Motion smear detection method, terminal equipment and readable storage medium

Abstract

The invention discloses a motion smear detection method, terminal equipment and a readable storage medium, and relates to the technical field of display pictures. The method comprises the steps that a target motion image collected by shooting equipment in a detection scene is acquired, the detection scene is composed of a plurality of background areas with different contrast ratios, and the target motion image is used for forming a smear area in the background areas; determining a first gray value change curve corresponding to each smear area; extracting a gray value abrupt change range from the first gray value change curve; determining a smear score corresponding to the smear area according to the gray value abrupt change range; and determining the motion smear degree of the shooting equipment according to the smear score of each smear area. The invention aims to solve the problems of inaccurate detection result, poor repeatability, low efficiency and high cost of the existing motion smear detection method.

Description

Technical Field

[0001] The present application relates to the field of display screen technology, and in particular to a motion smear detection method, terminal device, and computer-readable storage medium. Background Art

[0002] When using a camera to capture moving objects, it is generally necessary to use image processing algorithms such as High Dynamic Range Imaging (HDR) and temporal noise reduction to synthesize multiple frames of images. The motion ghosting that appears in the video is generally due to the inaccurate judgment of the moving objects by the above algorithms, resulting in the residual moving object information of the previous frame in the synthesized image, thus forming motion ghosting.

[0003] However, in related technologies, the method for detecting the degree of motion ghosting of shooting equipment mainly relies on human observation and scoring based on subjective feelings. This detection method has problems such as inaccurate detection results, poor repeatability, low efficiency and high labor costs. Summary of the Invention

[0004] The present application provides a motion smear detection method, terminal device and computer-readable storage medium, aiming to solve the problems of inaccurate detection results, poor repeatability, low efficiency and high cost in existing motion smear detection methods.

[0005] In a first aspect, the present application provides a method for detecting motion smear, the method comprising:

[0006] Acquire a target motion image captured by a shooting device in a detection scene, wherein the detection scene is composed of a plurality of background areas with different contrasts, and the target motion image is used to form a smear area in the background area;

[0007] Determining a first grayscale value change curve corresponding to each of the smear areas;

[0008] Extracting a grayscale value mutation range from the first grayscale value change curve;

[0009] Determining a smear score corresponding to the smear area according to the grayscale value mutation range;

[0010] The degree of motion smear of the shooting device is determined according to the smear score of each smear area.

[0011] In a second aspect, the present application provides a terminal device, the terminal device comprising a memory and a processor;

[0012] The memory is used to store computer programs;

[0013] The processor is configured to execute the computer program and implement the motion smear detection method described above when executing the computer program.

[0014] In a third aspect, the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the motion smear detection method as described above.

[0015] The motion smear detection method, terminal device, and computer-readable storage medium provided in the embodiments of the present application obtain a target motion image captured by a camera in a detection scene; determine a first grayscale value change curve corresponding to each smear region; extract a grayscale value mutation range from the first grayscale value change curve; determine a smear score corresponding to the smear region based on the grayscale value mutation range; and determine the degree of motion smear of the camera based on the smear score of each smear region. This standardizes the evaluation criteria for the degree of motion smear, reduces errors caused by human subjectivity, and provides highly repeatable, objective, and unified evaluation results. It also improves the efficiency and accuracy of motion smear detection, saving labor and software costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 This is a motion image with a smearing phenomenon provided by an embodiment of the present application;

[0018] Figure 2 This is a schematic diagram of an application scenario of a camera motion blur test system provided by related technology;

[0019] Figure 3 Schematic diagram of an application environment of a motion smear detection method provided in an embodiment of the present application;

[0020] Figure 4 This is a schematic flow chart of the steps of a motion smear detection method provided in an embodiment of the present application;

[0021] Figure 5 This is a schematic diagram of a detection scenario provided in an embodiment of the present application;

[0022] Figure 6 This is a schematic diagram of a scene of a smear area provided in an embodiment of the present application;

