A beverage filling bottle mouth positioning method, device and system based on machine vision

Abstract

The present invention discloses a method, device and system for positioning the mouth of a beverage filling bottle based on machine vision, the method comprising collecting a bottom image of a bottle to be filled; determining the center point position corresponding to the bottom contour shape of the bottle to be filled from the bottom image; determining the actual position information of the bottle to be filled in a preset plane coordinate axis corresponding to the bottom image based on the center point position; judging whether the center point position coincides with the center point position of the mouth of the bottle to be filled on the preset plane coordinate axis; if so, determining the real-time mouth position of the bottle to be filled when the bottle to be filled is filled based on the actual position information. The present invention can improve the image operation processing efficiency and recognition accuracy, reduce the complexity of the machine vision algorithm and reduce the complexity of image processing, thereby avoiding the consumption of a large amount of computing resources and excessive precise parameter adjustments.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a beverage filling bottle mouth positioning method, device and system based on machine vision. Background Art

[0002] Beverage bottles usually refer to containers used to package various beverages, and beverages are liquids for human consumption, including tea, coffee, juice, soda, mineral water, etc. Bottled beverages are mainly prepared by filling machines into beverage bottles, which are then packaged and sold.

[0003] In modern large-scale high-speed beverage filling production lines, the position of the bottle mouth needs to be accurately positioned to achieve filling of the bottle body. However, the positioning devices on the existing production lines are mainly mechanical positioning, which has low accuracy and slow positioning speed, and cannot meet the requirements of modern high-speed automated beverage filling production lines. The bottle mouth positioning method based on machine vision has the characteristics of high speed, high precision and high intelligence. It not only increases the flexibility and automation of production, but also greatly improves the intelligence and versatility of production, and therefore has received more and more attention.

[0004] However, the existing bottle mouth positioning methods based on machine vision are all based on direct detection based on images containing the bottle mouth. Due to the noisy environment of the image acquisition site, large light interference and the structural characteristics of the bottle mouth, the acquired images will contain a lot of noise, resulting in increased complexity of subsequent image processing and machine vision algorithms, resulting in a large amount of computing resources and too many precise parameter adjustments. Summary of the invention

[0005] In order to solve at least one of the above-mentioned technical problems, the present invention provides a beverage filling bottle mouth positioning method, device and system based on machine vision.

[0006] In a first aspect, the present invention provides a method for locating a beverage filling bottle mouth based on machine vision, the method comprising:

[0007] Collect the bottom image of the bottle to be filled;

[0008] Determine the center point position corresponding to the bottom contour shape of the bottle to be filled from the bottom image;

[0009] Based on the position of the center point, determining the actual position information of the bottle to be filled in the preset plane coordinate axis corresponding to the bottom image;

[0010] Determining whether the center point position coincides with the center point position of the bottle mouth of the to-be-filled bottle body on the preset plane coordinate axis comprises: querying the bottle mouth positioning scheme corresponding to the to-be-filled bottle body in a preset bottle mouth positioning scheme database; wherein the bottle mouth positioning scheme comprises a first positioning scheme and a second positioning scheme; when the bottle mouth positioning scheme is the first positioning scheme, the center point position coincides with the center point position of the bottle mouth of the to-be-filled bottle body on the preset plane coordinate axis; when the bottle mouth positioning scheme is the second positioning scheme, the center point position does not coincide with the center point position of the bottle mouth of the to-be-filled bottle body on the preset plane coordinate axis; wherein querying the bottle mouth positioning scheme corresponding to the to-be-filled bottle body in a preset bottle mouth positioning scheme database comprises: constructing a three-dimensional map of the to-be-filled bottle body; based on the A three-dimensional graph is used to obtain the bottom contour shape information and bottle mouth information of the bottle to be filled; wherein, the bottom contour shape information includes the bottom contour shape and the center point position of the bottom contour shape, and the bottle mouth information includes one or more of the inner diameter of the bottle mouth, the outer diameter of the bottle mouth, the center point position of the bottle mouth, the height of the center point of the bottle mouth, the direction of the bottle mouth and the inclination of the bottle mouth; if the inclination of the bottle mouth is 0°, and the center point position of the bottom contour shape and the center point position of the bottle mouth of the bottle to be filled are on the same vertical line, it is determined that the bottle mouth positioning scheme corresponding to the bottle to be filled is the first positioning scheme; if the inclination of the bottle mouth is 0°, and the center point position of the bottom contour shape and the center point position of the bottle mouth of the bottle to be filled are not on the same vertical line, it is determined that the bottle mouth positioning scheme corresponding to the bottle to be filled is the second positioning scheme;

[0011] If yes, based on the actual position information, determine the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled;

[0012] If not, collect the top image of the bottle to be filled, determine the target area where the bottle mouth of the bottle to be filled is located from the top image, and map the position of the target area in the preset plane coordinate axis to determine the quadrant position where the bottle mouth of the bottle to be filled is located, and determine the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled according to the quadrant position and the actual position information;

[0013] Wherein, determining the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled includes:

[0014] Obtaining the current conveying speed of the conveying device where the bottle to be filled is located; wherein the conveying device is used to convey the bottle to be filled through the filling area to the next process;

[0015] Determine the actual position information as the current position of the mouth of the bottle to be filled; or determine the current position of the mouth of the bottle to be filled according to the quadrant position and the actual position information;

[0016] According to the current position of the bottle mouth and the current conveying speed, the real-time position of the bottle mouth of the bottle to be filled is obtained when the bottle to be filled is filled.

[0017] Preferably, based on the position of the center point, determining the actual position information of the bottle to be filled in the preset plane coordinate axis corresponding to the bottom image includes:

[0018] Acquire a standard bottom image corresponding to the bottle to be filled;

[0019] Determining the standard center point position corresponding to the bottom contour shape of the bottle to be filled from the standard bottom image;

[0020] Taking the standard center point position as the origin, establishing a plane coordinate axis in the standard bottom image to obtain the preset plane coordinate axis;

[0021] Mapping the center point position in the preset plane coordinate axis to determine the coordinate position of the center point position;

[0022] Determine the offset distance of the bottle to be filled based on the coordinate position;

[0023] The actual position information of the bottle to be filled is determined based on the offset distance.

