Detection method and system for blanking mouth state based on laser line sensing based on area division

Abstract

The present invention relates to a method for detecting the state of a blanking port using laser line sensing based on region division, comprising: acquiring a detection image, i.e., an RGB image of the blanking port irradiated by a laser line, through a camera device; converting the RGB image into a single-channel feature map of the same resolution; then dividing the detection image based on macroblocks; and then determining whether each macroblock contains a laser line based on the pixel values ​​of the feature map, thereby locating all macroblocks containing the laser line; dividing the detection image into four regions: a normal working region S1, a sticking material and secondary warning region S2, a primary warning region S3, and a material flow size analysis region S4, and further subdividing each region into multiple subregions; and determining the state of the blanking port and the material flow size based on the presence of laser lines in each subregion within each region, wherein the blanking port state includes conditions such as excessive dust / smoke concentration, normal feeding, sticking material, secondary blockage, and primary blockage. The method and system are advantageous for quickly and accurately determining the state of a belt conveyor blanking port.

Description

Technical Field

[0001] The present invention relates to the technical field of belt conveyor detection, and in particular to a detection method and system for a blanking port state based on area division and laser line sensing. Background Art

[0002] Belt conveyors are a reliable, efficient, and economical method for transporting materials. In industries such as ports, thermal power plants, and mining, they are a crucial material transport method, more efficient and economical than truck-based transport. Belt conveyor safety is crucial to safe port operations, making belt conveyor safety inspections a top priority for companies using them.

[0003] Belt conveyors are prone to blockage, belt deviation, and tearing, which can affect production operations and cause economic losses. Therefore, how to conduct online real-time monitoring of belt conveyors is the key to intelligent belt conveyors.

[0004] Chinese patent application number CN202310230572.8 discloses a laser-based material blockage detection device and method for a belt transfer station. The device comprises an upper belt, a lower belt, and a guide trough. Material enters the guide trough via the upper belt and is then transferred to the lower belt via the guide trough. A laser is provided on the upper portion of the guide trough, facing the position where the guide trough receives material and emitting a laser line toward that position, forming a laser coverage area. A camera is also provided to capture images of the laser coverage area. Although this patent also discloses a laser-based material blockage detection method, the implementation algorithm of this detection method is complex, and the speed, accuracy, and comprehensiveness of detection and judgment need to be improved. Summary of the Invention

[0005] The object of the present invention is to provide a method and system for detecting the state of a blanking opening of a belt conveyor based on laser line sensing of area division, which method and system are conducive to quickly and accurately judging the state of the blanking opening of the belt conveyor.

[0006] In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a detection method of the blanking mouth state based on laser line sensing of area division, comprising:

[0007] Acquire the detection image through the camera device, that is, the RGB image of the blanking mouth illuminated by the laser line;

[0008] Convert the RGB image into a single-channel feature map of the same resolution, then divide the detection image based on macroblocks. Then, determine whether each macroblock contains laser lines based on the pixel values ​​of the feature map, thereby locating all macroblocks containing laser lines.

[0009] The detection image is divided into four areas: normal working area S1, sticky material and secondary warning area S2, primary warning area S3 and material flow size analysis area S4, and each area is further divided into multiple sub-areas;

[0010] According to the presence of laser lines in each sub-area of ​​each area, the state of the blanking port and the size of the material flow are judged. The states of the blanking port include excessive dust / smoke concentration, normal feeding, sticking material, secondary blockage, and primary blockage.

[0011] Furthermore, the specific method of converting the RGB image into a single-channel feature map is:

[0012] A1) Convert the RGB color space image to the HLS color space image and extract the L channel image as I L ; Since the laser line is a brighter area, the brightness channel is extracted to enhance the laser line;

[0013] A2) The red pixel output in the enhanced image is denoted as I R , Among them, R, G, and B are the three channels of the RGB color space image;

[0014] A3) Fusion of brightness channel image I L and red image I R And normalize the pixel value to between 0 and 255, record the feature map F, F = norm (0.2 * I L +0.8*I R ), norm(·) is the normalization function;

[0015] A4) There is noise in the feature map F. The disconnected laser lines are connected through morphological opening and closing operations, and the noise areas smaller than the set area are removed to obtain the final feature map.

[0016] Furthermore, the specific method for locating all macroblocks containing laser lines is as follows:

[0017] B1) Define the size as w m *h m The detection image with a resolution of W*H is evenly divided into m*n macroblocks, where m=W / w m , n=H / h m ;

[0018] B2) For a macroblock, if the pixel value of the feature map in the macroblock exceeds the set threshold T f If the number of pixels exceeds 50% of the macroblock size, the macroblock is determined to contain a laser line; all macroblocks in the detection image are traversed to determine all macroblocks containing laser lines.

