exposure duration.

[0090] The dynamic exposure module 240 may update the predetermined exposure parameters in the image acquisition module 210 based on the predetermined preferred exposure duration.

[0091] Step S350: focus adjustment. Specifically, a focus area is calculated according to the subject position corresponding to each image to be processed; and a predetermined focus parameter is updated according to the focus area.

[0092] The smart focus tracking module 220 may update the predetermined focus parameters in the image acquisition module 210 according to the focus area.

[0093] Step S360: Image processing. Step S360 may specifically include steps S361 to S364. The image processing module 260 may include: an image alignment unit for executing step S361; a type classification unit for executing step S362; an image noise reduction unit for executing step S363; and an image fusion unit for executing step S364.

[0094] Step S361: Alignment processing. Specifically, based on the non-subject background in each candidate composite image, multiple candidate composite images are aligned to a unified coordinate system to obtain the alignment position information of the subject foreground and non-subject background of each candidate composite image in the unified coordinate system.

[0095] Step S362: Region type classification: Specifically, the region types of different image regions in the unified coordinate system are determined based on the motion parameters, foreground and background information, and alignment position information corresponding to each candidate synthesized image.

[0096] Specifically, the motion parameters, foreground and background information, and alignment position information corresponding to each candidate composite image may be used to obtain the motion and still types, foreground and background types, and overlapping and non-overlapping types corresponding to the regional images aligned to each image region; and the region types of each image region may be obtained based on the combination of the motion and still types, foreground and background types, and overlapping and non-overlapping types corresponding to the regional images in each image region. The region types may include foreground motion region, foreground and still overlapping region, foreground and still non-overlapping region, background motion and still overlapping region, background motion and still non-overlapping region, background motion and still overlapping region, and background still non-overlapping region.

[0097] Step S363: Denoise by type. Specifically, the regional images aligned to each image region are denoised according to the corresponding noise reduction method for the region type of each image region, resulting in multiple background denoised images and multiple foreground denoised images. These multiple background denoised images and multiple foreground denoised images are used to synthesize the subject motion trajectory image.

[0098] Specifically, the regional images in the overlapping image areas can be denoised by a multi-frame fusion noise reduction method to obtain a fused noise-reduced regional image; the regional images in the non-overlapping image areas can be denoised by a single-frame fusion noise reduction method to obtain a single-frame noise-reduced regional image; based on the fused noise-reduced regional image and the single-frame noise-reduced regional image, multiple background noise-reduced images and multiple foreground noise-reduced images are obtained.

[0099] Step S364: Image fusion. Specifically, based on the alignment position information, multiple background noise reduction images are stitched together in a unified coordinate system to form an overall background image. Furthermore, multiple foreground noise reduction images are fused with the overall background image to obtain a fused trajectory image. Based on the fused trajectory image, a subject motion trajectory image is obtained.

[0100] In this way, in this scenario, by applying the embodiments of the present application, at least beneficial effects are achieved: after multiple candidate composite images are separated by background, the multiple candidate composite images are independently aligned to a unified coordinate system based on the non-subject background, so that the acquisition of the original image can be unrestricted by the field of view, and the image acquisition process can follow the movement of the subject to increase the field of view range, thereby improving the trajectory integrity of the motion trajectory image in large-scale motion scenes; further, by dividing the image area in the unified coordinate system according to the region type, and denoising the regional images aligned to each image area according to the noise reduction method corresponding to the region type of each image area, it is possible to effectively avoid motion blur caused by exposure parameters during rapid motion of the subject, further ensuring the image quality of the synthesized motion trajectory image. Overall, it can effectively improve the image quality and trajectory integrity of the motion trajectory images generated in most motion scenes, thereby enhancing the user experience.

[0101] To facilitate the implementation of the motion trajectory image generation method provided in the embodiments of this application, the embodiments of this application also provide a motion trajectory image generation device based on the aforementioned motion trajectory image generation method. The meanings of the terms herein are the same as those in the aforementioned motion trajectory image generation method. For specific implementation details, please refer to the description in the method embodiments. Figure 4 shows a block diagram of the motion trajectory image generation device according to one embodiment of the present application.