[0024] Preferably, collecting the bottom image of the bottle to be filled includes:

[0025] Arrange the scene based on the color, size and height of the bottle to be filled, so as to enhance the contour shape of the bottle to be filled in the image;

[0026] Install a shooting device directly below the arranged scene, and adjust the shooting direction of the shooting device;

[0027] After the bottle to be filled is detected, the photographing device is controlled to photograph the bottle to be filled from the bottom of the bottle to be filled along the top direction of the bottle to be filled to obtain a bottom image of the bottle to be filled.

[0028] Preferably, it also includes:

[0029] Based on the real-time bottle mouth position, control the filling device to execute a filling method corresponding to a preset filling scheme to fill the bottle to be filled; wherein the filling method includes intermittent filling and continuous filling;

[0030] When the filling method is the intermittent filling, the real-time bottle mouth position remains unchanged, and when the bottle mouth of the bottle to be filled reaches the real-time bottle mouth position, the conveying device is controlled to stop conveying, the filling port of the filling device is adjusted to the real-time bottle mouth position, and the filling device is driven to fill the bottle to be filled, until the filling work is completed, the conveying work of the conveying device is resumed, and the filling port of the filling device is reset;

[0031] When the filling mode is the continuous filling, the conveying device continuously performs the conveying work, and dynamically updates the real-time bottle mouth position based on the current speed of the conveying device, and when the bottle mouth of the bottle to be filled reaches the real-time bottle mouth position, the filling port of the filling device is moved to the real-time bottle mouth position, and the filling port of the filling device is synchronously moved according to the current speed of the conveying device, so that the filling port of the filling device is always in the real-time bottle mouth position, and the filling device is driven to fill the bottle to be filled, until the filling work is completed, and the filling port of the filling device is moved again to the real-time bottle mouth position of the next bottle to be filled.

[0032] In a second aspect, the present invention further provides a beverage filling bottle mouth positioning device based on machine vision, the device comprising:

[0033] A collection module, used to collect the bottom image of the bottle to be filled;

[0034] A first determination module is used to determine the center point position corresponding to the bottom contour shape of the bottle to be filled from the bottom image;

[0035] A second determination module is used to determine the actual position information of the bottle to be filled in the preset plane coordinate axis corresponding to the bottom image based on the position of the center point;

[0036] A judgment module, for judging whether the center point position and the center point position of the bottle mouth of the bottle to be filled coincide on the preset plane coordinate axis, comprising: querying the bottle mouth positioning scheme corresponding to the bottle to be filled in a preset bottle mouth positioning scheme database; wherein the bottle mouth positioning scheme comprises a first positioning scheme and a second positioning scheme; when the bottle mouth positioning scheme is the first positioning scheme, the center point position and the center point position of the bottle mouth of the bottle to be filled coincide on the preset plane coordinate axis; when the bottle mouth positioning scheme is the second positioning scheme, the center point position and the center point position of the bottle mouth of the bottle to be filled do not coincide on the preset plane coordinate axis; wherein querying the bottle mouth positioning scheme corresponding to the bottle to be filled in a preset bottle mouth positioning scheme database comprises: constructing a three-dimensional map of the bottle to be filled; Based on the three-dimensional graph, the bottom contour shape information and the bottle mouth information of the bottle to be filled are obtained; wherein, the bottom contour shape information includes the bottom contour shape and the center point position of the bottom contour shape, and the bottle mouth information includes one or more of the inner diameter of the bottle mouth, the outer diameter of the bottle mouth, the center point position of the bottle mouth, the height of the center point of the bottle mouth, the direction of the bottle mouth and the inclination of the bottle mouth; if the inclination of the bottle mouth is 0°, and the center point position of the bottom contour shape and the center point position of the bottle mouth of the bottle to be filled are on the same vertical line, it is determined that the bottle mouth positioning scheme corresponding to the bottle to be filled is the first positioning scheme; if the inclination of the bottle mouth is 0°, and the center point position of the bottom contour shape and the center point position of the bottle mouth of the bottle to be filled are not on the same vertical line, it is determined that the bottle mouth positioning scheme corresponding to the bottle to be filled is the second positioning scheme;

[0037] A third determination module is used to determine the position of the bottle mouth of the bottle to be filled when filling the bottle to be filled based on the reference bottle mouth center point position corresponding to the bottle to be filled and the actual position information when the center point position coincides with the bottle mouth center point position of the bottle to be filled on the preset plane coordinate axis;

[0038] a fourth determination module, configured to, when the center point position and the center point position of the bottle mouth of the bottle to be filled do not coincide on the preset plane coordinate axis, collect a top image of the bottle to be filled, determine a mapping position of the bottle mouth of the bottle to be filled in the preset plane coordinate axis based on the top image, and determine a position of the bottle mouth of the bottle to be filled when filling the bottle to be filled based on the mapping position;

[0039] Wherein, determining the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled includes:

[0040] Obtaining the current conveying speed of the conveying device where the bottle to be filled is located; wherein the conveying device is used to convey the bottle to be filled through the filling area to the next process;

[0041] Determine the actual position information as the current position of the mouth of the bottle to be filled; or determine the current position of the mouth of the bottle to be filled according to the quadrant position and the actual position information;

[0042] According to the current position of the bottle mouth and the current conveying speed, the real-time position of the bottle mouth of the bottle to be filled is obtained when the bottle to be filled is filled.

