Motion detection method, detection device, electronic device and medium for transmission belt

Abstract

The present application discloses a motion detection method, detection equipment, electronic equipment and medium for a conveyor belt, the detection method comprising: obtaining an image sequence collected for a target conveyor belt; determining the optical flow features of the optical flow tracking points based on the optical flow tracking points of the area to be detected in different images in the image sequence; the area to be detected is at least set based on a sub-area of ​​the target conveyor belt; and determining the motion state of the target conveyor belt based on the optical flow features. Through the above-mentioned method, the present application realizes the motion state detection of the target conveyor belt based on the optical flow features of the optical flow tracking points when the image sequence is relatively constant, and has a high detection accuracy.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a motion detection method, detection equipment, electronic equipment and medium for a conveyor belt. Background Art

[0002] In recent years, with the increasing development of computer technology, computers are used to process, analyze and detect the belt image information transmitted by the camera in a certain order, and then output the belt movement status results and issue a status change alarm, which is convenient for staff and improves production efficiency.

[0003] As an important energy source in the industrial production process, coal mines play a vital role in the country's basic industry. Due to the special production conditions of coal mines and the complex mine environment, conveyor belts, as crucial equipment in the production and transportation of mineral materials, have greatly improved the efficiency of mineral production operations on the one hand, and reduced the probability of personal safety accidents of miners on the other hand, playing an increasingly important role. Using information technology to realize intelligent monitoring of the working status of mineral belts is of great significance for further reducing the cost of mineral production and improving production safety.

[0004] At present, due to the fact that the conveyor belt, such as the coal mine belt, moves at a fast speed when unloaded, or the belt is smooth and has no coal, the acquired images will have small differences. The grayscale values ​​of the acquired images are compared to judge the movement state of the belt, so the difference obtained by the grayscale value comparison is also small, which leads to misjudgment of the movement state of the conveyor belt. Summary of the invention

[0005] In order to solve the above technical problems, the technical solution adopted in the first aspect of the present application is to provide a motion detection method for a conveyor belt, which detection method includes: acquiring an image sequence collected for a target conveyor belt; determining optical flow characteristics of the optical flow tracking points based on optical flow tracking points of the area to be detected in different images in the image sequence; the area to be detected is set at least based on a sub-area of ​​the target conveyor belt; and determining the motion state of the target conveyor belt based on the optical flow characteristics.

[0006] In order to solve the above technical problems, the technical solution adopted in the second aspect of the present application is to provide a detection device, which includes:

[0007] An acquisition module, used for acquiring an image sequence collected for a target conveyor belt;

[0008] A determination module, for determining optical flow features of optical flow tracking points based on optical flow tracking points of the area to be detected in different images in the image sequence; the area to be detected is set based on at least a sub-area of ​​the target transmission belt;

[0009] The determination module is also used to determine the motion state of the target conveyor belt based on the optical flow features.

[0010] In order to solve the above technical problems, the technical solution adopted in the third aspect of the present application is to provide an electronic device, which includes: a processor and a memory, the memory stores a computer program, and the processor is used to execute the computer program to implement the detection method as in the first aspect of the present application.

[0011] In order to solve the above technical problems, the technical solution adopted in the fourth aspect of the present application is to provide a computer-readable storage medium, which stores a computer program, and the computer program can implement the detection method of the first aspect of the present application when executed by a processor.

[0012] The beneficial effects of the present application are as follows: the present application obtains an image sequence captured for the target conveyor belt, and when the image sequence is relatively constant, determines the optical flow characteristics of the optical flow tracking points based on the optical flow tracking points on different images, and determines the motion state of the target conveyor belt based on the optical flow characteristics, thereby making the detection method more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 It is a schematic diagram of the flow of the motion detection method of the conveyor belt of the present application;

[0015] Figure 2 This is a schematic diagram of the ROI area configured in this application;

[0016] Figure 3 This application Figure 1 A schematic diagram of a specific embodiment of obtaining optical flow tracking points in step S12;

[0017] Figure 4 This application Figure 1 A schematic diagram of a specific embodiment of calculating optical flow features in step S12;