[0102] As shown in Figure 4, the motion trajectory image generation device 400 may include: an image acquisition unit 410 can be used to acquire multiple candidate synthetic images; an image alignment unit 420 can be used to align the multiple candidate synthetic images to a unified coordinate system based on the non-subject background in each of the candidate synthetic images, and obtain the alignment position information of the subject foreground and non-subject background of each of the candidate synthetic images in the unified coordinate system; a type classification unit 430 can be used to determine the region types of different image regions in the unified coordinate system according to the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images; an image denoising unit 440 can be used to denoise the region images aligned to each of the image regions according to the denoising method corresponding to the region type of each of the image regions, to obtain multiple background denoised images and multiple foreground denoised images, and the multiple background denoised images and multiple foreground denoised images are used to synthesize the subject motion trajectory image.

[0103] In some embodiments of the present application, the type division unit is used to: obtain the dynamic and static type, foreground and background type, and overlapping and non-overlapping type corresponding to the regional image aligned to each of the image areas based on the motion parameters, foreground and background information, and the alignment position information corresponding to each of the candidate synthetic images; and obtain the regional type of each image area based on the combination of the dynamic and static type, foreground and background type, and overlapping and non-overlapping type corresponding to the regional image in each of the image areas.

[0104] In some embodiments of the present application, the image denoising unit is used to: perform denoising on the regional images in the overlapping image areas by a multi-frame fusion denoising method to obtain a fused denoised regional image; perform denoising on the regional images in the non-overlapping image areas by a single-frame fusion denoising method to obtain a single-frame denoised regional image; and obtain the multiple background denoised images and the multiple foreground denoised images based on the fused denoised regional image and the single-frame denoised regional image.

[0105] In some embodiments of the present application, the image acquisition unit is used to: acquire multiple images to be processed; acquire at least one of the focus state, subject position and exposure state corresponding to each of the images to be processed to obtain screening parameters; and screen out the images to be processed that meet predetermined conditions from the multiple images to be processed according to the screening parameters corresponding to each of the images to be processed to obtain the multiple candidate composite images, wherein the predetermined conditions include at least one of not being in the focusing process, not being in the exposure convergence process and meeting the subject clarity requirements.

[0106] In some embodiments of the present application, the multiple images to be processed are collected according to predetermined exposure parameters; the device also includes an exposure adjustment unit, which is used to: obtain motion parameters and allowable displacement limits corresponding to each of the images to be processed; determine the allowable exposure time limit based on the motion parameters and allowable displacement limits; obtain a predetermined preferred exposure time that is less than the allowable exposure time limit based on the scene brightness; and update the predetermined exposure parameters based on the predetermined preferred exposure time.

[0107] In some embodiments of the present application, the multiple images to be processed are collected according to predetermined focus parameters; the device also includes a focus adjustment unit, which is used to: calculate the focus area according to the subject position corresponding to each of the images to be processed; and update the predetermined focus parameters according to the focus area.

[0108] In some embodiments of the present application, after the regional images to be aligned to each of the image regions are denoised according to the denoising method corresponding to the region type of each of the image regions to obtain a plurality of background denoised images and a plurality of foreground denoised images, the device further includes a fusion unit for: splicing the plurality of background denoised images into an overall background image in the unified coordinate system according to the alignment position information; and fusing the plurality of foreground denoised images with the overall background image to obtain a fused trajectory image; and obtaining a subject motion trajectory image based on the fused trajectory image.

[0109] 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 embodiment of the application, the features and functions of two or more modules or units described above can be concretized 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 concretized.

[0110] In addition, an embodiment of the present application further provides an electronic device, as shown in FIG5 . FIG5 shows a block diagram of an electronic device according to an embodiment of the present application. Specifically:

[0111] The electronic device may include components such as a processor 501 with one or more processing cores, a memory 502 with one or more computer-readable storage media, a power supply 503, and an input unit 504. Those skilled in the art will appreciate that the electronic device structure shown in FIG5 does not limit the electronic device and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0112] Processor 501 is the control center of the electronic device. It utilizes various interfaces and circuits to connect the various components of the entire computer device. By running or executing software programs and / or modules stored in memory 502 and accessing data stored in memory 502, it performs various computer device functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, processor 501 may include one or more processing cores; preferably, processor 501 may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interfaces, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 501.