[0043] In a third aspect, the present invention further provides a beverage filling bottle mouth positioning system based on machine vision, the system comprising:

[0044] A beverage filling bottle mouth positioning device based on machine vision as described above;

[0045] A conveying device, used to convey the bottles to be filled through the filling area to the next process;

[0046] At least two photographing devices, the two photographing devices are respectively arranged above and below the conveying device, and the two photographing devices are arranged at an interval, and the photographing devices are used to take images of the bottles to be filled to obtain bottom images and top images;

[0047] A filling device, arranged on one side of the conveying device, and used for filling the bottles to be filled in the filling area;

[0048] A handling device is slidably mounted on the conveying device, and is used to dynamically handle the filling port of the filling device to the real-time bottle mouth position in the filling area according to the real-time bottle mouth position obtained based on the detection results of the bottom image and the top image.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] 1) The beverage filling bottle mouth positioning method based on machine vision provided by the present invention first collects the bottom image of the bottle body to be filled, and determines the center point position corresponding to the bottom contour shape of the bottle body to be filled from the bottom image; then based on the center point position, determines the actual position information of the bottle body to be filled in the preset plane coordinate axis corresponding to the bottom image; the present invention determines the actual position information of the bottle body to be filled based on the bottom image of the bottle body to be filled, and then determines the real-time position of the bottle mouth, without directly performing the real-time position recognition and analysis of the bottle mouth from the image, and because the bottom image is more convenient for contour shape and center point position processing than the top image, it can reduce interference information in image processing and reduce the complexity of image processing, thereby improving the image operation processing efficiency and recognition accuracy, reducing the complexity of the machine vision algorithm, thereby avoiding consuming a large amount of computing resources and performing too many precise parameter adjustments.

[0051] 2) After obtaining the actual position information of the bottle to be filled, by judging whether the center point position coincides with the center point position of the bottle mouth of the bottle to be filled on the preset plane coordinate axis, the real-time bottle mouth position of the bottle to be filled is analyzed and processed accordingly according to the judgment result, thereby avoiding consuming a large amount of computing resources and making too many precise parameter adjustments, and further improving the image processing efficiency, recognition accuracy and equipment working energy efficiency.

[0052] 3) If the judgment result is overlap, the real-time bottle mouth position of the bottle to be filled can be determined according to the actual position information when the bottle to be filled is filled, without further processing the image, thus avoiding the consumption of a large amount of computing resources and too many precise parameter adjustments, thereby improving the image processing efficiency, recognition accuracy, equipment working energy efficiency and production efficiency.

[0053] 4) If the judgment result is that there is no overlap, the top image of the bottle to be filled is collected, and the target area where the bottle mouth of the bottle to be filled is located is determined from the top image, and the position of the target area is mapped in the preset plane coordinate axis to determine the quadrant position where the bottle mouth of the bottle to be filled is located. According to the quadrant position and the actual position information, the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled is determined. Since the image obtained by directly shooting the bottle mouth will have too much interference information, such as when shooting from the top, the bottle mouth position is generally within the outer contour of the bottle body and is not easy to display. If it is necessary to directly shoot the bottle mouth Accurate position recognition will greatly increase the complexity of machine vision algorithms, and the recognition results are not necessarily accurate, resulting in a large amount of computing resources being consumed and too many precise parameter adjustments being made, which is not conducive to fast and efficient production. Therefore, the present invention determines the target area where the bottle mouth of the bottle to be filled is located from the top image, and determines the quadrant position of the target area according to the preset plane coordinate axis, so that the real-time bottle mouth position can be quickly determined according to the quadrant position and the actual position information, ultimately greatly improving the image computing processing efficiency, recognition accuracy, equipment working energy efficiency and production efficiency.

[0054] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0056] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0057] Figure 1 A schematic diagram of a flow chart of a beverage filling bottle mouth positioning method based on machine vision provided by an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of the structure of a beverage filling bottle mouth positioning device based on machine vision provided by an embodiment of the present invention;

[0059] Figure 3 A simplified structural diagram of a beverage filling bottle mouth positioning system based on machine vision provided by an embodiment of the present invention;

[0060] Figure 4 A simplified structural schematic diagram of a first preset shooting area in a beverage filling bottle mouth positioning system based on machine vision provided by an embodiment of the present invention;

[0061] Figure 5 A simplified structural schematic diagram of a second preset shooting area of ​​a beverage filling bottle mouth positioning system based on machine vision provided by an embodiment of the present invention.

[0062] Figure numbers: 1. Conveying device, 11. Transparent conveyor belt, 12. Soft light, 13. Preset background material, 14. Light-absorbing material, 2. Shooting device. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0065] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0066] In addition, in order to better illustrate the present invention, numerous specific details are provided in the following specific embodiments. It should be understood by those skilled in the art that the present invention can be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present invention.

[0067] See also Figure 1 , Figure 1 The present invention provides a flowchart of a beverage filling bottle mouth positioning method based on machine vision. Figure 1 As shown, a beverage filling bottle mouth positioning method based on machine vision, the method comprises:

[0068] S10, collecting the bottom image of the bottle to be filled;

[0069] It should be noted that due to the structural characteristics of the bottle mouth, there will be too many interference factors. Therefore, when performing contour shape detection and recognition on an image containing the bottle mouth, the detection complexity and time cost are often increased in the processing process. However, the present application can realize fast and efficient processing of the image by collecting the bottom image of the bottle to be filled and processing the bottom image of the bottle to be filled. Specifically, the following steps are included:

[0070] See also Figure 4 S11, arranging the scene based on the color, size and height of the bottle to be filled, so as to enhance the contour shape of the bottle to be filled in the image; specifically, including:

[0071] The conveying device 1 is provided with a transparent conveyor belt 11, through which the bottles to be filled are conveyed through the filling area and then to the next process;

[0072] A first preset shooting area is set on the transparent conveyor belt 11; wherein the first preset shooting area is before the process of the filling area;

[0073] A preset background material 13 is arranged above the transparent conveyor belt 11 in the first preset shooting area; the preset background material 13 is arranged parallel to the transparent conveyor belt 11, and there is a preset spacing between the preset background material 13 and the transparent conveyor belt 11, and the preset spacing is greater than the height of the bottle to be filled; wherein the preset background material 13 can be cloth or paper; the color of the preset background material 13 is arranged relative to the color of the bottle to be filled, and a background color with a high contrast with the color of the bottle is selected. For example, if the bottle is light-colored, a dark background can be used; if the bottle is dark, a light background can be used. This can help the algorithm to more easily segment the bottle from the background, and the color of the preset background material 13 is a single color, avoiding the use of complex patterns or backgrounds of multiple colors. It helps to reduce the interference of the background and make the outline shape of the bottle more prominent. At the same time, matte materials or cloth can be selected as the background, and reflective materials can be avoided, so as to prevent the light spots and shadows caused by light reflection from affecting the image quality.