[0019] Furthermore, when feeding, the material flow enters the blanking port in a parabolic shape. When the laser line irradiates the blanking port, part of the laser line irradiates the bottom of the blanking port, and part of the laser line irradiates directly on the material flow.

[0020] Based on the standard inspection image during normal feeding, mark out the following in the image:

[0021] 1) The rectangular area including all laser lines irradiated on the bottom of the blanking port is defined as the normal working area S1;

[0022] 2) A rectangular area including all laser lines irradiated on the material flow, and extending the rectangular area along the direction of the laser lines to the edge of the image, is defined as the material flow size analysis area S4;

[0023] 3) The area between area S1 and area S4, which is equal in length to area S1, is divided into the sticky material and secondary warning area S2 and the primary warning area S3;

[0024] After dividing the four regions S1, S2, S3, and S4, each region is further subdivided into multiple sub-regions along its length.

[0025] Furthermore, the three areas S1, S2, and S3 are each subdivided into 7 sub-areas, and the S4 area is subdivided into 9 sub-areas.

[0026] Furthermore, according to the presence of laser lines in each sub-area of ​​each area, the state of the blanking port and the size of the material flow are judged. The specific method is as follows:

[0027] C1) Determine whether there are laser lines in more than F0 sub-regions in the S4 region, that is, the number of macroblocks containing laser lines in the sub-region exceeds the set threshold T r If yes, it is determined to be in feeding state and go to step C3), otherwise go to step C2;

[0028] C2) Determine whether there are laser lines in more than F5 sub-areas of areas S1, S2, and S3. If so, it is determined that the dust / smoke concentration at the blanking port is too high, affecting the normal shooting of the camera device, and then remind the site to spray. Otherwise, continue to determine whether there are laser lines in each sub-area of ​​area S1. It means that it is determined to be a non-feeding state and then terminate the judgment process. Otherwise, it is determined to be an abnormal state and then terminate the judgment process.

[0029] C3) judging the material flow size based on the number of sub-areas with laser lines in area S4, and judging whether laser lines exist in every sub-area in area S1. If so, it is judged as a normal feeding state and the judgment process ends. Otherwise, it is judged that there may be sticking or blocking of the material and the process goes to step C4;

[0030] C4) determining whether there are laser lines in more than F1 sub-areas in area S1, if yes, go to step C5, otherwise go to step C6;

[0031] C5) determining whether there are laser lines in more than F2 sub-areas in the S2 area. If so, it is determined to be a material sticking state and the determination process ends; otherwise, it is determined to be an abnormal state and the determination process ends;

[0032] C6) Determine whether there are laser lines in more than F3 sub-areas in the S2 area. If so, it is determined to be a secondary blockage state and the determination process ends. Otherwise, go to step C7;

[0033] C7) Determine whether there are laser lines in more than F4 sub-areas in the S3 area. If so, it is determined to be a first-level material blocking state and the determination process is terminated. Otherwise, it is determined to be an abnormal state and the determination process is terminated.

[0034] Further, F0=3, F1=2, F2=1, F3=3, F4=3, F5=3.

[0035] Furthermore, in step C3, when judging the size of the material flow according to the number of sub-regions with laser lines in region S4, it is further judged whether the sub-regions with laser lines in region S4 are continuous. If not, it is determined to be an abnormal state.

[0036] Furthermore, k consecutive frames of detection images are acquired and continuously judged. Only when the judgment results of the k consecutive frames of detection images are the same, the judgment result is confirmed to be correct and output.

[0037] The present invention also provides a detection system for the state of a blanking port based on laser line sensing of area division, which includes a memory, a processor, and computer program instructions stored in the memory and capable of being executed by the processor. When the processor executes the computer program instructions, the above-mentioned method steps can be implemented.