[0018] Figure 5 This application Figure 1 A schematic diagram of a specific embodiment of step S13;

[0019] Figure 6 This application Figure 1 A flowchart of another specific embodiment of obtaining optical flow tracking points in step S12;

[0020] Figure 7 It is a flowchart of a specific embodiment of the state counting of the present application;

[0021] Figure 8 It is a schematic diagram of the status counting of this application;

[0022] Fig. 9 This is a schematic diagram of the conveyor belt motion state alarm of the present application;

[0023] Fig.10 is a schematic structural block diagram of an embodiment of the detection device of the present application;

[0024] Fig.11 is a schematic structural block diagram of an embodiment of an electronic device of the present application;

[0025] Fig.12 It is a schematic block diagram of the structure of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0027] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0028] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0029] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] In order to illustrate the technical solution of the present application, the following is an explanation through a specific embodiment. The present application provides a motion detection method for a conveyor belt. The detection method is applied to a detection device, which includes a target conveyor belt, a camera assembly and a processor. The camera assembly is arranged above the target conveyor belt, and the processor is connected to the camera assembly. The target conveyor belt can be a coal mine belt. Please refer to Figure 1 , Figure 1 : is a flow chart of the motion detection method of the conveyor belt of the present application, and the detection method specifically comprises the following steps:

[0033] S11: Acquire an image sequence collected for the target transmission belt;

[0034] In order to obtain a sequence of images captured for the target conveyor belt, the camera assembly can be set above the target conveyor belt. Specifically, in order to make the captured image sequence more convenient to use, the camera assembly can be set directly above the target conveyor belt so that the target conveyor belt is located in the middle of the shooting area of ​​the camera assembly.

[0035] The camera assembly includes a camera, which can be used to shoot the target conveyor belt. When the camera is turned on, the target conveyor belt can be shot. Due to the recording of the camera, the recorded video of the target conveyor belt can be obtained. By processing the recorded video, each frame of the video image can be extracted to obtain an image sequence collected for the target conveyor belt.

[0036] The processor is connected to the camera assembly. Generally, the camera assembly can be connected to the processor for communication, which can be a wireless connection or a wired connection, which is not limited here. Through the communication connection between the camera assembly and the processor, the camera can send the image sequence to the processor, so that the image sequence is collected and transmitted, and the processor obtains the image sequence through the camera assembly.

[0037] S12: determining optical flow features of the optical flow tracking points based on the optical flow tracking points of the to-be-detected area in different images in the image sequence;

[0038] In the image sequence, the target conveyor belt occupies the middle position of each image, and the area occupied by the target conveyor belt can be called the area to be detected, that is, the area to be detected is set at least based on a sub-area of ​​the target conveyor belt. Specifically, the target conveyor belt can be processed, the edge of the target conveyor belt can be detected, and the edge can be enclosed into a polygon to determine the area to be detected.

[0039] Among them, from a practical point of view, the area to be detected has at least three sides. Through a connecting line between the near end and the far end of the camera component, an optical flow tracking point of the area to be detected can be selected on the connecting line to determine the object tracked by the camera.

[0040] The processor determines and selects the optical flow tracking points in the area to be detected where the target conveyor belt is located, and can collect, calculate and transmit the optical flow tracking points in the area to be detected for tracking by running a tracking algorithm on the processor. Specifically, after the optical flow tracking points are determined, the optical flow features of the optical flow tracking points can be determined because there is a certain time interval between different images.

[0041] S13: Determine the motion state of the target conveyor belt based on the optical flow features.

[0042] Specifically, if there is an optical flow distance, the processor can determine that the state of the target conveyor belt has moved, but usually, in reality, there are many situations in which the target conveyor belt can move, so an optical flow distance threshold is usually set to indicate whether the movement state of the target conveyor belt is real, thereby filtering out the buffer state of the target conveyor belt to a certain extent, such as if the target conveyor belt is only shaking, slipping, etc., and then accurately judging the target conveyor belt. Of course, whether to set an optical flow distance threshold is not limited here.