[0074] By arranging the photographing device 2 below the transparent conveyor belt 11 in the first preset photographing area, the bottle to be filled is photographed when it is conveyed through the preset background material 13, thereby obtaining a bottom image;

[0075] A soft light 12 is arranged above the preset background material 13;

[0076] Light-absorbing materials 14 are arranged on both sides between the transparent conveyor belt 11 and the preset background material 13 in the preset shooting area; the light-absorbing materials 14 are black cloth or black paper;

[0077] Suppose you want to identify a transparent plastic bottle, you can take the following specific measures:

[0078] Choose a dark blue background material: let the transparent bottle form a clear contrast with the background.

[0079] Set up backlighting behind the bottle: Use soft light 12 to illuminate the bottle through the background material above the dark blue background material to avoid obvious shadows and reflective spots on the bottle, while enhancing the outline of the bottle to make it clearer.

[0080] Another example: identifying a white bottle;

[0081] Background: black velvet or cardboard;

[0082] Light source: Place a soft light 12 behind the black flannel, and adjust the angle so that the light evenly and softly illuminates the bottle through the background material. Enhance the outline of the bottle and make it clearer.

[0083] Effect: The bottle's outline will appear on the dark background, making its edges clearly visible.

[0084] Case 2: Identify dark blue bottles;

[0085] Background: White cardboard or cloth

[0086] Light source: Place a soft light 12 behind the colored cardboard or cloth, and adjust the angle so that the light evenly and softly illuminates the bottle through the background material, thus enhancing the outline of the bottle and making it clearer.

[0087] Effect: The bottle's outline will appear on the white background, making its edges clearly visible.

[0088] S12, installing the shooting device 2 directly below the arranged scene, and adjusting the shooting direction of the shooting device 2;

[0089] S13, after detecting the bottle to be filled, controlling the photographing device 2 to photograph the bottle to be filled from the bottom of the bottle to be filled along the top direction of the bottle to be filled, to obtain a bottom image of the bottle to be filled.

[0090] S20, determining the center point position corresponding to the bottom contour shape of the bottle to be filled from the bottom image;

[0091] It should be noted that by determining the center point of the bottom contour of the bottle to be filled from the bottom image, the position of the bottle mouth can be quickly determined without too much complex calculation processing, and the position of the bottle mouth can be efficiently determined. Specifically, it includes:

[0092] Grayscale and Gaussian filtering: Input image (I), use grayscale formula and Gaussian filtering formula to get the preprocessed image (I_{gray}).

[0093] Canny edge detection: Apply Canny edge detection to (I_{gray}) to obtain an edge image.

[0094] Contour extraction and screening: Extract contours from edge images and screen out target contours based on area or other features.

[0095] Calculate the center point: Use the centroid formula to calculate the center point ((C_x, C_y)) of the filtered contour.

[0096] Through these steps, we can identify the bottom contour shape of the bottle from the image and calculate the position of its center point.

[0097] S30, based on the position of the center point, determining the actual position information of the bottle to be filled in the preset plane coordinate axis corresponding to the bottom image; specifically, comprising the following steps:

[0098] S31, obtaining a standard bottom image corresponding to the bottle to be filled;

[0099] It should be noted that the standard bottom image is obtained in advance for reference.

[0100] S32, determining the standard center point position corresponding to the bottom contour shape of the bottle to be filled from the standard bottom image;

[0101] S33, taking the standard center point position as the origin, establishing a plane coordinate axis in the standard bottom image to obtain the preset plane coordinate axis;

[0102] S34, mapping the center point position in the preset plane coordinate axis to determine the coordinate position of the center point position;

[0103] S35, determining the offset distance of the bottle to be filled based on the coordinate position;

[0104] S36. Determine the actual position information of the bottle to be filled based on the offset distance.

[0105] The present invention determines the actual position information of the bottle to be filled based on the bottom image of the bottle to be filled, and then determines the real-time position of the bottle mouth. There is no need to directly perform real-time position recognition and analysis of the bottle mouth from the image. In addition, since the bottom image is more convenient for contour shape and center point position processing than the top image, it can reduce interference information in image processing and reduce the complexity of image processing, thereby improving the image operation processing efficiency and recognition accuracy, reducing the complexity of the machine vision algorithm, thereby avoiding consuming a large amount of computing resources and performing too many precise parameter adjustments.

[0106] S40, determining whether the center point position coincides with the center point position of the bottle mouth of the bottle to be filled on the preset plane coordinate axis; specifically, comprising:

[0107] S41, querying the bottle mouth positioning scheme corresponding to the bottle to be filled in a preset bottle mouth positioning scheme database; wherein the bottle mouth positioning scheme includes a first positioning scheme and a second positioning scheme; specifically, including:

[0108] S411, constructing a three-dimensional image of the bottle to be filled;

[0109] S412, based on the three-dimensional graph, obtaining the bottom contour shape information and the bottle mouth information of the bottle to be filled; wherein the bottom contour shape information includes the bottom contour shape and the center point position of the bottom contour shape, and the bottle mouth information includes one or more of the inner diameter of the bottle mouth, the outer diameter of the bottle mouth, the center point position of the bottle mouth, the height of the center point of the bottle mouth, the direction of the bottle mouth and the inclination of the bottle mouth;

[0110] S413: If the inclination of the bottle mouth is 0°, and the center point of the bottom contour shape and the center point of the bottle mouth of the bottle to be filled are on the same vertical line, determine that the bottle mouth positioning scheme corresponding to the bottle to be filled is the first positioning scheme;

[0111] S414: If the inclination of the bottle mouth is 0°, and the center point of the bottom contour shape and the center point of the bottle mouth of the bottle to be filled are not on the same vertical line, determine that the bottle mouth positioning scheme corresponding to the bottle to be filled is the second positioning scheme.