[0038] Compared with the existing technology, the present invention has the following beneficial effects: based on irradiating the blanking port with a laser line, the method obtains a detection image through a camera device, and then judges the state of the blanking port based on the shape change of the laser line in the detection image, including: whether it is operating normally, the size of the material flow, whether sticking occurs, whether blockage occurs, etc., which improves the speed, accuracy and comprehensiveness of the detection of the state of the belt conveyor blanking port, and has strong practicality and open application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flowchart of a method implementation of an embodiment of the present invention;

[0040] Figure 2 is a detection image obtained by a camera device in an embodiment of the present invention;

[0041] Figure 3 is a single-channel feature map obtained in an embodiment of the present invention;

[0042] Figure 4 is a schematic diagram of dividing a detection image into macroblocks in an embodiment of the present invention;

[0043] Figure 5 is a macroblock-based laser line positioning result diagram in an embodiment of the present invention;

[0044] Figure 6 is a graph showing the image region division result according to an embodiment of the present invention;

[0045] Figure 7 It is a flow chart for judging the state of the blanking port in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0047] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0048] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0049] The present invention provides a detection method and system for sensing the state of a blanking port based on area division using a laser line. The method determines whether the blanking port is feeding, blocked, or sticking, the material flow rate, and the dust concentration at the blanking port by judging the position and shape of the laser line. The implementation principle is as follows:

[0050] 1) When the laser appears on the material flow, it can be determined that the current state is feeding. The size of the material flow can be determined according to the length of the laser line on the material flow.

[0051] 2) When the position of the bottom laser line deviates, it can be determined that the bottom is sticking or blocking. According to the position of the laser line, a graded warning can be issued. When it exceeds a certain area, the highest level warning will be issued. Then, water injection / vibration or shutdown can be carried out according to the warning level.

[0052] 3) When the bottom laser line appears at multiple locations at the same time, it can be judged that the dust / smoke concentration on site has increased, and a reminder is given to spray on site.

[0053] like Figure 1As shown, this embodiment provides a method for detecting the blanking opening state based on laser line sensing based on area division, including:

[0054] 1. Deploy a laser at the blanking port and direct the laser beam from the laser to the bottom of the port. Deploy a camera at an appropriate location, ensuring that the camera's field of view covers the blanking port illuminated by the laser beam.

[0055] On this basis, the camera device can obtain Figure 2 The inspection image shown is an RGB image of the blanking mouth illuminated by the laser line.

[0056] Second, the RGB image is converted into a single-channel feature map of the same resolution. The detection image is then divided based on macroblocks. The pixel values ​​of the feature map are used to determine whether each macroblock contains laser lines, thereby locating all macroblocks containing laser lines.

[0057] In this embodiment, the specific method of converting the RGB image into a single-channel feature map is:

[0058] A1) Convert the RGB color space image to the HLS color space image and extract the L channel image as I L ; Since the laser line is a brighter area, the brightness channel is extracted to enhance the laser line.

[0059] A2) The red pixel output in the enhanced image is denoted as I R , Among them, R, G, and B are the three channels of the RGB color space image.

[0060] A3) Fusion of brightness channel image I L and red image I R And normalize the pixel value to between 0 and 255, record the feature map F, F = norm (0.2 * I L +0.8*I R ), norm(·) is the normalization function.

[0061] A4) There is noise in the feature map F. The disconnected laser lines are connected through morphological opening and closing operations, and the brightness areas with an area smaller than the set value (in this embodiment, the area is smaller than 7*7 pixels) are removed. This is the noise area, and the final feature map is obtained, as shown in FIG. Figure 3 shown.

[0062] The specific method to locate all macroblocks containing laser lines is:

[0063] B1) Define the size as w m *h m The detection image with a resolution of W*H is evenly divided into m*n macroblocks, where m=W / w m, n=H / h m ,like Figure 4 shown.

[0064] B2) For a macroblock, if the pixel value of the feature map in the macroblock exceeds the set threshold T f If the number of pixels exceeds 50% of the macroblock size, the macroblock is determined to contain laser lines; all macroblocks in the detection image are traversed to determine all macroblocks containing laser lines, and the following is obtained: Figure 5 The macroblock-based laser line positioning result diagram is shown.

[0065] 3. Divide the detection image into four areas: normal working area S1, sticky material and secondary warning area S2, primary warning area S3 and material flow size analysis area S4, and further subdivide each area into multiple sub-areas.

[0066] like Figure 2 As shown, when feeding, the material flow enters the blanking port in a parabolic shape. When the laser line irradiates the blanking port, part of the laser line irradiates the bottom of the blanking port, and part of the laser line directly irradiates the material flow.

[0067] Based on the standard inspection image during normal feeding, mark out the following in the image:

[0068] 1) The rectangular area including all laser lines irradiated on the bottom of the blanking port is defined as the normal working area S1.

[0069] 2) A rectangular area including all laser lines irradiated on the material flow and extending the rectangular area to the edge of the image along the direction of the laser lines is defined as the material flow size analysis area S4.

[0070] 3) The area between area S1 and area S4, which is equal in length to area S1, is divided into the sticky material and secondary warning area S2 and the primary warning area S3.