[0023] Figure 7 Schematic diagram of a gray value change curve provided in an embodiment of the present application;

[0024] Figure 8 This is a schematic block diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0027] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0028] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0029] Generally speaking, the phenomenon of ghosting of moving objects in videos is caused by the temporal noise reduction algorithm. The ghosting can be understood as the ghost of the previous frame or frames remaining in the current frame. The subjective feeling is that the moving objects in the video are ghosted and dragged at the movement boundary. Figure 1 As shown, Figure 1 The dotted box in the middle shows that there is a ghosting in the picture of the moving person.

[0030] like Figure 2 As shown in FIG, in the related art, imatest designed a camera motion blur test system, which simulates object motion by rotating a disk and evaluates motion smear by calculating the number of motion blur pixels generated by circular black dots.

[0031] However, the existing imatest motion smear evaluation scheme has the following problems:

[0032] (1) The distinction between foreground and background is simple. If it is directly applied to the evaluation of time domain noise reduction algorithms, it is impossible to fully evaluate the ability of time domain noise reduction algorithms to suppress complex foreground and background smears.

[0033] (2) This solution does not have open source code, so it cannot be flexibly adapted and adjusted in actual use.

[0034] In practical applications, the degree of moving object smearing caused by temporal noise reduction algorithms in videos is currently evaluated primarily through human observation, with subjective evaluation indicators providing a score. However, human visual evaluation has the following problems:

[0035] (1) Highly subjective: Different raters may give different scores, resulting in inconsistent results.

[0036] (2) Poor repeatability: Manual scoring is easily affected by the physical and mental state of the staff at the time. The repeatability of sample scoring is poor, and it is difficult to ensure the objectivity of each scoring.

[0037] (3) Inefficiency: Manual scoring is usually time-consuming and inefficient, especially when a large number of video samples are required for evaluation.

[0038] (4) High cost: Due to the subjectivity of each person, in order to obtain an objective evaluation result, multiple people may be needed to review it, which results in high labor costs.

[0039] The motion ghosting detection method, terminal device and readable storage medium provided in the embodiments of the present application can unify the evaluation criteria for the degree of motion ghosting, reduce errors caused by human subjectivity, and provide highly repeatable, objective and unified evaluation results. At the same time, it can also improve the efficiency and accuracy of motion ghosting detection, save labor costs and imatest software costs.

[0040] The method can be applied to servers, and of course, terminal devices, including fixed terminals such as mobile phones, tablet computers, and personal digital assistants (PDAs). The server can be, for example, a single server or a server cluster. However, for ease of understanding, the following embodiments will describe in detail the motion smear detection method applied to a server.

[0041] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0042] like Figure 3 As shown, the motion smear detection method provided in the embodiment of the present application can be applied to Figure 3In the application environment shown. The application environment includes a shooting device 110 and a server 120, wherein the shooting device 110 can communicate with the server 120 via a network. Specifically, the server 120 obtains a target motion image captured by the shooting device in a detection scene; determines a first grayscale value change curve corresponding to each smear area; extracts a grayscale value mutation range from the first grayscale value change curve; determines a smear score corresponding to the smear area based on the grayscale value mutation range; and determines the degree of motion smear of the shooting device 110 based on the smear score of each smear area. Among them, the server 120 can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The shooting device 110 can be a device with a camera function, such as a camera, a mobile phone, a tablet computer, etc., which is not specifically limited here. The shooting device 110 and the server 120 can be connected directly or indirectly via wired or wireless communication, which is not limited in this application.

[0043] See also Figure 4 , Figure 4 This is a schematic flow chart of a motion smear detection method provided in an embodiment of the present application. This motion smear detection method can unify the criteria for judging the degree of motion smear, reduce errors caused by human subjectivity, and provide highly repeatable, objective, and unified evaluation results. It can also improve the efficiency and accuracy of motion smear detection, saving labor costs and imatest software costs.