[0112] S42, when the bottle mouth positioning scheme is the first positioning scheme, the center point position coincides with the bottle mouth center point position of the bottle to be filled on the preset plane coordinate axis;

[0113] S43: When the bottle mouth positioning scheme is the second positioning scheme, the center point position does not coincide with the center point position of the bottle mouth of the bottle to be filled on the preset plane coordinate axis.

[0114] In this embodiment, after obtaining the actual position information of the bottle to be filled, it is determined whether the center point position coincides with the center point position of the bottle mouth of the bottle to be filled on the preset plane coordinate axis, and accordingly the real-time bottle mouth position of the bottle to be filled is analyzed and processed according to the judgment result, thereby avoiding consuming a large amount of computing resources and making too many precise parameter adjustments, and further improving the image computing and processing efficiency, recognition accuracy and equipment working energy efficiency.

[0115] S50: If yes, determine the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled based on the actual position information;

[0116] In one embodiment, determining the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled also includes:

[0117] S51, obtaining the current conveying speed of the conveying device 1 where the bottle to be filled is located; wherein the conveying device 1 is used to convey the bottle to be filled through the filling area to the next process;

[0118] S52, determining the actual position information as the current position of the bottle mouth of the bottle to be filled;

[0119] S53, obtaining the real-time position of the bottle mouth of the bottle to be filled when filling the bottle to be filled according to the current position of the bottle mouth and the current conveying speed.

[0120] In this embodiment, if the judgment result is overlap, the real-time bottle mouth position of the bottle to be filled can be determined according to the actual position information when the bottle to be filled is filled, without the need for further processing of the image, thereby avoiding the consumption of a large amount of computing resources and excessive precise parameter adjustments, thereby improving the image processing efficiency, recognition accuracy, equipment working energy efficiency and production efficiency.

[0121] S60: If not, collect the top image of the bottle to be filled, determine the target area where the bottle mouth of the bottle to be filled is located from the top image, and map the position of the target area in the preset plane coordinate axis to determine the quadrant position where the bottle mouth of the bottle to be filled is located, and determine the real-time bottle mouth position of the bottle to be filled when filling the bottle according to the quadrant position and the actual position information.

[0122] In one embodiment, capturing the top image of the bottle to be filled includes:

[0123] See also Figure 5 S61: Arrange the scene based on the color, size and height of the bottle to be filled, so as to enhance the contour shape of the bottle to be filled in the image;

[0124] The conveying device 1 is provided with a transparent conveyor belt 11, through which the bottles to be filled are conveyed through the filling area and then to the next process;

[0125] A second preset shooting area is set on the transparent conveyor belt 11; wherein, the second preset shooting area is before the process of the filling area and after the first preset shooting area, that is, the first preset shooting area, the second preset shooting area and the filling area are set in sequence; wherein, the top image and the bottom image are consistent in size to ensure accurate and stable processing of the image, and are applicable to the same preset plane coordinate axis.

[0126] A preset background material 13 is arranged below the transparent conveyor belt 11 in the second preset shooting area; the preset background material 13 is arranged parallel to the transparent conveyor belt 11, and there is a preset spacing between the preset background material 13 and the transparent conveyor belt 11, and the preset spacing is greater than the height of the bottle to be filled; wherein the preset background material 13 can be cloth or paper; the color of the preset background material 13 is arranged relative to the color of the bottle to be filled, and a background color with a high contrast with the color of the bottle is selected. For example, if the bottle is light-colored, a dark background can be used; if the bottle is dark, a light background can be used. This can help the algorithm to more easily segment the bottle from the background, and the color of the preset background material 13 is a single color, avoiding the use of complex patterns or backgrounds of multiple colors. This helps to reduce background interference and make the bottle more prominent. At the same time, matte materials or cloth can be selected as the background, and reflective materials can be avoided, which can prevent the light spots and shadows caused by light reflection from affecting the image quality.

[0127] By arranging the photographing device 2 above the transparent conveyor belt 11 in the second preset photographing area, the bottle to be filled is photographed when it is conveyed through the preset background material 13, thereby obtaining a top image;

[0128] A soft light 12 is arranged below the preset background material 13;

[0129] Light absorbing materials 14 are arranged on both sides between the transparent conveyor belt 11 and the shooting device 2 in the preset shooting area; the light absorbing materials 14 are black cloth or black paper;

[0130] S62, installing the shooting device 2 just above the arranged scene, and adjusting the shooting direction of the shooting device 2;

[0131] S63, after detecting the bottle to be filled, controlling the photographing device 2 to photograph the bottle to be filled from the top of the bottle to be filled along the bottom direction of the bottle to be filled, to obtain a top image of the bottle to be filled.

[0132] In one embodiment, determining the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled also includes:

[0133] S64, obtaining the current conveying speed of the conveying device 1 where the bottle to be filled is located; wherein the conveying device 1 is used to convey the bottle to be filled through the filling area to the next process;

[0134] S65, determining the current position of the bottle mouth of the bottle to be filled according to the quadrant position and the actual position information;

[0135] S66. Obtaining the real-time position of the bottle mouth of the bottle to be filled when filling the bottle to be filled according to the current position of the bottle mouth and the current conveying speed.

[0136] In one embodiment, determining the target area where the mouth of the bottle to be filled is located from the top image includes:

[0137] Image preprocessing: read the input image. For example, use OpenCV to read the image; convert the image to grayscale to simplify subsequent processing, and use Gaussian blur to remove noise in the image;

[0138] Edge detection: Use the Canny edge detection algorithm to detect edges in the image;

[0139] Object detection: Detect contours in edge detection results and select possible contours of bottle mouths based on features such as area and shape;

[0140] In post-processing, if multiple possible bottle mouth areas are detected, the final target can be further confirmed based on its position, shape or other features, the detected bottle mouth position is marked on the image, and the processing result is output.