[0071] After dividing the four regions S1, S2, S3, and S4, each region is further subdivided into multiple sub-regions along its length. In this embodiment, the three regions S1, S2, and S3 are subdivided into 7 sub-regions respectively, and the region S4 is subdivided into 9 sub-regions. Finally, the following is obtained: Figure 6 The image region segmentation result is shown in FIG.

[0072] Fourth, according to the presence of laser lines in each sub-area of ​​each area, the state of the blanking port and the size of the material flow are judged. The state of the blanking port includes excessive dust / smoke concentration, normal feeding, sticking material, secondary blockage, and primary blockage. Figure 7 As shown, the judgment process is:

[0073] C1) Determine whether there are more than F0 sub-regions with laser lines in the S4 region, that is, the number of macroblocks containing laser lines in the sub-region exceeds the set threshold Tr If yes, it is determined to be in feeding state and go to step C3), otherwise go to step C2.

[0074] C2) Determine whether there are laser lines in more than F5 sub-areas of areas S1, S2, and S3. If so, it is determined that the dust / smoke concentration at the drop port is too high, affecting the normal shooting of the camera device, and then remind the site to spray. Otherwise, continue to determine whether there are laser lines in each sub-area of ​​area S1, which means it is determined to be a non-feeding state and then terminate the judgment process. Otherwise, it is determined to be an abnormal state and then terminate the judgment process.

[0075] C3) Determine the material flow size based on the number of sub-areas with laser lines in area S4, and determine whether there are laser lines in each sub-area in area S1. If so, it is determined to be a normal feeding state and the judgment process is terminated. Otherwise, it is determined that there may be sticking or blocking of the material and the process goes to step C4.

[0076] C4) Determine whether there are laser lines in more than F1 sub-areas in area S1. If yes, go to step C5; otherwise, go to step C6.

[0077] C5) Determine whether there are laser lines in more than F2 sub-areas in the S2 area. If so, it is determined to be a material sticking state and the determination process ends. Otherwise, it is determined to be an abnormal state and the determination process ends.

[0078] C6) Determine whether there are laser lines in more than F3 sub-areas in area S2. If so, it is determined to be a secondary blockage state and the determination process ends. Otherwise, go to step C7.

[0079] C7) Determine whether there are laser lines in more than F4 sub-areas in the S3 area. If so, it is determined to be a first-level material blocking state and the determination process is terminated. Otherwise, it is determined to be an abnormal state and the determination process is terminated.

[0080] The above abnormal status may be due to abnormal operation of the entire system, such as abnormal laser line.

[0081] In this embodiment, F0=3, F1=2, F2=1, F3=3, F4=3, and F5=3.

[0082] Preferably, in step C3, when judging the size of the material flow according to the number of sub-regions with laser lines in region S4, it is further judged whether the sub-regions with laser lines in region S4 are continuous. If they are not continuous, it is determined to be an abnormal state.

[0083] In order to avoid the influence of image jitter on the judgment result, k consecutive frames of detection images are obtained and judgment is performed continuously. When the judgment results of the detection images of k consecutive frames are the same, the judgment result is confirmed to be correct and output.

[0084] This embodiment also provides a detection system for the state of a blanking port based on laser line sensing of area division, including a memory, a processor, and computer program instructions stored in the memory and capable of being executed by the processor. When the processor executes the computer program instructions, the above-mentioned method steps can be implemented.

[0085] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0086] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0089] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any other manner. Any person skilled in the art may utilize the above-disclosed technical content to modify or modify the present invention into equivalent embodiments. However, any simple modifications, equivalent variations, and modifications to the above embodiments that do not depart from the technical content of the present invention and are based on the technical essence of the present invention remain within the scope of protection of the present invention.

