Conveyor belt object posture detection system and method
The camera takes images of the occlusion of components on the conveyor belt with specific colors, analyzes the posture of objects, and solves the problems of increasing cost and space occupation of multiple sensors in the prior art, achieving accurate detection and flexibility improvements.
Patent Information
- Application Number
- CN202111053078.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-09-08
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2041-09-08
AI Technical Summary
The existing conveyor belt item attitude detection system requires the installation of multiple sensors, which increases cost and space occupation, and is not flexible enough to adapt to item size changes.
The camera is used to capture images that indicate the occlusion of components on the conveyor belt, and determine the posture of the item through the host analysis of the image, reducing cost and space occupation, and improving flexibility.
It realizes accurate detection of item posture, reduces investment costs, saves space, and is suitable for the detection of multi-size items, improving the flexibility of the system.
Smart Images

Figure CN113686300B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of conveyors, and in particular to a conveyor belt article posture detection system and method. Background Art
[0002] When using a conveyor belt to transport items, it is usually necessary to detect the posture of the items (center position and tilt angle) to ensure that the items can be transported along the expected trajectory. For example, if the items need to be sealed during the transportation process, in addition to ensuring that the center position of the items is at the predetermined position, it is also necessary to ensure that the opening position of the items is aligned with the sealing device position.
[0003] Currently, sensors are usually used to detect the position and angle of items on the conveyor belt. This method has the following defects:
[0004] 1. In order to ensure the detection accuracy, multiple sensors need to be installed, which increases the investment cost and installation space;
[0005] 2. If the size of the object being transported changes, the sensor installation position needs to be adjusted, which results in low flexibility.
[0006] Therefore, there is an urgent need for a conveyor belt object posture detection system and method to reduce investment costs, reduce space waste and improve flexibility. Summary of the invention
[0007] In view of the above, it is necessary to provide a conveyor belt object posture detection system and method, aiming to reduce investment costs, reduce space waste and improve flexibility.
[0008] To achieve the above object, the present invention provides a conveyor belt object posture detection system, the conveyor belt object posture detection system comprising a host, a camera, a belt conveyor with a conveyor belt, and specific color schematic components arranged on both sides of the conveyor belt and parallel to the conveyor belt, wherein:
[0009] The conveyor belt is used to convey items;
[0010] The camera is used to capture a first image of a situation in which the conveyed object blocks the specific color indicating component;
[0011] The host is used to determine whether the posture of the object is correct according to the first image.
[0012] Optionally, the specific color is a first color, the color of the conveyed object is a second color, and the color difference between the first color and the second color is within a preset color difference range.
[0013] Optionally, a lateral spacing distance between the specific color schematic component and the conveyor belt is within a preset spacing distance range, and a width of the specific color schematic component is within a preset width range.
[0014] Optionally, a first position point and a second position point are marked on the fixed outer frame of the conveyor belt, the first position point is the position point where the camera shooting ends, and the second position point is the position point where the host executes corresponding measures according to the posture of the object.
[0015] Optionally, the length of the specific color indicating component is greater than the length of the object to be conveyed, and the end point of the specific color indicating component is flush with the first position point, or exceeds the first position point.
[0016] To achieve the above object, the present invention further provides a conveyor belt object posture detection system, the conveyor belt object posture detection system comprises a host, a camera and a belt conveyor with a conveyor belt, the conveyor belt comprises a standard conveying area and specific color schematic areas respectively distributed on the left and right sides of the standard conveying area, wherein:
[0017] The conveyor belt is used to convey items;
[0018] The camera is used to capture a first image of a situation in which a conveyed object blocks a specific color indicated area on the conveyor belt;
[0019] The host is used to determine whether the posture of the object is correct according to the first image.
[0020] Optionally, the specific color is a first color, the color of the conveyed object is a second color, and the color difference between the first color and the second color is within a preset color difference range.
[0021] Optionally, the width of the specific color schematic area is within a preset width range.