[0141] In this embodiment, if the judgment result is that there is no overlap, the top image of the bottle to be filled is collected, the target area where the bottle mouth of the bottle to be filled is located is determined from the top image, and the position of the target area is mapped in the preset plane coordinate axis to determine the quadrant position where the bottle mouth of the bottle to be filled is located. According to the quadrant position and the actual position information, the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled is determined. Since the image obtained when the bottle mouth is directly photographed will have too much interference information, such as when photographed from the top, the bottle mouth position is generally within the outer contour of the bottle body and is not easy to display. If it is necessary to directly photograph the bottle mouth, the bottle mouth position is generally located within the outer contour of the bottle body and is not easy to display. Accurate position recognition of the bottle mouth will greatly increase the complexity of the machine vision algorithm, and the recognition result is not necessarily accurate, resulting in a large amount of computing resources being consumed and too many precise parameter adjustments being performed, which is not conducive to fast and efficient production. Therefore, the present invention determines the target area where the bottle mouth of the bottle to be filled is located from the top image, and determines the quadrant position of the target area according to the preset plane coordinate axis, so that the real-time bottle mouth position can be quickly determined according to the quadrant position and the actual position information, ultimately greatly improving the image calculation processing efficiency, recognition accuracy, equipment working energy efficiency and production efficiency.

[0142] In one embodiment, it also includes:

[0143] S70, based on the real-time bottle mouth position, controlling the filling device to execute a filling method corresponding to a preset filling scheme to fill the bottle to be filled; wherein the filling method includes intermittent filling and continuous filling;

[0144] S71. When the filling method is the intermittent filling, the real-time bottle mouth position remains unchanged. When the bottle mouth of the bottle to be filled reaches the real-time bottle mouth position, the conveying device 1 is controlled to stop the conveying work, the filling port of the filling device is adjusted to the real-time bottle mouth position, and the filling device is driven to fill the bottle to be filled. After the filling work is completed, the conveying work of the conveying device 1 is resumed, and the filling port of the filling device is reset; through intermittent filling, stable filling of the bottle is achieved, thereby ensuring the stability of production.

[0145] S72, when the filling mode is the continuous filling, the conveying device 1 continuously performs the conveying work, and dynamically updates the real-time bottle mouth position based on the current speed of the conveying device 1, and when the bottle mouth of the bottle to be filled reaches the real-time bottle mouth position, the filling port of the filling device is moved to the real-time bottle mouth position, and the filling port of the filling device is synchronously moved according to the current speed of the conveying device 1, so that the filling port of the filling device is always at the real-time bottle mouth position, and the filling device is driven to fill the bottle to be filled, until the filling work is completed, and the filling port of the filling device is moved again to the real-time bottle mouth position of the next bottle to be filled. Through continuous filling, filling is achieved during transportation, thereby improving production efficiency.

[0146] The beneficial effects of the present invention include:

[0147] The beverage filling bottle mouth positioning method based on machine vision provided by the present invention first collects the bottom image of the bottle body to be filled, and determines the center point position corresponding to the bottom contour shape of the bottle body to be filled from the bottom image; then, based on the center point position, determines the actual position information of the bottle body to be filled in the preset plane coordinate axis corresponding to the bottom image; the present invention determines the actual position information of the bottle body to be filled based on the bottom image of the bottle body to be filled, and then determines the real-time position of the bottle mouth, without directly performing the real-time position recognition and analysis of the bottle mouth from the image, and because the bottom image is more convenient for contour shape and center point position processing than the top image, it can reduce interference information in image processing and reduce the complexity of image processing, thereby improving the image operation processing efficiency and recognition accuracy, reducing the complexity of the machine vision algorithm, thereby avoiding consuming a large amount of computing resources and performing too many precise parameter adjustments.

[0148] After obtaining the actual position information of the bottle to be filled, by judging whether the center point position coincides with the center point position of the bottle mouth of the bottle to be filled on the preset plane coordinate axis, the real-time bottle mouth position of the bottle to be filled is analyzed and processed accordingly according to the judgment result, thereby avoiding consuming a large amount of computing resources and making too many precise parameter adjustments, and further improving the image computing and processing efficiency, recognition accuracy and equipment working energy efficiency.

[0149] If the judgment result is overlap, the real-time bottle mouth position of the bottle to be filled can be determined according to the actual position information when the bottle to be filled is filled, without the need for further processing of the image, thus avoiding the consumption of a large amount of computing resources and excessive precise parameter adjustments, thereby improving the image processing efficiency, recognition accuracy, equipment working energy efficiency and production efficiency.

[0150] If the judgment result is that there is no overlap, the top image of the bottle to be filled is collected, the target area where the bottle mouth of the bottle to be filled is located is determined from the top image, and the position of the target area is mapped in the preset plane coordinate axis to determine the quadrant position where the bottle mouth of the bottle to be filled is located. According to the quadrant position and the actual position information, the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled is determined. Since the image obtained by directly shooting the bottle mouth will have too much interference information, such as when shooting from the top, the bottle mouth position is generally within the outer contour of the bottle body and is not easy to display. If it is necessary to directly accurately shoot the bottle mouth Accurate position recognition will greatly increase the algorithm complexity of machine vision, and the recognition result is not necessarily accurate, resulting in a large amount of computing resources being consumed and too many precise parameter adjustments being made, which is not conducive to fast and efficient production. Therefore, the present invention determines the target area where the bottle mouth of the bottle to be filled is located from the top image, and determines the quadrant position of the target area according to the preset plane coordinate axis, so that the real-time bottle mouth position can be quickly determined according to the quadrant position and the actual position information, ultimately greatly improving the image operation processing efficiency, recognition accuracy, equipment working energy efficiency and production efficiency.