Claims

1. A method for detecting the blanking opening state based on laser line sensing of area division, characterized in that: include: Acquire the detection image through the camera device, that is, the RGB image of the blanking mouth illuminated by the laser line; Convert the RGB image into a single-channel feature map of the same resolution, then divide the detection image based on macroblocks. Then, determine whether each macroblock contains laser lines based on the pixel values ​​of the feature map, thereby locating all macroblocks containing laser lines. When feeding, the material flow enters the blanking port in a parabolic shape. When the laser line irradiates the blanking port, part of the laser line irradiates the bottom of the blanking port, and part of the laser line irradiates directly on the material flow. Based on the standard inspection image during normal feeding, the following are divided in the image: 1) The rectangular area including all laser lines irradiated on the bottom of the blanking mouth is defined as the normal working area S1; 2) A rectangular area including all laser lines irradiated on the material flow, and extending the rectangular area along the direction of the laser lines to the edge of the image, is defined as the material flow size analysis area S4; 3) The area between area S1 and area S4, which is equal in length to area S1, is divided into the sticky material and secondary warning area S2 and the primary warning area S3; After dividing the four regions S1, S2, S3, and S4, each region is further subdivided into multiple sub-regions along its length; According to the presence of laser lines in each sub-area of ​​each area, the state of the blanking port and the size of the material flow are judged, specifically: C1) Determine whether there are more than F0 sub-regions in the S4 region with laser lines, that is, the number of macroblocks containing laser lines in the sub-region exceeds the set threshold If yes, it is determined to be in feeding state and go to step C3), otherwise go to step C2; C2) Determine whether there are laser lines in more than F5 sub-areas of areas S1, S2, and S3. If so, it is determined that the dust / smoke concentration at the drop port is too high, affecting the normal shooting of the camera device, and then prompts the site to perform spraying. Otherwise, continue to determine whether there are laser lines in each sub-area of ​​area S1. It is determined to be a non-feeding state and then terminate the judgment process. Otherwise, it is determined to be an abnormal state and then terminate the judgment process. C3) Determine the material flow size based on the number of sub-areas with laser lines in area S4, and determine whether laser lines exist in every sub-area in area S1. If so, it is determined to be a normal feeding state and the determination process ends. Otherwise, it is determined that there may be sticking or blocking of the material and the process goes to step C4; C4) Determine whether there are laser lines in more than F1 sub-areas in area S1. If yes, go to step C5; otherwise, go to step C6; C5) Determine whether there are laser lines in more than F2 sub-areas in the S2 area. If so, it is determined to be a material sticking state and the determination process ends. Otherwise, it is determined to be an abnormal state and the determination process ends. C6) Determine whether there are laser lines in more than F3 sub-areas in the S2 area. If so, it is determined to be a secondary blockage state and the determination process ends. Otherwise, go to step C7; C7) Determine whether there are laser lines in more than F4 sub-areas in the S3 area. If so, it is determined to be a first-level material blockage state and the determination process ends. Otherwise, it is determined to be an abnormal state and the determination process ends.

2. The method for detecting the blanking opening state based on laser line sensing of area division according to claim 1 is characterized in that: The specific method of converting an RGB image into a single-channel feature map is: A1) Convert the RGB color space image to the HLS color space image and extract the L channel image as ; Since the laser line is a brighter area, the brightness channel is extracted to enhance the laser line; A2) The output image of red pixels in the enhanced image is denoted by , , where R, G, and B are the three channels of the RGB color space image; A3) Fusion of brightness channel images and red images And normalize the pixel value to between 0 and 255, record the feature map , , norm(·) is the normalization function; A4) Feature Map There is noise in the image. The disconnected laser lines are connected through morphological opening and closing operations, and the noise area smaller than the set area is removed to obtain the final feature map.

3. The method for detecting the blanking opening state based on laser line sensing of area division according to claim 1 is characterized in that: The specific method to locate all macroblocks containing laser lines is: B1) Define the size as Rectangular macroblocks with a resolution of The detection image is evenly divided into m*n macroblocks, where , ; B2) For a macroblock, if the pixel value of the feature map in the macroblock exceeds the set threshold T f If the number of pixels exceeds 50% of the macroblock size, the macroblock is determined to contain laser lines; all macroblocks in the detection image are traversed to determine all macroblocks containing laser lines.

4. The method for detecting the blanking opening state based on laser line sensing of area division according to claim 1 is characterized in that: The three areas S1, S2 and S3 are divided into 7 sub-areas respectively, and the S4 area is divided into 9 sub-areas.

5. The method for detecting the blanking opening state based on laser line sensing of area division according to claim 1 is characterized in that: F0=3, F1=2, F2=1, F3=3, F4=3, F5=3.

6. The method for detecting the blanking opening state based on laser line sensing based on area division according to claim 1 is characterized in that: In step C3, when judging the material flow size according to the number of sub-regions with laser lines in region S4, it is further judged whether the sub-regions with laser lines in region S4 are continuous. If they are not continuous, it is determined to be an abnormal state.

7. The method for detecting the blanking opening state based on laser line sensing based on area division according to claim 1 is characterized in that: Obtain k consecutive frames of detection images and perform judgments continuously. When the judgment results of the k consecutive frames of detection images are the same, confirm that the judgment result is correct and output it.

8. A laser line sensing system for detecting the blanking opening state based on area division, characterized in that: The method comprises a memory, a processor, and computer program instructions stored in the memory and capable of being executed by the processor. When the processor executes the computer program instructions, the method according to any one of claims 1 to 7 can be implemented.

Images