[0044] like Figure 4 As shown, the motion smear detection method includes steps S101 to S105.

[0045] S101 : Acquire a target motion image captured by a shooting device in a detection scene, where the detection scene is composed of a plurality of background areas with different contrasts, and the target motion image is used to form a smear area in the background area.

[0046] Among them, the detection scene can be composed of multiple background areas with different contrasts, for example, it can be composed of 3 or 5 background areas with different contrasts. The target motion image is an object motion image captured by the shooting device in the detection scene, and there is a ghosting phenomenon. The object motion image will form a corresponding ghosting area in each background area.

[0047] Exemplarily, the shooting device can be any device with a camera function, such as a camera, a mobile phone, a tablet computer, a computer, etc., and is not specifically limited here.

[0048] like Figure 5 As shown, exemplary, Figure 5 The left side is a single color (black) sports card. Figure 5 On the right are static background areas of varying grayscale. As the card moves horizontally, it passes through background areas of varying contrast, demonstrating the degree of motion artifacts created by the camera's temporal noise reduction algorithm.

[0049] The number of background areas with different contrasts is generally selected to be 3-6, and the grayscale values ​​within the background areas can be evenly divided in the range of 0-255 according to the number of background areas.

[0050] In some embodiments, a motion video is captured by a camera in a detection scene; the motion video is converted into multiple frames of motion images, and a target motion image is determined from the multiple frames of motion images. This allows the most suitable motion image for motion smear assessment to be determined from the motion video, thereby improving the accuracy of motion smear detection.

[0051] The motion video may be a video of the image card moving horizontally in a detection scene.

[0052] For example, the shooting device to be evaluated can capture motion video in the detection scene, and convert the captured motion video stream into multiple frames of motion images, and arbitrarily select a frame of motion image with ghosting from the multiple frames of motion images as the target motion image.

[0053] For example, a preliminary screening of multiple frames of motion images can be performed. For example, the smear region can be identified using an image recognition algorithm or a feature extraction algorithm, thereby selecting a frame of motion image exhibiting the most severe smear as the target motion image. Since this frame of motion image exhibits the most severe smear, it is the most suitable frame for motion smear assessment. Selecting this frame of motion image for subsequent assessment can effectively improve the accuracy of motion smear detection.

[0054] S102: Determine a first grayscale value variation curve corresponding to each smear area.

[0055] like Figure 6 As shown, the smear area is the area where smear is formed in the moving image. Each background area has a corresponding smear area. Figure 6 The three boxes in the figure are the corresponding smear areas in the three different background areas.

[0056] In some embodiments, for any smear region, the grayscale mean value of each column of images in the smear region is determined; and based on the grayscale mean value of each column of images in the smear region, a first grayscale value change curve corresponding to the smear region is generated. In this way, the grayscale value of each column of images in the smear region can be accurately determined, and a corresponding grayscale value change curve can be generated.

[0057] like Figure 7 As shown, the first gray value change curve is a gray value change curve formed by the gray value averages of different column images in the smear area. The horizontal axis of the first gray value change curve is the sequence number of the current column image, and the vertical axis is the average gray value of the current column image. The first gray value change curve is Figure 7 The green curve in .

[0058] For example, the grayscale mean of each column of images can be calculated by obtaining pixel values ​​of each column of images in the smear area and performing weighted averaging on the obtained pixel values ​​of each column of images. A curve can then be fitted based on the grayscale mean of each column of images to generate a first grayscale value change curve corresponding to the smear area. Similarly, the above image processing operation is performed on each smear area to generate a first grayscale value change curve corresponding to each smear area.

[0059] S103 , extracting a grayscale value mutation range from the first grayscale value change curve.

[0060] Among them, the gray value mutation range is used for the area with the largest gray value change, which can be used to estimate the tailing phenomenon.