[0151] See also Figure 2 , Figure 2 The present invention provides a structural diagram of a beverage filling bottle mouth positioning device based on machine vision. Figure 2 As shown, the present invention also provides a beverage filling bottle mouth positioning device based on machine vision, the device comprising:

[0152] A collection module, used to collect the bottom image of the bottle to be filled;

[0153] A first determination module is used to determine the center point position corresponding to the bottom contour shape of the bottle to be filled from the bottom image;

[0154] A second determination module is used to determine the actual position information of the bottle to be filled in the preset plane coordinate axis corresponding to the bottom image based on the position of the center point;

[0155] A judging module, used for judging whether the center point position coincides with the center point position of the bottle mouth of the bottle to be filled on the preset plane coordinate axis;

[0156] A third determination module is used to determine the position of the bottle mouth of the bottle to be filled when filling the bottle to be filled based on the reference bottle mouth center point position corresponding to the bottle to be filled and the actual position information when the center point position coincides with the bottle mouth center point position of the bottle to be filled on the preset plane coordinate axis;

[0157] The fourth determination module is used to collect the top image of the bottle to be filled when the center point position and the center point position of the bottle mouth of the bottle to be filled do not coincide with each other on the preset plane coordinate axis, determine the mapping position of the bottle mouth of the bottle to be filled in the preset plane coordinate axis based on the top image, and determine the position of the bottle mouth of the bottle to be filled when filling the bottle based on the mapping position.

[0158] See also Figure 3-5 , Figure 3 The following is a simplified structural diagram of a beverage filling bottle mouth positioning system based on machine vision provided by an embodiment of the present invention. Figure 3 As shown, the present invention also provides a beverage filling bottle mouth positioning system based on machine vision, the system comprising:

[0159] A beverage filling bottle mouth positioning device based on machine vision as described above;

[0160] A conveying device 11 is used to convey the bottles to be filled through the filling area to the next process;

[0161] At least two photographing devices 22, the two photographing devices 2 are respectively arranged above and below the conveying device 1, and the two photographing devices 2 are arranged at intervals, and the photographing devices 2 are used to take images of the bottles to be filled to obtain bottom images and top images;

[0162] A filling device, arranged on one side of the conveying device 1, and used for filling the bottles to be filled in the filling area;

[0163] A handling device is slidably mounted on the conveying device 1, and is used to dynamically handle the filling port of the filling device to the real-time bottle mouth position in the filling area according to the real-time bottle mouth position obtained based on the detection results of the bottom image and the top image.

[0164] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0165] The present invention also provides an electronic device, including a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any possible implementation manner.

[0166] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0167] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0168] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present invention have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

[0169] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0170] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0171] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0172] A person skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by a computer program to instruct the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The aforementioned storage medium includes: a read-only memory (ROM) or a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

Claims

1. A beverage filling bottle mouth positioning method based on machine vision, characterized in that: The method comprises: Collect the bottom image of the bottle to be filled; Determine the center point position corresponding to the bottom contour shape of the bottle to be filled from the bottom image; Based on the position of the center point, determining the actual position information of the bottle to be filled in the preset plane coordinate axis corresponding to the bottom image; Determining whether the center point position coincides with the center point position of the bottle mouth of the to-be-filled bottle body on the preset plane coordinate axis comprises: querying the bottle mouth positioning scheme corresponding to the to-be-filled bottle body in a preset bottle mouth positioning scheme database; wherein the bottle mouth positioning scheme comprises a first positioning scheme and a second positioning scheme; when the bottle mouth positioning scheme is the first positioning scheme, the center point position coincides with the center point position of the bottle mouth of the to-be-filled bottle body on the preset plane coordinate axis; when the bottle mouth positioning scheme is the second positioning scheme, the center point position does not coincide with the center point position of the bottle mouth of the to-be-filled bottle body on the preset plane coordinate axis; wherein querying the bottle mouth positioning scheme corresponding to the to-be-filled bottle body in a preset bottle mouth positioning scheme database comprises: constructing a three-dimensional map of the to-be-filled bottle body; based on the A three-dimensional graph is used to obtain the bottom contour shape information and bottle mouth information of the bottle to be filled; wherein, the bottom contour shape information includes the bottom contour shape and the center point position of the bottom contour shape, and the bottle mouth information includes one or more of the inner diameter of the bottle mouth, the outer diameter of the bottle mouth, the center point position of the bottle mouth, the height of the center point of the bottle mouth, the direction of the bottle mouth and the inclination of the bottle mouth; if the inclination of the bottle mouth is 0°, and the center point position of the bottom contour shape and the center point position of the bottle mouth of the bottle to be filled are on the same vertical line, it is determined that the bottle mouth positioning scheme corresponding to the bottle to be filled is the first positioning scheme; if the inclination of the bottle mouth is 0°, and the center point position of the bottom contour shape and the center point position of the bottle mouth of the bottle to be filled are not on the same vertical line, it is determined that the bottle mouth positioning scheme corresponding to the bottle to be filled is the second positioning scheme; If yes, based on the actual position information, determine the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled; If not, collect the top image of the bottle to be filled, determine the target area where the bottle mouth of the bottle to be filled is located from the top image, and map the position of the target area in the preset plane coordinate axis to determine the quadrant position where the bottle mouth of the bottle to be filled is located, and determine the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled according to the quadrant position and the actual position information; Wherein, determining the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled includes: Obtaining the current conveying speed of the conveying device where the bottle to be filled is located; wherein the conveying device is used to convey the bottle to be filled through the filling area to the next process; Determine the actual position information as the current position of the mouth of the bottle to be filled; or determine the current position of the mouth of the bottle to be filled according to the quadrant position and the actual position information; According to the current position of the bottle mouth and the current conveying speed, the real-time position of the bottle mouth of the bottle to be filled is obtained when the bottle to be filled is filled.

2. The beverage filling bottle mouth positioning method based on machine vision according to claim 1 is characterized in that: Based on the position of the center point, determining the actual position information of the bottle to be filled in the preset plane coordinate axis corresponding to the bottom image includes: Acquire a standard bottom image corresponding to the bottle to be filled; Determining the standard center point position corresponding to the bottom contour shape of the bottle to be filled from the standard bottom image; Taking the standard center point position as the origin, establishing a plane coordinate axis in the standard bottom image to obtain the preset plane coordinate axis; Mapping the center point position in the preset plane coordinate axis to determine the coordinate position of the center point position; Determine the offset distance of the bottle to be filled based on the coordinate position; The actual position information of the bottle to be filled is determined based on the offset distance.