[0022] Optionally, a first position point and a second position point are marked on the fixed outer frame of the conveyor belt, the first position point is the position point where the camera shooting ends, and the second position point is the position point where the host executes corresponding measures according to the posture of the object.
[0023] To achieve the above object, the present invention further provides a conveyor belt object posture detection method, which is applied to the above conveyor belt object posture detection system. The conveyor belt object posture detection method comprises:
[0024] Controlling the camera to capture a first image of the occlusion of the specific color schematic component or the specific color schematic area by the transported object;
[0025] Determine whether the posture of the object is correct according to the first image.
[0026] Optionally, when the transported object passes through the first position point, the shooting is terminated, and when the transported object passes through the second position point, corresponding measures are performed according to the posture of the object.
[0027] Optionally, determining whether the posture of the object is correct according to the first image includes:
[0028] Obtaining vertex coordinates of an outer edge of a specific color schematic component or a specific color schematic region in the first image;
[0029] Converting the first image into a second image from a top-down perspective according to the acquired vertex coordinates;
[0030] analyzing the intersection of the object conveyed in the second image with the specific color schematic component or the specific color schematic area;
[0031] Whether the posture of the object is correct is determined according to the intersection condition.
[0032] Optionally, if the intersection condition is that the conveyed object intersects with the specific color schematic component or the specific color schematic area and does not extend outside the specific color schematic component or the specific color schematic area, determining whether the posture of the object is correct according to the intersection condition includes:
[0033] Acquire an intersection area between the object conveyed in the second image and the specific color schematic component or the specific color schematic area;
[0034] Determine the center position and tilt angle of the conveyed object according to the intersection area;
[0035] Determine whether the distance difference between the center position and the standard position is greater than a distance threshold, and determine whether the angle difference between the tilt angle and the standard angle is greater than an angle threshold;
[0036] If the distance difference is judged to be greater than the distance threshold, or the angle difference is judged to be greater than the angle threshold, it is determined that the posture of the object is wrong.
[0037] Optionally, if the intersection situation is that the conveyed object does not intersect with the specific color schematic component or the specific color schematic area, it is determined that the posture of the object is correct.
[0038] Optionally, if the intersection situation is that the conveyed object intersects with the specific color schematic component or the specific color schematic area and extends outside the specific color schematic component or the specific color schematic area, it is determined that the posture of the object is wrong.
[0039] Compared with the prior art, the present invention uses a camera to capture a first image of the occlusion of a specific color schematic component or a specific color schematic area by a transmitted object, and determines whether the posture of the object is correct based on the first image, which reduces investment costs, saves space, is suitable for posture detection of objects of multiple sizes, and improves flexibility. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1It is a structural schematic diagram of a first embodiment of a conveyor belt object posture detection system of the present invention;
[0041] Figure 2 It is a schematic structural diagram of the second embodiment of the conveyor belt object posture detection system of the present invention. DETAILED DESCRIPTION
[0042] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0043] It should be noted that the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.
[0044] like Figure 1 FIG. 1 is a schematic diagram of the structure of the first embodiment of the conveyor belt object posture detection system of the present invention. In this embodiment, the conveyor belt object posture detection system 100 includes a host 1, a camera 2, a belt conveyor with a conveyor belt 3, and specific color schematic components 4 arranged on both sides of the conveyor belt 3 and parallel to the conveyor belt 3, wherein:
[0045] The conveyor belt 3 is used to convey objects 5;
[0046] The camera 2 is used to capture a first image of the occlusion of the specific color indicating component 4 by the conveyed object 5;
[0047] The host 1 is used to determine whether the posture of the object 5 is correct according to the first image.
[0048] In this embodiment, the belt conveyor conveys the article 5 to a predetermined position via the conveyor belt 3, and the specific color indicating component 4 may be a bar-shaped table with a fixed position.