[0113] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0114] The electronic device also includes a power supply 503 for supplying power to various components. Preferably, the power supply 503 can be logically connected to the processor 501 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 503 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0115] The electronic device may further include an input unit 504, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0116] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 501 in the electronic device will load the executable files corresponding to one or more computer program processes into the memory 502 according to the following instructions, and the processor 501 will run the computer program stored in the memory 502, thereby realizing the various functions of the aforementioned embodiments of the present application. For example, the processor 501 may perform the following steps:

[0117] Acquire multiple candidate composite images; based on the non-subject background in each of the candidate composite images, align the multiple candidate composite images to a unified coordinate system to obtain the alignment position information of the subject foreground and non-subject background of each of the candidate composite images in the unified coordinate system; determine the region types of different image regions in the unified coordinate system according to the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate composite images; perform denoising on the region images aligned to each of the image regions according to the denoising method corresponding to the region type of each of the image regions to obtain multiple background denoised images and multiple foreground denoised images, and the multiple background denoised images and multiple foreground denoised images are used to synthesize the subject motion trajectory image.

[0118] In some embodiments of the present application, the region types of different image regions in the unified coordinate system are determined based on the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images, including: obtaining the dynamic and static types, foreground and background types and overlapping and non-overlapping types corresponding to the regional images aligned to each of the image regions based on the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthetic images; obtaining the region type of each image region based on a combination of the dynamic and static types, foreground and background types and overlapping and non-overlapping types corresponding to the regional images in each of the image regions.

[0119] In some embodiments of the present application, the regional images aligned to each of the image areas are denoised according to the noise reduction method corresponding to the region type of each of the image areas to obtain multiple background noise-reduced images and multiple foreground noise-reduced images, including: denoising the regional images in the overlapping image areas by a multi-frame fusion noise reduction method to obtain a fused noise-reduced regional image; denoising the regional images in the non-overlapping image areas by a single-frame fusion noise reduction method to obtain a single-frame noise-reduced regional image; and obtaining the multiple background noise-reduced images and multiple foreground noise-reduced images based on the fused noise-reduced regional image and the single-frame noise-reduced regional image.

[0120] In some embodiments of the present application, obtaining a plurality of candidate composite images includes: obtaining a plurality of images to be processed; obtaining at least one of the focus state, subject position and exposure state corresponding to each of the images to be processed to obtain filtering parameters; and filtering out the images to be processed that meet predetermined conditions from the plurality of images to be processed according to the filtering parameters corresponding to each of the images to be processed to obtain the plurality of candidate composite images, wherein the predetermined conditions include at least one of not being in the focusing process, not being in the exposure convergence process and meeting the subject clarity requirements.

[0121] In some embodiments of the present application, the multiple images to be processed are collected according to predetermined exposure parameters; and the method further includes: obtaining motion parameters and allowable displacement limits corresponding to each of the images to be processed; determining an allowable exposure time limit based on the motion parameters and allowable displacement limits; obtaining a predetermined preferred exposure time that is less than the allowable exposure time limit based on the scene brightness; and updating the predetermined exposure parameters based on the predetermined preferred exposure time.

[0122] In some embodiments of the present application, the multiple images to be processed are collected according to predetermined focus parameters; and further comprising: calculating a focus area according to a subject position corresponding to each of the images to be processed; and updating the predetermined focus parameters according to the focus area.

[0123] In some embodiments of the present application, after the regional images to be aligned to each of the image areas are denoised according to the denoising method corresponding to the regional type of each of the image areas to obtain multiple background denoised images and multiple foreground denoised images, it also includes: according to the alignment position information, splicing the multiple background denoised images into an overall background image in the unified coordinate system; and, fusing the multiple foreground denoised images with the overall background image to obtain a fused trajectory image; and obtaining a subject motion trajectory image based on the fused trajectory image.

[0124] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0125] To this end, an embodiment of the present application further provides a storage medium storing a computer program, which can be loaded by a processor to execute the steps of any method provided in the embodiment of the present application.

[0126] The storage medium may be a computer-readable storage medium, and the storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0127] Since the computer program stored in the storage medium can execute the steps of any method provided in the embodiments of the present application, the beneficial effects that can be achieved by the method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0128] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0129] It should be understood that the present application is not limited to the embodiments that have been described above and shown in the accompanying drawings, but various modifications and changes may be made without departing from the scope thereof.