[0043] Therefore, when the image sequence obtained by the camera component shooting the target conveyor belt is relatively constant, the present application obtains the image sequence captured for the target conveyor belt, based on the optical flow tracking points on different images, and determines the optical flow features of the optical flow tracking points, and determines the motion state of the target conveyor belt based on the optical flow features, so that the detection method has higher accuracy.

[0044] Among them, see Figure 2 , Figure 2 : is a schematic diagram of the ROI area configuration of the present application. The target transmission belt can be a quadrilateral area surrounded by the dotted line in the figure, that is, the area to be detected can be a quadrilateral. Specifically, Figure 2 As shown, since the area to be inspected is obtained by taking a video image by a camera assembly, and the camera assembly is located directly above the target conveyor belt, the length of the target conveyor belt on the video image obtained is closer to the camera assembly than the length away from the camera assembly, so that the area to be inspected can be a trapezoidal area.

[0045] Furthermore, for obtaining optical flow tracking points of the region to be detected in different images in an image sequence, see Figure 3 , Figure 3 This application Figure 1 The flowchart of a specific embodiment of obtaining optical flow tracking points in step S12 specifically includes the following steps:

[0046] S21: convert each image in the image sequence into a grayscale image;

[0047] Due to external factors such as lighting, the video images captured by the camera component often have a certain color, and external environmental factors such as lighting have a great impact on pixels, which affects the optical flow tracking points and makes the optical flow features of the optical flow tracking points inaccurate. Therefore, in the actual processing process, in order to avoid the influence of external environmental factors as much as possible, it is necessary to consider the impact of lighting or color on pixels.

[0048] Specifically, the processor extracts image frames in the surveillance video in real time to obtain an image sequence. In order to make the transmission position of the target conveyor belt relatively constant, the lighting relatively constant, the movement speed relatively constant, and the image quality relatively constant without being affected by the external environment, the image sequence is only converted into a grayscale image here, which makes it easier to use the image sequence.

[0049] S22: Acquire the area to be detected corresponding to the target transmission belt from the grayscale image;

[0050] Specifically, Figure 2 As shown, the dotted box represents the target transmission belt area in each image, that is, the area to be detected, and the four points represent the configured region of interest (ROI), which should be a sub-region of the area where the target transmission belt in each image is located, that is, the area to be detected is a quadrilateral, of course not limited to the position shown in the figure.

[0051] In the solution of the present application, based on the grayscale image obtained previously, the processor can obtain the quadrilateral corresponding to the target transmission belt, and then calculate Figure 2The optical flow features of the pixels on the line connecting the two diagonal points are used to determine the movement state of the belt.

[0052] S23: Select pixel points on the line connecting the diagonal points of the area to be detected as optical flow tracking points.

[0053] Specifically, in order to make the selection of pixel points more possible, the processor may connect two pairs of diagonal points of the quadrilateral to form a connecting line, and select all required pixel points on the line connecting the two pairs of diagonal points as optical flow tracking points.

[0054] In this way, when the image sequence of the target conveyor belt is under relatively constant external environmental conditions, the longest connecting line is selected in the area to be detected to obtain pixel points within the maximum range, so as to determine the selection of reasonable optical flow tracking points. Therefore, one or more optical flow tracking points in each image can be selected.

[0055] Furthermore, the image sequence includes different first images and second images, wherein the first image and the second image may be two adjacent frame images, or two frame images with skipped frames, which is not limited here.

[0056] If the number of optical flow tracking points is not limited, please refer to Figure 4 , Figure 4 This application Figure 1 The flowchart of a specific embodiment of calculating the optical flow feature in step S12 is as follows, based on the optical flow tracking points of the to-be-detected area in different images in the image sequence, determining the optical flow features of the optical flow tracking points specifically includes the following steps:

[0057] S31: Acquire a first optical flow tracking point of a first area to be detected in a first image;

[0058] Specifically, from Figure 3 It can be seen from step S23 that a region to be detected can be determined in each image. Thus, for the first image, the first region to be detected in the first image can be determined, thereby obtaining the first optical flow tracking point in the first region to be detected in the first image.