[0049] The specific color is a first color, the color of the conveyed object 5 is a second color, and the color difference between the first color and the second color is within a preset color difference range (for example, greater than 12).
[0050] To prevent the conveyed items 5 from colliding with or rubbing against the specific color indicating component 4 and falling into the gap between the specific color indicating component 4 and the conveyor belt 3, the lateral spacing distance between the specific color indicating component 4 and the conveyor belt 3 is within a preset spacing distance range (e.g., 0.5 cm to 3.5 cm).
[0051] The width of the specific color schematic component 4 is within a preset width range (for example, 10 cm to 20 cm). If it is too narrow, it will be difficult to analyze the occlusion of the specific color schematic component 4 by the object 5 in the first image; if it is too large, it will waste resources and increase the amount of analysis data and analysis time.
[0052] In this embodiment, a first position point L1 and a second position point L2 are marked on the fixed outer frame of the conveyor belt 3 (the position of the outer frame of the conveyor belt 3 is fixed and does not move with the conveyance of the conveyor belt 3). The first position point L1 is the end position point of the shooting of the camera 2. If a photo is taken, it can be taken when the object 5 is conveyed to L1; if a video is taken, the shooting can be started when the object 5 enters the starting point of the specific color indication component 4, and the shooting can be stopped when the object 5 passes through L1.
[0053] The second position point L2 is the position point where the host 1 performs corresponding measures according to the posture of the object 5, that is, point L2 is a decision point. In the application scenario, a packaging device may be placed after L2. If the posture of the object 5 is analyzed incorrectly, corresponding measures need to be performed at L2, for example, stopping the conveyor belt 3, or using other tools to pick up the object 5. Therefore, the time length for analyzing the first image should be less than or equal to the time for the object 5 to be transferred from L1 to L2. Thus, the positions of L1 and L2 can be calculated. First, a specific position point (for example, the position before the packaging device) is set to L2, and the analysis time of the first image is determined. L1 can be calculated based on the conveying speed of the conveyor belt 3 and the analysis time.
[0054] The length of the specific color schematic component 4 is greater than the length of the conveyed object 5, and the end point of the specific color schematic component 4 is flush with the first position point L1, or exceeds the first position point L1. This requirement ensures that the first image must include the object 5 and the specific color schematic component 4, which facilitates subsequent analysis.
[0055] Preferably, the color of the specific color indicating component 4 can be a conspicuous solid color (for example, red), which can reduce the difficulty of image recognition and the requirements for the color of the transmitted object 5 (as long as the color of the object 5 is not similar to the color of the specific color indicating component 4); at the same time, because the color of the specific color indicating component 4 is conspicuous, the image analysis time can be reduced, making it suitable for projects with short transmission channels.
[0056] like Figure 2, which is a schematic diagram of the structure of the second embodiment of the conveyor belt object posture detection system of the present invention. The conveyor belt object posture detection system 200 comprises a host 1, a camera 2 and a belt conveyor with a conveyor belt 30, wherein the conveyor belt 30 comprises a standard conveying area 31 and specific color schematic areas 32 respectively distributed on the left and right sides of the standard conveying area 31, wherein:
[0057] The conveyor belt 30 is used to convey the article 5;
[0058] The camera 2 is used to capture a first image of the situation where the conveyed object 5 blocks the specific color schematic area 32 on the conveyor belt 30;
[0059] The host 1 is used to determine whether the posture of the object 5 is correct according to the first image.
[0060] Different from the first embodiment, in this embodiment, the specific color schematic area 32 is a part of the conveyor belt 30 .
[0061] The specific color is a first color, the color of the conveyed object 5 is a second color, and the color difference between the first color and the second color is within a preset color difference range (for example, greater than 12).
[0062] The width of the specific color schematic area 32 is within a preset width range (for example, 10 cm to 20 cm). If it is too narrow, it will be difficult to analyze the occlusion of the specific color schematic area 32 by the object 5 in the first image; if it is too large, it will waste resources and increase the amount of analysis data and analysis time.