Claims

1. A method for generating a motion trajectory image, wherein: include: Acquire multiple candidate composite images; Based on the non-subject background in each of the candidate synthetic images, the multiple candidate synthetic images are aligned to a unified coordinate system to obtain alignment position information of the subject foreground and the non-subject background of each of the candidate synthetic images in the unified coordinate system; Determining the region types of different image regions in the unified coordinate system according to the motion parameters, foreground and background information, and the alignment position information corresponding to each of the candidate synthesized images; The regional images aligned to the image regions are denoised according to the denoising method corresponding to the region type of each image region to obtain a plurality of background denoised images and a plurality of foreground denoised images. The plurality of background denoised images and the plurality of foreground denoised images are used to synthesize the subject motion trajectory image.

2. The method according to claim 1, wherein: The determining, according to the motion parameters, foreground and background information and the alignment position information corresponding to each of the candidate synthesized images, the region types of different image regions in the unified coordinate system includes: According to the motion parameters, foreground and background information and the alignment position information corresponding to each candidate synthetic image, the dynamic and static types, foreground and background types and overlapping and non-overlapping types corresponding to the regional images aligned to each of the image regions are obtained; The region type of each image region is obtained according to the combination of the dynamic and static types, the foreground and background types, and the overlapping and non-overlapping types corresponding to the region images in each of the image regions.

3. The method according to claim 1, wherein: The denoising is performed on the regional images aligned to the image regions according to the denoising method corresponding to the region type of each image region to obtain a plurality of background denoised images and a plurality of foreground denoised images, including: Denoising the regional images in the overlapping image regions by using a multi-frame fusion denoising method to obtain a fused denoised regional image; Denoising the regional images in the non-overlapping image regions by using a single-frame fusion denoising method to obtain a single-frame denoised regional image; The multiple background noise reduction images and multiple foreground noise reduction images are obtained according to the fused noise reduction area image and the single-frame noise reduction area image.

4. The method according to claim 1, wherein: The obtaining of a plurality of candidate composite images comprises: Obtain multiple images to be processed; Obtaining at least one of a focus state, a subject position, and an exposure state corresponding to each of the images to be processed to obtain a screening parameter; According to the screening parameters corresponding to each of the images to be processed, the images to be processed that meet the predetermined conditions are screened out from the multiple images to be processed to obtain the multiple candidate composite images, wherein the predetermined conditions include at least one of not being in the focusing process, not being in the exposure convergence process, and meeting the subject clarity requirements.

5. The method according to claim 4, wherein: The plurality of images to be processed are collected according to predetermined exposure parameters; the method further comprises: Obtaining motion parameters and allowable displacement limits corresponding to each of the images to be processed; Determining an allowable exposure time limit according to the motion parameter and the allowable displacement limit; Acquire a predetermined preferred exposure time that is less than the allowable exposure time limit according to the scene brightness; The predetermined exposure parameter is updated based on the predetermined preferred exposure duration.

6. The method according to claim 4, wherein: The plurality of images to be processed are collected according to predetermined focus parameters; The method further comprises: Calculating a focus area according to a subject position corresponding to each of the images to be processed; The predetermined focus parameter is updated according to the focus area.

7. The method according to claim 1, wherein: After the regional images aligned to the image regions are subjected to noise reduction according to noise reduction methods corresponding to the regional types of the image regions to obtain a plurality of background noise reduction images and a plurality of foreground noise reduction images, the method further includes: splicing the plurality of background noise reduction images into an overall background image in the unified coordinate system according to the alignment position information; and Fusion of the plurality of foreground denoised images with the overall background image to obtain a fused trajectory image; A subject motion trajectory image is obtained according to the fused trajectory image.

8. The method according to claim 1, wherein: The acquiring of the plurality of candidate composite images includes: acquiring a plurality of images to be processed, and using the plurality of images to be processed as the plurality of candidate composite images.

9. The method according to claim 5, wherein: The step of obtaining a predetermined preferred exposure time that is less than the allowable exposure time limit according to the scene brightness includes: Among a plurality of predetermined exposure times that are less than an allowable exposure time limit value acquired according to the scene brightness, a predetermined exposure time that matches the scene brightness is used as the predetermined preferred exposure time.

10. The method according to claim 7, wherein: The step of obtaining a subject motion trajectory image according to the fused trajectory image comprises: The fused trajectory image is used as the obtained subject motion trajectory image; or the fused trajectory image is smoothed by an image smoothing algorithm to obtain a smoothed image, and a motion trajectory photo of a selected area is generated by cropping the smoothed image as the subject motion trajectory image.