[0061] In some embodiments, the grayscale mean points in the first grayscale value change curve are sequentially traversed from the lowest point to the highest point of the first grayscale value change curve. If the curve formed by the current grayscale mean point and the adjacent grayscale mean points is in an increasing state, the current grayscale mean point is used as the first grayscale value mutation point. The grayscale mean points in the first grayscale value change curve are sequentially traversed from the highest point to the lowest point of the first grayscale value change curve. If the curve formed by the current grayscale mean point and the adjacent grayscale mean points is in a decreasing state, the current grayscale mean point is used as the second grayscale value mutation point. The grayscale value mutation range is determined based on the first grayscale value mutation point and the second grayscale value mutation point. In this way, the grayscale value mutation range can be accurately determined based on the grayscale value mutation points of the first grayscale value change curve.

[0062] The first grayscale value mutation point is the turning point where the grayscale in the smear area begins to increase, and the second grayscale value mutation point is the turning point where the grayscale in the smear area begins to decrease. Adjacent can mean adjacent only on one side (e.g., n points to the left of the current point or n points to the right of the current point) or adjacent on both sides, without specific limitation here.

[0063] For example, from the lowest point of the first grayscale value change curve (the lowest point on the right) to the highest point (the highest point on the left), if the grayscale mean value of the current grayscale mean point is 5, the grayscale mean value of the adjacent grayscale mean point on the left is 6, and the grayscale mean value of the adjacent grayscale mean point on the right is 4, that is, from the lowest point to the highest point, the grayscale means of these three grayscale mean points are 4, 5, and 6 respectively. Therefore, the curve formed by these three grayscale mean points is in an increasing state, and the current grayscale mean point is taken as the first grayscale value mutation point.

[0064] For example, from the lowest point of the first grayscale value change curve (the lowest point on the right) to the highest point (the highest point on the left), if the grayscale mean value of the current grayscale mean point is 5, and the three adjacent grayscale mean points on the left have grayscale means of 6, 7, and 8, that is, from the lowest point to the highest point, the grayscale means of these four grayscale mean points are 5, 6, 7, and 8 respectively. Therefore, the curve formed by these four grayscale mean points is in an increasing state, and the current grayscale mean point is taken as the first grayscale value mutation point.

[0065] For example, from the highest point (the highest point on the left) to the lowest point (the lowest point on the right) of the first grayscale value change curve, if the grayscale mean value of the current grayscale mean point is 50, the two adjacent grayscale mean points on the left have grayscale means of 52 and 54, and the two adjacent grayscale mean points on the right have grayscale means of 46 and 42, that is, from the highest point to the lowest point, the grayscale means of these five grayscale mean points are 54, 52, 50, 46, and 42 respectively. Therefore, the curve formed by these five grayscale mean points is in a decreasing state, and the current grayscale mean point is taken as the second grayscale value mutation point.

[0066] It should be noted that there may be one or more adjacent grayscale mean points, which is not specifically limited here.

[0067] In some embodiments, a first grayscale value change curve is filtered to obtain a second grayscale value change curve; a first grayscale value mutation point is extracted from the first grayscale value change curve; a second grayscale value mutation point is extracted from the second grayscale value change curve; and a grayscale value mutation range is determined based on the first and second grayscale value mutation points. This allows for more accurate determination of the first and second grayscale value mutation points, and thus, the grayscale value mutation range.

[0068] like Figure 7 As shown, the second gray value change curve is obtained by filtering the first gray value change curve. The horizontal axis of the second gray value change curve is the sequence number of the current column image, and the vertical axis is the average gray value of the current column image. The second gray value change curve is Figure 7 The blue curve in .

[0069] For the second grayscale value mutation point, i.e., the decreasing turning point (the turning point on the left), the background area here is a light background area. Due to the noise and tailing in the light background area, the first grayscale value change curve will fluctuate greatly at this position. Therefore, it is difficult to extract the second grayscale value mutation point directly from the first grayscale value change curve. Therefore, it is necessary to filter the first grayscale value change curve to form a second grayscale value change curve, which is conducive to extracting the second grayscale value mutation point. For the first grayscale value mutation point, i.e., the increasing turning point (the turning point on the right), the background area here is a dark background area. Dark background areas are generally more stable, so the first grayscale value mutation point can be directly extracted from the first grayscale value change curve.