[0059] S32: Acquire a second optical flow tracking point in a second area to be detected in the second image;

[0060] By adopting a method similar to step S31, the second optical flow tracking point in the second area to be detected in the second image can be further obtained.

[0061] Since the optical flow distance between the first optical flow tracking point and the second optical flow tracking point needs to be calculated, for the accuracy of the calculation, it can be limited that the second optical flow tracking point actually corresponds to the first optical flow tracking point. That is to say, if the influence of the time factor is ignored, the first optical flow tracking point and the second optical flow tracking point can actually be identified as the same optical flow tracking point.

[0062] Among them, step S31 can be executed first and then step S32, and step S31 and step S32 can also be executed at the same time, which is not limited here.

[0063] S33: Calculate the optical flow distance between the first optical flow tracking point and the second optical flow tracking point based on the optical flow method.

[0064] If the optical flow feature includes the optical flow distance, the speed of the first optical flow tracking point can be measured by the optical flow method, so that the optical flow distance between the first optical flow tracking point and the second optical flow tracking point can be further calculated according to the second optical flow tracking point.

[0065] Furthermore, if the image sequence includes adjacent first image and second image.

[0066] Among them, since the time interval between frames of the image sequence is the same, the rate of the optical flow tracking point can be measured by the optical flow method, so that the movement distance of the optical flow tracking point can be calculated, and then the movement distance is used as the optical flow distance of the optical flow tracking point between two adjacent frames of video images to determine the movement state of the conveyor belt.

[0067] Furthermore, based on the optical flow distance, the processor determines the motion state of the target conveyor belt, see Figure 5 , Figure 5 This application Figure 1 The flowchart of a specific embodiment of step S13 in the embodiment specifically includes the following steps:

[0068] S41: Determine whether the optical flow distance is greater than or equal to a preset distance threshold;

[0069] In order to compare the size of the optical flow distance, usually, a preset distance threshold distance_thresh is set in the processor to determine the size of the optical flow distance of the motion of the optical flow tracking point.

[0070] Specifically, by calculating formula (1), the optical flow distance of the optical flow tracking points between two adjacent frames of video images can be obtained. The processor further determines whether the optical flow distance is greater than or equal to the optical flow distance threshold, and then the motion state of the target conveyor belt can be judged.

[0071] If the optical flow distance is greater than or equal to the distance threshold, the process proceeds to step S42, where the processor sets the motion flag of the target conveyor belt to a first preset value, and determines that the state of the target conveyor belt is moving; if the optical flow distance is less than the distance threshold, the process proceeds to step S43, where the processor sets the motion flag of the target conveyor belt to a second preset value, and determines that the state of the target conveyor belt is stationary.

[0072] Specifically, the first preset value may be 1, and the second preset value may be 0. Figure 2 If the average optical flow distance of the optical flow tracking points on the connection path is greater than or equal to distance_thresh, the state move_state of the target conveyor belt is judged to be moving, otherwise it is stationary. Specifically, it can be as shown in formula (1):

[0073]

[0074] Wherein, move_state indicates the state of the target conveyor belt; distance indicates the optical flow distance of the optical flow tracking point, and distance_thresh indicates the optical flow distance threshold. Of course, the first preset value can also be set to 2 and the second preset value can be set to 1, which is not limited here.

[0075] Among them, if multiple pixel points on the connecting line are uniformly selected as multiple optical flow tracking points, the pixel points can be selected as far as possible within a reasonable distribution range. Of course, relevant technical personnel in this field can also perform sparse selection on the connecting line to obtain sparse optical flow points, which is not limited here.

[0076] See also Figure 6 , Figure 6 This application Figure 1 A flowchart of another specific embodiment of obtaining optical flow tracking points in step S12, which is based on the optical flow tracking points of the to-be-detected area in different images in the image sequence, obtaining multiple optical flow tracking points in each image, wherein steps S51, S52 and S53 are respectively Figure 4 Step S31, step S32 and step S33 in are similar, but the difference is Figure 4 The number of optical flow tracking points in is taken as one, and Figure 6 The number of optical flow tracking points in is taken as an example, which will not be repeated here.