[0063] In this embodiment, a first position point L1 and a second position point L2 are marked on the fixed outer frame of the conveyor belt 30 (the position of the outer frame of the conveyor belt 30 is fixed and does not move with the conveyance of the conveyor belt 30). The first position point L1 is the end position point of the shooting of the camera 2. If a photo is taken, it can be taken when the object 5 is conveyed to L1; if a video is taken, the shooting can be started when the object 5 enters the starting point of the specific color schematic area 32, and the shooting can be stopped when the object 5 passes through L1.
[0064] The second position point L2 is the position point where the host 1 performs corresponding measures according to the posture of the object 5, that is, point L2 is a decision point. In the application scenario, a packaging device may be placed after L2. If the posture of the object 5 is analyzed incorrectly, corresponding measures need to be performed at L2, for example, stopping the conveyor belt 3, or using other tools to pick up the object 5. Therefore, the time length for analyzing the first image should be less than or equal to the time for the object 5 to be transferred from L1 to L2. Thus, the positions of L1 and L2 can be calculated. First, a specific position point (for example, the position before the packaging device) is set to L2, and the analysis time of the first image is determined. L1 can be calculated according to the conveying speed of the conveyor belt 30 and the analysis time.
[0065] Preferably, the color of the specific color schematic area 32 can be a conspicuous solid color (for example, red), which can reduce the difficulty of image recognition and the requirements for the color of the transmitted object 5 (as long as the color of the object 5 is not similar to the color of the specific color schematic area 32); at the same time, because the color of the specific color schematic area 32 is conspicuous, the image analysis time can be reduced, making it suitable for projects with short transmission channels.
[0066] The present invention further provides a conveyor belt article posture detection method, which is applied to the above-mentioned conveyor belt article posture detection system 100 or conveyor belt article posture detection system 200, and the conveyor belt article posture detection method comprises:
[0067] S1, controlling the camera 2 to capture a first image of the occlusion of the specific color schematic component 4 or the specific color schematic area 32 by the transported object 5;
[0068] S2. Determine whether the posture of the object 5 is correct according to the first image.
[0069] In this embodiment, when the transported object 5 passes through the first position point L1 , the shooting is terminated, and when the transported object 5 passes through the second position point L2 , corresponding measures are executed according to the posture of the object 5 .
[0070] The determining whether the posture of the object 5 is correct according to the first image includes:
[0071] A1, obtaining vertex coordinates of the outer side of the specific color schematic component 4 or the specific color schematic area 32 in the first image;
[0072] In this embodiment, the outline of the specific color schematic component 4 or the specific color schematic area 32 is obtained by scanning the first image. The scanning can be performed in the horizontal and vertical directions respectively to find the area of the specific color, and the boundary coordinates are recorded. Then, based on the shape of the specific color schematic component 4 or the specific color schematic area 32 itself, the boundary coordinates are further confirmed. For example, if the specific color schematic component 4 or the specific color schematic area 32 is a rectangle, the least squares method can be used to determine the straight line where the outer edge is located. Based on the straight line, the coordinates of the two vertices of the outer edge of the specific color schematic component 4 or the specific color schematic area 32 can be obtained.
[0073] A2, converting the first image into a second image of a top-down perspective according to the acquired vertex coordinates;
[0074] The relative positions of the four vertex coordinates of the specific color schematic component 4 or the specific color schematic area 32 are fixed. For example, if the coordinates of the upper left vertex are known, the coordinates of the other three vertices can be calculated. In step A1, the coordinates of the two vertices of the outer side of the specific color schematic component 4 or the specific color schematic area 32 in the first image have been determined. According to the two vertex coordinates, the first image can be converted into a second image of the upper perspective.