[0070] It should be noted that the grayscale value change curve through which the first grayscale value mutation point and the second grayscale value mutation point are extracted can be determined according to actual conditions, such as adjusting it according to the depth of the background area. Of course, the first grayscale value mutation point and the second grayscale value mutation point can also be extracted at the same time from the second grayscale value change curve, which is not specifically limited here.

[0071] In some embodiments, from the lowest point to the highest point of the first grayscale value change curve, the grayscale mean points in the first grayscale value change curve are traversed in sequence. If the curve formed by the current grayscale mean point and the adjacent grayscale mean point is in an increasing state, the current grayscale mean point is used as the first grayscale value mutation point; from the highest point to the lowest point of the second grayscale value change curve, the grayscale mean points in the second grayscale value change curve are traversed in sequence. If the curve formed by the current grayscale mean point and the adjacent grayscale mean point is in a decreasing state, the current grayscale mean point is used as the second grayscale value mutation point.

[0072] For example, from the lowest point of the first grayscale value change curve (the lowest point on the right) to the highest point (the highest point on the left), if the grayscale mean value of the current grayscale mean point is 10, the grayscale mean value of the adjacent grayscale mean point on the left is 13, and the grayscale mean value of the adjacent grayscale mean point on the right is 7, that is, from the lowest point to the highest point, the grayscale means of these three grayscale mean points are 7, 10, and 13 respectively. Therefore, the curve formed by these three grayscale mean points is in an increasing state, and the current grayscale mean point is taken as the first grayscale value mutation point.

[0073] For example, from the highest point (the highest point on the left) to the lowest point (the lowest point on the right) of the second grayscale value change curve, if the grayscale mean value of the current grayscale mean point is 60, the two adjacent grayscale mean points on the left have grayscale means of 62 and 64, and the two adjacent grayscale mean points on the right have grayscale means of 56 and 52, that is, from the highest point to the lowest point, the grayscale means of these five grayscale mean points are 64, 62, 60, 56, and 52 respectively. Therefore, the curve formed by these five grayscale mean points is in a decreasing state, and the current grayscale mean point is taken as the second grayscale value mutation point.

[0074] It should be noted that there may be one or more adjacent grayscale mean points, which is not specifically limited here.

[0075] like Figure 7 As shown, illustratively, a vertical line corresponding to the first gray value mutation point and the second gray value mutation point can be determined according to the first gray value mutation point and the second gray value mutation point, and the gray value mutation range can be delineated according to the vertical line.

[0076] S104 , determining a smear score corresponding to the smear area according to the grayscale value mutation range.

[0077] The smear score corresponding to the smear area is used to indicate the degree of motion smear corresponding to the smear area.

[0078] In some embodiments, the smear distance is determined based on the grayscale value mutation range, and the smear score of the smear area is determined based on the smear distance based on the mapping relationship between the smear distance and the smear score. In this way, the smear score corresponding to each smear area can be accurately determined.

[0079] The smear distance is the distance at which the smear is formed in the smear area.

[0080] For example, the mapping relationship between the smear distance and the smear score is shown in Table 1.

[0081] Table 1

[0082] Smear distance range Smear score [0，50) 90 [50，75) 80 [75，85) 70 [85，110) 65 [110，140) 55 [140，180) 45 [180，～) 35

[0083] It should be noted that the mapping relationship between the smear distance and the smear score can be adjusted according to actual conditions and is not specifically limited here.

[0084] For example, if the smear distance of the smear area A is 68, the smear score of the smear area A is determined to be 80 points; if the smear distance of the smear area B is 125, the smear score of the smear area B is determined to be 55 points.