[0077] S54: Calculate and obtain multiple optical flow distances, and obtain an average value of the multiple optical flow distances.

[0078] Here, two adjacent frame images are used as an example for calculation, and there is no limitation for using skip frame images for calculation.

[0079] Based on the optical flow method, the processor calculates the optical flow distance of the optical flow tracking points between two adjacent frames of video images. Specifically, the Lucas–Kanade optical flow algorithm (LK optical flow method) can be used. The processor calculates the average distance of movement of multiple optical flow tracking points between two adjacent frames of video images, where the LK optical flow method is an optical flow estimation algorithm for two adjacent frames.

[0080] Specifically, the average distance of multiple optical flow tracking points between two adjacent video frames is expressed as follows:

[0081]

[0082] Where dist represents the average distance moved by N optical flow tracking points between two adjacent video frames; N is a positive integer greater than or equal to 1, representing the number of pixels; and Respectively represent the horizontal and vertical coordinates of the pixel point in the previous frame of the current frame; and Respectively represent the horizontal and vertical coordinates of the pixel point in the current frame.

[0083] Furthermore, after determining the state of the target conveyor belt corresponding to the area to be inspected, refer to Figure 7 , Figure 7 : is a flow chart of a specific embodiment of the state counting of the present application, and the detection method also includes:

[0084] S61: Determine whether the state of the target conveyor belt is moving or stationary;

[0085] If the optical flow distance is greater than the distance threshold, indicating that the state of the target conveyor belt is moving, then the process enters step S62 to determine that the state of the target conveyor belt is moving, and the state count of the processor is increased by 1, which may indicate that the belt starts to move; if the optical flow is less than or equal to the distance threshold, indicating that the state of the target conveyor belt is stationary, then the process enters step S63 to determine that the state of the target conveyor belt is stationary, and the state count of the processor is decreased by 1, which may indicate that the belt stops moving.

[0086] Furthermore, the detection device also includes an alarm component connected to the processor, see Figure 8 and Fig. 9 ,, Figure 8 This is a schematic diagram of the application status count. Fig. 9 This is a schematic diagram of the conveyor belt motion status alarm of this application.

[0087] Among them, Figure 8As shown, the counting state includes at least a counting state, a static counting state, a transition counting state and a motion counting state, and the counting state is set between the transition counting states. Specifically, the counting range of the state counting is 0-10, assuming that the counting starts from 0, the counting range of the static counting state is 0-3, the counting range of the transition counting state is 3-7, and the counting range of the motion counting state is 7-10.

[0088] Furthermore, the detection method further includes: when the state count is greater than a first threshold, issuing a motion alarm of the target conveyor belt; when the state count is less than a second threshold, issuing a stationary alarm of the target conveyor belt.

[0089] Specifically, if the first threshold is 7 and the second threshold is 3, when the state count is greater than 7, the motion flag of the target conveyor belt jumps to 1 to determine that the target conveyor belt starts to move, and the alarm component issues a motion alarm of the target conveyor belt; when the state count is less than 3, the motion flag of the target conveyor belt jumps to 1 to determine that the target conveyor belt stops moving, and the alarm component issues a stationary alarm of the target conveyor belt.

[0090] Furthermore, the detection method also includes:

[0091] When the target conveyor belt's motion state move_state jumps to 1, the alarm component needs to issue a belt motion alarm; conversely, when the target conveyor belt's motion state move_state jumps to 0, the alarm component needs to issue a belt stationary alarm.

[0092] To avoid false alarms caused by misdetection of the optical flow method, the alarm component needs to confirm the alarm signal. When the processor determines that the alarm component corresponding to the previous frame image of the current frame and the alarm component corresponding to the current frame image have both issued an alarm, it confirms that the alarm signal of the current frame image is a real alarm, otherwise the false alarm will be ignored.

[0093] Furthermore, the detection method also includes: when the state count is greater than a first threshold value and less than a second threshold value, confirming that the alarm signal of the target conveyor belt movement state is a real alarm to prevent repeated alarms.