[0075] A3, analyzing the intersection of the object 5 transmitted in the second image and the specific color schematic component 4 or the specific color schematic area 32;
[0076] In the second image from the top perspective, if the transported object 5 does not block the specific color schematic component 4 or the specific color schematic area 32, the inner edge line of the specific color schematic component 4 or the specific color schematic area 32 is fixed; if there is blockage, the inner edge line will move outward; if the specific color schematic component 4 or the specific color schematic area 32 is cut off in the second image, it means that the object 5 has extended beyond the specific color schematic component 4 or the specific color schematic area 32.
[0077] A4. Determine whether the posture of the object 5 is correct according to the intersection condition.
[0078] In this embodiment, if the intersection situation is that the conveyed object 5 intersects with the specific color schematic component 4 or the specific color schematic area 32 and does not extend outside the specific color schematic component 4 or the specific color schematic area 32, the determining whether the posture of the object 5 is correct according to the intersection situation includes:
[0079] B1, obtaining the intersection area between the object 5 conveyed in the second image and the specific color schematic component 4 or the specific color schematic area 32;
[0080] The intersection area between the conveyed object 5 and the specific color indicating component 4 or the specific color indicating area 32 can be determined according to the areas of the first color and the second color in the second image.
[0081] B2. Determine the center position and inclination angle of the conveyed object 5 according to the intersection area;
[0082] The boundary coordinates of the intersection area can be used to obtain the boundary straight line and the intersection coordinates using the least squares method, and then the angle between the boundary straight line and the outer line of the specific color schematic component 4 or the specific color schematic area 32 can be calculated, which is the inclination angle.
[0083] According to the boundary straight line, the intersection of the straight lines, and the size of the object 5, the coordinates of the other two diagonal vertices of the object 5 can be calculated, and the midpoint of the line connecting the diagonal vertices is the center position of the object 5.
[0084] B3, judging whether the distance difference between the center position and the standard position is greater than a distance threshold, and judging whether the angle difference between the tilt angle and the standard angle is greater than an angle threshold;
[0085] The standard position may be the center line of the specific color schematic component 4 or the specific color schematic area 32, and the standard angle may be the position angle corresponding to the packaging device. The distance threshold and the angle threshold may be set specifically according to the application scenario, and are not limited here.
[0086] B4. If the distance difference is greater than the distance threshold, or the angle difference is greater than the angle threshold, it is determined that the posture of the object 5 is wrong.
[0087] If the distance difference is greater than the distance threshold, or the angle difference is greater than the angle threshold, it means that the posture of the object 5 is wrong.
[0088] In this embodiment, if the intersection situation is that the transported object 5 does not intersect with the specific color schematic component 4 or the specific color schematic area 32, it means that the posture of the object 5 is correct; if the intersection situation is that the transported object 5 intersects with the specific color schematic component 4 or the specific color schematic area 32 and extends outside the specific color schematic component 4 or the specific color schematic area 32, it means that the posture of the object 5 is wrong.
[0089] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A conveyor belt object posture detection system, characterized in that: The conveyor belt object posture detection system comprises a host, a camera, a belt conveyor with a conveyor belt, and specific color-coded components arranged on both sides of the conveyor belt and parallel to the conveyor belt, wherein: The conveyor belt is used to convey items; The camera is used to capture a first image of a situation in which the conveyed object blocks the specific color indicating component; The host is used to analyze the intersection of the object and the specific color schematic component according to the first image, and determine whether the posture of the object is correct according to the intersection.
2. The conveyor belt object posture detection system according to claim 1, characterized in that: The specific color is a first color, the color of the transmitted object is a second color, and the color difference between the first color and the second color is within a preset color difference range.
3. The conveyor belt object posture detection system according to claim 1, characterized in that: The lateral spacing distance between the specific color schematic component and the conveyor belt is within a preset spacing distance range, and the width of the specific color schematic component is within a preset width range.
4. The conveyor belt object posture detection system according to claim 1, characterized in that: The fixed outer frame of the conveyor belt is marked with a first position point and a second position point, the first position point is the position point where the camera ends shooting, and the second position point is the position point where the host executes corresponding measures according to the posture of the object.