[0085] S105 : Determine the motion smear degree of the shooting device according to the smear score of each smear area.

[0086] The degree of motion smear of the shooting device can be reflected by the smear score of each smear area. In the embodiment of the present application, the lower the smear score, the more serious the degree of motion smear of the shooting device.

[0087] In some embodiments, the contrast ratio of the background area corresponding to each smear area is determined; a weight ratio of each smear area is determined based on the contrast ratio; based on the weight ratio of each smear area, the smear scores of each smear area are weighted and summed to obtain a smear score of the camera; and the degree of motion smear of the camera is determined based on the smear score of the camera. In this way, corresponding weight ratios can be assigned to different smear areas based on the contrast ratio of the background area, thereby accurately determining the degree of motion smear of the camera.

[0088] Through testing, we know that the lower the contrast of the background area, the more serious the tailing is. Therefore, the weight ratio of the tailing score corresponding to the low-contrast tailing area can be increased.

[0089] For example, if the smear area includes smear area C, smear area D, and smear area E, and the contrast of smear area C is lower than that of smear area D, and the contrast of smear area D is lower than that of smear area E, then based on the contrast ratios, it can be determined that smear area C, smear area D, and smear area E are 60%, 30%, and 10%, respectively. If the smear scores corresponding to smear area C, smear area D, and smear area E are 65, 70, and 80, respectively, a weighted sum of the smear scores of smear area C, smear area D, and smear area E yields a smear score of 68 for the camera. Finally, the degree of motion smear of the camera is determined based on the smear score of the camera.

[0090] The motion smear detection method provided in the embodiments of the present application obtains a target motion image captured by a camera in a detection scene; determines a first grayscale value change curve corresponding to each smear region; extracts a grayscale value mutation range from the first grayscale value change curve; determines a smear score corresponding to the smear region based on the grayscale value mutation range; and determines the degree of motion smear of the camera based on the smear score of each smear region. This method unifies the criteria for judging the degree of motion smear, reduces errors caused by human subjectivity, and provides highly repeatable, objective, and unified evaluation results. It also improves the efficiency and accuracy of motion smear detection and saves labor and software costs.

[0091] See also Figure 8 , Figure 8 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0092] like Figure 8 As shown, the terminal device 200 may include a processor 201 and a memory 202, and the processor 201 and the memory 202 are connected via a bus 203, such as an I2C (Inter-integrated Circuit) bus.

[0093] In an exemplary embodiment, the processor 201 can be used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 201 can be a central processing unit (CPU), and the processor 201 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0094] Specifically, the memory 202 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0095] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0096] The processor 201 is configured to run a computer program stored in the memory, and implement any one of the motion smear detection methods provided by the embodiments of the present invention when executing the computer program.

[0097] In one embodiment, the processor 201 is used to run a computer program stored in a memory, and implement the following steps when executing the computer program: obtaining a target motion image captured by a shooting device in a detection scene, wherein the detection scene is composed of multiple background areas with different contrasts, and the target motion image is used to form a trailing area in the background area; determining a first grayscale value change curve corresponding to each of the trailing areas; extracting a grayscale value mutation range from the first grayscale value change curve; determining a trailing score corresponding to the trailing area based on the grayscale value mutation range; and determining a degree of motion trailing of the shooting device based on the trailing score of each of the trailing areas.

[0098] In one embodiment, when the processor 201 implements the acquisition of the target motion image captured by the shooting device in the detection scene, it is used to implement: capturing a motion video in the detection scene through the shooting device; converting the motion video into multiple frames of motion images, and determining the target motion image from the multiple frames of motion images.

[0099] In one embodiment, when the processor 201 implements the determination of the first grayscale value change curve corresponding to each of the drag areas, it is used to implement: for any one of the drag areas, determine the grayscale mean of each column of images in the drag area; and generate the first grayscale value change curve corresponding to the drag area based on the grayscale mean of each column of images in the drag area.