[0094] Specifically, if the first threshold is 7 and the second threshold is 3, then when the state count is greater than 3 and less than 7, the target conveyor belt is determined to be in a transition state, and the alarm component does not alarm to prevent repeated alarms. Specifically, the alarm signal can be output with a delay, and an alarm signal is generated when a change in the motion state of the target conveyor belt is detected. Figure 7 The target conveyor belt motion state alarm state machine shown further confirms whether the alarm signal needs to be output to reduce the occurrence of false alarms and achieve single alarms.

[0095] The initial state is set to S0, and the alarm count C is set to 0. Specifically, S0 represents stillness, S1 represents transition state, and S2 represents motion state, where the motion state needs to prevent repeated alarms. The alarm threshold M is different from the threshold of the optical flow distance. A=0 indicates that the alarm state of the target conveyor belt is stillness, and A=1 indicates that the alarm state of the target conveyor belt is motion.

[0096] S0: When the motion alarm state A=1 is received, the state jumps to S1, enters the pre-alarm stage, and the alarm count C starts counting; when A=0, the S0 state is maintained.

[0097] S1: When the alarm count C is less than the alarm threshold M, maintain the S1 state; when the alarm count C reaches the alarm threshold M, when the alarm state A = 1, an alarm is issued and jumps to S2 to enter the state of preventing repeated alarms; when the alarm state A = 0, jumps to S0.

[0098] S2: When the alarm state A=1, it means that the target conveyor belt is running all the time, and S2 is repeated to continue calculating and obtaining the optical flow distance. When the alarm state A=0, jump to S0.

[0099] Therefore, in the relatively constant environment of the coal mine conveyor belt image, the target conveyor belt motion state detection is realized by using the optical flow method, which has a high detection accuracy. And based on the belt motion alarm mechanism, false alarms can be reduced and a single alarm of motion state switching can be realized.

[0100] In order to illustrate the technical solution of the present application, the present application also provides a detection device, please refer to Fig.10 , Fig.10 It is a schematic block diagram of the structure of an embodiment of the detection device of the present application. The detection device 7 includes: an acquisition module 71 and a determination module 72.

[0101] An acquisition module 71 is used to acquire an image sequence collected for a target conveyor belt;

[0102] A determination module 72, for determining optical flow features of optical flow tracking points based on optical flow tracking points of the area to be detected in different images in the image sequence; the area to be detected is set based on at least a sub-area of ​​the target transmission belt;

[0103] The determination module 72 is also used to determine the motion state of the target conveyor belt based on the optical flow characteristics.

[0104] Therefore, the present application uses an acquisition module 71 to acquire an image sequence captured for the target conveyor belt. When the image sequence is relatively constant, based on the optical flow tracking points on different images, the optical flow features of the optical flow tracking points are determined by the determination module 72, and the motion state of the target conveyor belt is determined based on the optical flow features, so that the detection method has higher accuracy.

[0105] In order to illustrate the technical solution of the present application, the present application also provides an electronic device, which can be a computer or a mobile phone, etc., without specific limitation. Fig.11 , Fig.11 It is a schematic block diagram of the structure of an electronic device embodiment of the present application. The electronic device 8 includes: a processor 81 and a memory 82. The memory 82 stores a computer program 821. The processor 81 is used to execute the computer program 821 to implement the detection method of the embodiment of the present application, which will not be repeated here.

[0106] In addition, this application also provides a computer-readable storage medium, see Fig.12 , Fig.12 It is a structural schematic block diagram of an embodiment of a computer-readable storage medium of the present application. The computer-readable storage medium 9 stores a computer program 91. When the computer program 91 is executed by a processor, it can implement the detection method of the embodiment of the present application, which will not be repeated here.

[0107] If it is implemented in the form of a software functional unit and sold or used as an independent product, it can also be stored in a device with a storage function. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage device, including a number of instructions (program data) to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present invention. The aforementioned storage device includes: various media such as USB flash drive, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and electronic devices such as computers, mobile phones, laptops, tablet computers, cameras, etc. with the above storage media.