3. The beverage filling bottle mouth positioning method based on machine vision according to claim 1 is characterized in that: Capture the bottom image of the bottle to be filled, including: Arrange the scene based on the color, size and height of the bottle to be filled, so as to enhance the contour shape of the bottle to be filled in the image; Install a shooting device directly below the arranged scene, and adjust the shooting direction of the shooting device; After the bottle to be filled is detected, the photographing device is controlled to photograph the bottle to be filled from the bottom of the bottle to be filled along the top direction of the bottle to be filled to obtain a bottom image of the bottle to be filled.

4. The beverage filling bottle mouth positioning method based on machine vision according to claim 1 is characterized in that: Also includes: Based on the real-time bottle mouth position, control the filling device to execute a filling method corresponding to a preset filling scheme to fill the bottle to be filled; wherein the filling method includes intermittent filling and continuous filling; When the filling method is the intermittent filling, the real-time bottle mouth position remains unchanged, and when the bottle mouth of the bottle to be filled reaches the real-time bottle mouth position, the conveying device is controlled to stop conveying, the filling port of the filling device is adjusted to the real-time bottle mouth position, and the filling device is driven to fill the bottle to be filled, until the filling work is completed, the conveying work of the conveying device is resumed, and the filling port of the filling device is reset; When the filling mode is the continuous filling, the conveying device continuously performs the conveying work, and dynamically updates the real-time bottle mouth position based on the current speed of the conveying device, and when the bottle mouth of the bottle to be filled reaches the real-time bottle mouth position, the filling port of the filling device is moved to the real-time bottle mouth position, and the filling port of the filling device is synchronously moved according to the current speed of the conveying device, so that the filling port of the filling device is always in the real-time bottle mouth position, and the filling device is driven to fill the bottle to be filled, until the filling work is completed, and the filling port of the filling device is moved again to the real-time bottle mouth position of the next bottle to be filled.

5. A beverage filling bottle mouth positioning device based on machine vision, characterized in that: The device comprises: A collection module, used to collect the bottom image of the bottle to be filled; A first determination module is used to determine the center point position corresponding to the bottom contour shape of the bottle to be filled from the bottom image; A second determination module is used to determine the actual position information of the bottle to be filled in the preset plane coordinate axis corresponding to the bottom image based on the position of the center point; A judgment module, for judging whether the center point position and the center point position of the bottle mouth of the bottle to be filled coincide on the preset plane coordinate axis, comprising: querying the bottle mouth positioning scheme corresponding to the bottle to be filled in a preset bottle mouth positioning scheme database; wherein the bottle mouth positioning scheme comprises a first positioning scheme and a second positioning scheme; when the bottle mouth positioning scheme is the first positioning scheme, the center point position and the center point position of the bottle mouth of the bottle to be filled coincide on the preset plane coordinate axis; when the bottle mouth positioning scheme is the second positioning scheme, the center point position and the center point position of the bottle mouth of the bottle to be filled do not coincide on the preset plane coordinate axis; wherein querying the bottle mouth positioning scheme corresponding to the bottle to be filled in a preset bottle mouth positioning scheme database comprises: constructing a three-dimensional map of the bottle to be filled; Based on the three-dimensional graph, the bottom contour shape information and the bottle mouth information of the bottle to be filled are obtained; wherein, the bottom contour shape information includes the bottom contour shape and the center point position of the bottom contour shape, and the bottle mouth information includes one or more of the inner diameter of the bottle mouth, the outer diameter of the bottle mouth, the center point position of the bottle mouth, the height of the center point of the bottle mouth, the direction of the bottle mouth and the inclination of the bottle mouth; if the inclination of the bottle mouth is 0°, and the center point position of the bottom contour shape and the center point position of the bottle mouth of the bottle to be filled are on the same vertical line, it is determined that the bottle mouth positioning scheme corresponding to the bottle to be filled is the first positioning scheme; if the inclination of the bottle mouth is 0°, and the center point position of the bottom contour shape and the center point position of the bottle mouth of the bottle to be filled are not on the same vertical line, it is determined that the bottle mouth positioning scheme corresponding to the bottle to be filled is the second positioning scheme; A third determination module is used to determine the position of the bottle mouth of the bottle to be filled when filling the bottle to be filled based on the reference bottle mouth center point position corresponding to the bottle to be filled and the actual position information when the center point position coincides with the bottle mouth center point position of the bottle to be filled on the preset plane coordinate axis; a fourth determination module, configured to, when the center point position and the center point position of the bottle mouth of the bottle to be filled do not coincide on the preset plane coordinate axis, collect a top image of the bottle to be filled, determine a mapping position of the bottle mouth of the bottle to be filled in the preset plane coordinate axis based on the top image, and determine a position of the bottle mouth of the bottle to be filled when filling the bottle to be filled based on the mapping position; Wherein, determining the real-time bottle mouth position of the bottle to be filled when filling the bottle to be filled includes: Obtaining the current conveying speed of the conveying device where the bottle to be filled is located; wherein the conveying device is used to convey the bottle to be filled through the filling area to the next process; Determine the actual position information as the current position of the mouth of the bottle to be filled; or determine the current position of the mouth of the bottle to be filled according to the quadrant position and the actual position information; According to the current position of the bottle mouth and the current conveying speed, the real-time position of the bottle mouth of the bottle to be filled is obtained when the bottle to be filled is filled.

6. A beverage filling bottle mouth positioning system based on machine vision, characterized in that: The system comprises: A beverage filling bottle mouth positioning device based on machine vision as claimed in claim 5; A conveying device, used to convey the bottles to be filled through the filling area to the next process; At least two photographing devices, the two photographing devices are respectively arranged above and below the conveying device, and the two photographing devices are arranged at an interval, and the photographing devices are used to take images of the bottles to be filled to obtain bottom images and top images; A filling device, arranged on one side of the conveying device, and used for filling the bottles to be filled in the filling area; A handling device is slidably mounted on the conveying device, and is used to dynamically handle the filling port of the filling device to the real-time bottle mouth position in the filling area according to the real-time bottle mouth position obtained based on the detection results of the bottom image and the top image.

Images