[0100] In one embodiment, when the processor 201 implements the extraction of the grayscale value mutation range from the first grayscale value change curve, it is used to implement: from the lowest point to the highest point of the first grayscale value change curve, traverse the grayscale mean points in the first grayscale value change curve in sequence, if the curve formed by the current grayscale mean point and the adjacent grayscale mean point is in an increasing state, then the current grayscale mean point is used as the first grayscale value mutation point; from the highest point to the lowest point of the first grayscale value change curve, traverse the grayscale mean points in the first grayscale value change curve in sequence, if the curve formed by the current grayscale mean point and the adjacent grayscale mean point is in a decreasing state, then the current grayscale mean point is used as the second grayscale value mutation point; determine the grayscale value mutation range according to the first grayscale value mutation point and the second grayscale value mutation point.

[0101] In one embodiment, when the processor 201 implements the extraction of the grayscale value mutation range from the first grayscale value change curve, it is used to implement: filtering the first grayscale value change curve to obtain a second grayscale value change curve; extracting a first grayscale value mutation point from the first grayscale value change curve; extracting a second grayscale value mutation point from the second grayscale value change curve; and determining the grayscale value mutation range based on the first grayscale value mutation point and the second grayscale value mutation point.

[0102] In one embodiment, when the processor 201 implements the step of extracting the first grayscale value mutation point from the first grayscale value change curve, the processor 201 is configured to implement the following steps: sequentially traversing the grayscale mean points in the first grayscale value change curve from the lowest point to the highest point of the first grayscale value change curve; if a curve formed by a current grayscale mean point and adjacent grayscale mean points is in an increasing state, then using the current grayscale mean point as the first grayscale value mutation point;

[0103] When the processor 201 implements the step of extracting the second grayscale value mutation point from the second grayscale value change curve, the processor 201 is configured to implement:

[0104] From the highest point to the lowest point of the second grayscale value change curve, traverse the grayscale mean points in the second grayscale value change curve in sequence. If the curve formed by the current grayscale mean point and the adjacent grayscale mean point is in a decreasing state, the current grayscale mean point is used as the second grayscale value mutation point.

[0105] In one embodiment, when the processor 201 determines the shadow score corresponding to the shadow area based on the grayscale value mutation range, it is used to implement: determining the shadow distance based on the grayscale value mutation range; based on the mapping relationship between the shadow distance and the shadow score, determining the shadow score of the shadow area according to the shadow distance.

[0106] In one embodiment, when determining the degree of motion drag of the shooting device based on the drag scores of each of the drag areas, the processor 201 is used to implement: determining the contrast of the background area corresponding to each of the drag areas; determining the weight ratio of each of the drag areas based on the contrast; performing weighted summation of the drag scores of each of the drag areas based on the weight ratio of each of the drag areas to obtain the drag score of the shooting device; and determining the degree of motion drag of the shooting device based on the drag score of the shooting device.

[0107] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned embodiment and will not be repeated here.

[0108] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a computer program, which includes program instructions. The processor executes the above program instructions to implement any one of the motion smear detection methods provided in the embodiments of the present application.

[0109] For example, when the program is loaded by the processor, the following steps may be performed:

[0110] Acquire a target motion image captured by a shooting device in a detection scene, wherein the detection scene is composed of multiple background areas with different contrasts, and the target motion image is used to form a trailing shadow area in the background area; determine a first grayscale value change curve corresponding to each of the trailing shadow areas; extract a grayscale value mutation range from the first grayscale value change curve; determine a trailing shadow score corresponding to the trailing shadow area according to the grayscale value mutation range; and determine the degree of motion trailing shadow of the shooting device according to the trailing shadow score of each of the trailing shadow areas.

[0111] The computer-readable storage medium may be an internal storage unit of the terminal device in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The computer-readable storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD card), a flash card, etc. equipped on the terminal device.

[0112] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, programs required for at least one function, etc.; the data storage area may store data created according to each program, etc.