[0108] The description of the execution process of the program data in the device with storage function can refer to the description in the above-mentioned detection method embodiment of the present application, which will not be repeated here.

[0109] The above descriptions are merely embodiments of the present application and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for detecting the motion of a conveyor belt, characterized in that: The detection method comprises: Acquire a sequence of images collected for a target conveyor belt; Based on the optical flow tracking points of the area to be detected in different images in the image sequence, determining the optical flow features of the optical flow tracking points; the area to be detected is set based on at least a sub-area of ​​the target transmission belt; Based on the optical flow characteristics, determining the motion state of the target conveyor belt; Wherein, the optical flow tracking points based on the area to be detected in different images in the image sequence include: Convert each image in the image sequence into a grayscale image; Acquire the area to be detected corresponding to the target transmission belt from the grayscale image, wherein the area to be detected is a quadrilateral; Select pixel points on the line connecting the diagonal points of the area to be detected as the optical flow tracking points.

2. The method according to claim 1, characterized in that The image sequence includes different first and second images; The step of determining the optical flow features of the optical flow tracking points based on the optical flow tracking points of the to-be-detected area in different images in the image sequence includes: Acquire a first optical flow tracking point of a first area to be detected in the first image, and a second optical flow tracking point of a second area to be detected in the second image; Based on the optical flow method, an optical flow distance between the first optical flow tracking point and the second optical flow tracking point is calculated, and the optical flow feature includes the optical flow distance.

3. The detection method according to claim 2, characterized in that: The image sequence includes adjacent first and second images.

4. The detection method according to claim 2, characterized in that: The step of determining the motion state of the target conveyor belt based on the optical flow feature includes: Determining whether the optical flow distance is greater than or equal to a preset distance threshold; If the optical flow distance is greater than or equal to the distance threshold, determining that the state of the target conveyor belt is moving; If the optical flow distance is less than the distance threshold, it is determined that the state of the target transmission belt is stationary.

5. The detection method according to claim 2, characterized in that: The step of determining the optical flow features of the optical flow tracking points based on the optical flow tracking points of the to-be-detected area in different images in the image sequence includes: Acquire a plurality of first optical flow tracking points of the first to-be-detected area and a plurality of second optical flow tracking points of the second to-be-detected area; Based on the optical flow method, a plurality of optical flow distances between the plurality of first optical flow tracking points and the plurality of second optical flow tracking points are calculated, and an average value of the plurality of optical flow distances is calculated.

6. The detection method according to claim 4, characterized in that: After determining the state of the target transmission belt, the detection method further includes: When it is determined that the state of the target conveyor belt is moving, the state count is increased by 1; When it is determined that the state of the target conveyor belt is stationary, the state count is reduced by 1.

7. The detection method according to claim 6, characterized in that: The method further comprises: When the state count is greater than a first threshold, issuing a motion alarm of the target conveyor belt; When the state count is less than a second threshold, a stationary alarm of the target conveyor belt is issued.

8. The detection method according to claim 6, characterized in that: The method further comprises: When the state count is greater than the first threshold and less than the second threshold, it is confirmed that the alarm signal of the target conveyor belt movement state is a real alarm to prevent repeated alarms.

9. A detection device, characterized in that: include: An acquisition module, used for acquiring an image sequence collected for a target conveyor belt; A determination module, configured to determine optical flow features of the optical flow tracking points based on optical flow tracking points of the area to be detected in different images in the image sequence; the area to be detected is set based on at least a sub-area of ​​the target transmission belt; The determination module is further used to determine the motion state of the target conveyor belt based on the optical flow feature; Wherein, when the determination module is used to track points based on the optical flow of the area to be detected in different images in the image sequence, it is also used to: Convert each image in the image sequence into a grayscale image; Acquire the area to be detected corresponding to the target transmission belt from the grayscale image, wherein the area to be detected is a quadrilateral; Select pixel points on the line connecting the diagonal points of the area to be detected as the optical flow tracking points.

10. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the detection method according to any one of claims 1 to 8.

11. 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 detection method according to any one of claims 1 to 8 is implemented.

Images