11. The method according to claim 4, wherein: The plurality of images to be processed are image sequences shot in real time for a moving subject; The step of acquiring at least one of a focus state, a subject position, and an exposure state corresponding to each of the images to be processed to obtain a screening parameter includes: Automatically tracking focus on each of the images to be processed to obtain a focus state and a subject position corresponding to each of the images to be processed; Detecting the exposure process of shooting each image to be processed, and obtaining the exposure state corresponding to each image to be processed; The focus state, subject position and exposure state corresponding to each of the images to be processed are used as screening parameters of each of the images to be processed.

12. The method according to claim 4, wherein: The plurality of images to be processed are a pre-stored image sequence; The step of acquiring at least one of a focus state, a subject position, and an exposure state corresponding to each of the images to be processed to obtain a screening parameter includes: Obtaining the focus state, subject position and exposure state corresponding to each of the images to be processed from the information corresponding to each of the images to be processed that is stored frame by frame in advance; The focus state, subject position and exposure state corresponding to each of the images to be processed are used as screening parameters of each of the images to be processed.

13. The method according to claim 5, wherein: After obtaining a predetermined preferred exposure time that is less than the allowable exposure time limit according to the scene brightness, the method further includes: While updating the predetermined exposure parameters based on the predetermined preferred exposure duration, the brightness compensation gain of the image to be processed can be adjusted synchronously.

14. A motion trajectory image generating device, wherein: include: An image acquisition unit, used for acquiring a plurality of candidate composite images; An image alignment unit, configured to align the plurality of candidate synthetic images to a unified coordinate system based on the non-subject background in each of the candidate synthetic images, and obtain alignment position information of the subject foreground and the non-subject background of each of the candidate synthetic images in the unified coordinate system; The type classification unit is used to classify the candidate synthetic images according to the motion parameters, foreground and background information and the The alignment position information is used to determine the region types of different image regions in the unified coordinate system; The image denoising unit is used to denoise the regional images aligned to each of the image regions according to the denoising method corresponding to the regional type of each of the image regions, so as to obtain multiple background denoised images and multiple foreground denoised images, wherein the multiple background denoised images and multiple foreground denoised images are used to synthesize the subject motion trajectory image.

15. The device according to claim 14, wherein: The type classification unit is used to obtain, according to the motion parameters, foreground and background information and the alignment position information corresponding to each candidate synthetic image, the dynamic and static type, the foreground and background type and the overlapping and non-overlapping type corresponding to the regional image aligned to each of the image regions; The region type of each image region is obtained according to the combination of the dynamic and static types, the foreground and background types, and the overlapping and non-overlapping types corresponding to the region images in each of the image regions.

16. The device according to claim 14, wherein: The image denoising unit is used to: denoise the regional images in the overlapping image regions by a multi-frame fusion denoising method to obtain a fused denoised regional image; denoise the regional images in the non-overlapping image regions by a single-frame fusion denoising method to obtain a single-frame denoised regional image; The multiple background noise reduction images and multiple foreground noise reduction images are obtained according to the fused noise reduction area image and the single-frame noise reduction area image.

17. The device according to claim 14, wherein: The image acquisition unit is used to: acquire a plurality of images to be processed; acquire at least one of a focus state, a subject position and an exposure state corresponding to each of the images to be processed to obtain a screening parameter; and screen out images to be processed that meet predetermined conditions from the plurality of images to be processed according to the screening parameters corresponding to each of the images to be processed to obtain the plurality of candidate composite images, wherein the predetermined conditions include at least one of not being in a focusing process, not being in an exposure convergence process and meeting a subject clarity requirement.

18. The device according to claim 17, wherein: The plurality of images to be processed are collected according to predetermined exposure parameters; the device further comprises an exposure adjustment unit, which is used to: obtain motion parameters and allowable displacement limits corresponding to each of the images to be processed; and determine an allowable exposure time limit according to the motion parameters and allowable displacement limits; Acquire a predetermined preferred exposure duration that is less than the allowable exposure duration limit according to the scene brightness; and update the predetermined exposure parameters based on the predetermined preferred exposure duration.

19. A storage medium, wherein: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the method according to any one of claims 1 to 13.

20. An electronic device, wherein: include: a memory storing a computer program; A processor reads a computer program stored in a memory to execute the method according to any one of claims 1 to 13.

Images