[0113] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for detecting motion smear, characterized in that: The method comprises: Acquire a target motion image captured by a shooting device in a detection scene, wherein the detection scene is composed of a plurality of background areas with different contrasts, and the target motion image is used to form a smear area in the background area; Determining a first grayscale value change curve corresponding to each of the smear areas; Extracting a grayscale value mutation range from the first grayscale value change curve; Determining a smear score corresponding to the smear area according to the grayscale value mutation range; The degree of motion smear of the shooting device is determined according to the smear score of each smear area.

2. The method according to claim 1, characterized in that The acquiring of the target motion image captured by the shooting device in the detection scene includes: Collecting motion video in the detection scene by the shooting device; The motion video is converted into a plurality of frames of motion images, and the target motion image is determined from the plurality of frames of motion images.

3. The method according to claim 1, characterized in that The determining of the first grayscale value change curve corresponding to each of the smear areas includes: For any of the smear areas, determining the grayscale mean of each column of images in the smear area; A first grayscale value variation curve corresponding to the smear area is generated according to the grayscale mean value of each column of images in the smear area.

4. The method according to claim 1, wherein The step of extracting the grayscale value mutation range from the first grayscale value change curve includes: From the lowest point to the highest point of the first grayscale value change curve, traverse the grayscale mean points in the first grayscale value change curve in sequence, and if the curve formed by the current grayscale mean point and the adjacent grayscale mean points is in an increasing state, then use the current grayscale mean point as the first grayscale value mutation point; Traversing the grayscale mean points in the first grayscale value change curve from the highest point to the lowest point in the first grayscale value change curve in sequence, and if the curve formed by the current grayscale mean point and the adjacent grayscale mean points is in a decreasing state, taking the current grayscale mean point as the second grayscale value mutation point; A grayscale value mutation range is determined according to the first grayscale value mutation point and the second grayscale value mutation point.

5. The method according to claim 1, wherein The step of extracting the grayscale value mutation range from the first grayscale value change curve includes: performing filtering processing on the first grayscale value change curve to obtain a second grayscale value change curve; Extracting a first gray value mutation point from the first gray value change curve; Extracting a second gray value mutation point from the second gray value change curve; A grayscale value mutation range is determined according to the first grayscale value mutation point and the second grayscale value mutation point.

6. The method according to claim 5, characterized in that The step of extracting a first grayscale value mutation point from the first grayscale value change curve includes: From the lowest point to the highest point of the first grayscale value change curve, traverse the grayscale mean points in the first grayscale value change curve in sequence, and if the curve formed by the current grayscale mean point and the adjacent grayscale mean points is in an increasing state, then use the current grayscale mean point as the first grayscale value mutation point; The step of extracting a second grayscale value mutation point from the second grayscale value change curve includes: From the highest point to the lowest point of the second grayscale value change curve, traverse the grayscale mean points in the second grayscale value change curve in sequence. If the curve formed by the current grayscale mean point and the adjacent grayscale mean point is in a decreasing state, the current grayscale mean point is used as the second grayscale value mutation point.

7. The method according to claim 1, characterized in that The determining of the smear score corresponding to the smear area according to the grayscale value mutation range includes: Determining the smear distance according to the grayscale value mutation range; Based on a mapping relationship between the smear distance and the smear score, the smear score of the smear area is determined according to the smear distance.

8. The method according to claim 1, characterized in that The determining the motion smear degree of the shooting device according to the smear score of each smear area includes: Determining the contrast of the background area corresponding to each of the smear areas; determining a weight ratio of each of the smear areas according to the contrast; Based on the weight ratio of each of the smear areas, performing weighted summation on the smear scores of each of the smear areas to obtain the smear score of the shooting device; The degree of motion smear of the shooting device is determined according to the smear score of the shooting device.

9. A terminal device, characterized in that: The terminal device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the motion smear detection method according to any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the motion smear detection method according to any one of claims 1 to 8.

Images