5. The conveyor belt article posture detection system according to claim 4, characterized in that: The length of the specific color indicating component is greater than the length of the conveyed object, and the end point of the specific color indicating component is flush with the first position point, or exceeds the first position point.
6. A conveyor belt object posture detection system, characterized in that: The conveyor belt object posture detection system includes a host, a camera and a belt conveyor with a conveyor belt, wherein the conveyor belt includes a standard conveying area and specific color schematic areas respectively distributed on the left and right sides of the standard conveying area, wherein: The conveyor belt is used to convey items; The camera is used to capture a first image of a situation in which a conveyed object blocks a specific color indicated area on the conveyor belt; The host is used to analyze the intersection of the object and the specific color schematic component according to the first image, and determine whether the posture of the object is correct according to the intersection.
7. The conveyor belt article posture detection system according to claim 6, characterized in that: The specific color is a first color, the color of the transmitted object is a second color, and the color difference between the first color and the second color is within a preset color difference range.
8. The conveyor belt article posture detection system according to claim 6, characterized in that: The width of the specific color schematic area is within a preset width range.
9. The conveyor belt article posture detection system according to claim 6, characterized in that: The fixed outer frame of the conveyor belt is marked with a first position point and a second position point, the first position point is the position point where the camera ends shooting, and the second position point is the position point where the host executes corresponding measures according to the posture of the object.
10. A method for detecting the posture of an object on a conveyor belt, applied to the system for detecting the posture of an object on a conveyor belt as claimed in any one of claims 1 to 9, characterized in that: The conveyor belt object posture detection method comprises: Controlling the camera to capture a first image of the occlusion of the specific color schematic component or the specific color schematic area by the transported object; The intersection between the object and the specific color schematic component or the specific color schematic area is analyzed according to the first image, and whether the posture of the object is correct is determined according to the intersection.
11. The method for detecting the posture of an object on a conveyor belt according to claim 10, wherein: When the transported object passes through the first position point, the shooting is ended, and when the transported object passes through the second position point, corresponding measures are executed according to the posture of the object.
12. The method for detecting the posture of an object on a conveyor belt according to claim 10, wherein: The step of analyzing the intersection of the object and the specific color schematic component or the specific color schematic area according to the first image includes: Obtaining vertex coordinates of an outer edge of a specific color schematic component or a specific color schematic region in the first image; Converting the first image into a second image from a top-down perspective according to the acquired vertex coordinates; The intersection of the conveyed object in the second image with the specific color-indicating component or the specific color-indicating area is analyzed.
13. The method for detecting the posture of an object on a conveyor belt according to claim 12, wherein: If the intersection condition is that the conveyed object intersects with the specific color schematic component or the specific color schematic area and does not extend beyond the specific color schematic component or the specific color schematic area, determining whether the posture of the object is correct according to the intersection condition includes: Acquire an intersection area between the object conveyed in the second image and the specific color schematic component or the specific color schematic area; Determine the center position and tilt angle of the conveyed object according to the intersection area; Determine whether the distance difference between the center position and the standard position is greater than a distance threshold, and determine whether the angle difference between the tilt angle and the standard angle is greater than an angle threshold; If the distance difference is judged to be greater than the distance threshold, or the angle difference is judged to be greater than the angle threshold, it is determined that the posture of the object is wrong.
14. The method for detecting the posture of an object on a conveyor belt according to claim 12, wherein: If the intersection situation is that the conveyed object does not intersect with the specific color indicating component or the specific color indicating area, it is determined that the posture of the object is correct.
15. The method for detecting the posture of an object on a conveyor belt according to claim 12, wherein: If the intersection situation is that the conveyed object intersects with the specific color schematic component or the specific color schematic area and extends outside the specific color schematic component or the specific color schematic area, it is determined that the posture of the object is wrong.
