Intelligent filling system and filling method

Abstract

The application discloses an intelligent filling system and filling method, and relates to the technical field of intelligent filling, which adopts a pressure sensor to monitor whether a container enters a filling table, triggers a terminal to generate a detection instruction, uses a camera cluster to collect images, extracts the positional relationship between a filling port and a container port, fits a standard and a to-be-filled plane graph and checks them to determine a filling condition, constructs a container panoramic image to determine the capacity and the filling amount if the filling condition is normal, and executes filling, wherein the scheme comprises a data acquisition, storage and processing module; the pressure sensor and the camera are cooperated to accurately control the filling process through an image processing technology, the filling precision and efficiency are improved, the scheme is suitable for various containers, manual intervention is reduced, and the production automation level is improved.

Description

Technical Field

[0001] This invention belongs to the field of intelligent filling technology, specifically, it relates to an intelligent filling system and filling method. Background Technology

[0002] With rapid economic development, industrial production is increasingly demanding automation and intelligence. In the filling industry, traditional filling technology mainly relies on manual operation or simple mechanical control, which has problems such as low efficiency and insufficient precision.

[0003] Although sensor monitoring and image acquisition equipment have been introduced into existing technologies, current monitoring methods are usually limited to single-point pressure detection, which cannot accurately determine whether the container is correctly positioned, easily causing empty filling or refilling, affecting production efficiency. In the filling volume control stage, traditional methods mostly rely on preset parameters and cannot be dynamically adjusted according to the actual shape of the container, failing to meet the production needs of irregularly shaped containers or capacity fluctuations. In addition, the level of intelligence of traditional filling systems is low, and the data of each stage lacks correlation analysis, failing to form a complete production monitoring closed loop.

[0004] To address the aforementioned issues, this application proposes an intelligent filling system and filling method. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an intelligent filling system and method, which solves the problems of existing technologies being unable to dynamically adjust according to the actual shape of the container and lacking a complete production monitoring closed loop.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A smart filling method, comprising the following steps:

[0008] Step 1: Install a pressure sensor on the bottom of the filling station to monitor whether a container enters the filling station. If not, continue monitoring.

[0009] If so, a first signal is generated and transmitted to the terminal processor. The terminal processor then confirms the first signal, generates a detection command, and transmits it to the camera cluster installed in the filling station area for image acquisition.

[0010] Step 2: Extract the positional relationship between the filling port and the filling station, and combine the images collected by the camera cluster to fit a standard filling plan.

[0011] Based on images acquired by a cluster of cameras, the positional relationship between the container opening and the filling station is extracted, and a plan view to be filled is fitted.

[0012] The filling plan is verified against the standard filling plan, and the abnormal filling situation and normal filling situation are determined based on the verification results.

[0013] If the verification result indicates an abnormal filling situation, skip this filling operation and repeat steps one and two.

[0014] If the verification result indicates normal filling, proceed to step three;

[0015] Step 3: Extract the images collected by the camera cluster again, construct a panoramic image of the current container, and determine the container capacity;

[0016] The filling volume is further determined based on the determined container capacity, and the filling operation is then performed.

[0017] As a further aspect of the present invention, the specific method for generating the detection command in step one is as follows:

[0018] The initial value for calibrating the pressure sensor is 0;

[0019] The pressure sensor values ​​are acquired in real time by an edge processor connected to the pressure sensor. ;

[0020] like If this occurs, the edge processor's built-in counter T will start counting from 0 seconds, and T will increase over time. If the duration of counter T exceeds the operator's preset time threshold... If the presence of a container is detected on the pressure sensor, the edge processor generates a first signal, which is then transmitted to the terminal processor via the system bus.

[0021] As a further aspect of the present invention, the specific method for image acquisition in step one is as follows:

[0022] The detection commands generated by the terminal processor are transmitted to the camera cluster via the system bus;

[0023] The camera cluster is denoted as ,in, This is a counting index, representing the total number of cameras in the camera cluster;

[0024] By utilizing a cluster of cameras to provide comprehensive coverage of the entire filling station area, and by taking photos even when there are no containers within the filling station area, the results are obtained. Zhang images, denoted as the set of images of the filling station. ,in, and correspond, This is a counting index, with values ​​ranging from 1 to... ;

[0025] After receiving the detection command, the camera cluster will take another picture of the filling station area and record the results. Zhang is denoted as a container image set. The relationship between the container image and the filling station image and the actual size is one to one.

[0026] As a further aspect of the present invention, the specific method for determining abnormal filling conditions and normal filling conditions based on the verification processing results in step two is as follows:

[0027] from Extract the top-view image of the filling station from directly above it and label it as... ;

[0028] by The origin is the first pixel in the bottom left corner. Using the left boundary as the vertical axis, The lower boundary is constructed using the horizontal axis. The associated two-dimensional coordinate system;

[0029] Then obtain the two-dimensional coordinates of the center point of the filling nozzle on the two-dimensional coordinate system. Extract the filling port radius In two-dimensional coordinates Draw a circle with the center and the radius of the filling nozzle. Draw a circle with a radius to obtain a circle. ;

[0030] Preserve the circle At In the associated two-dimensional coordinate system, and this two-dimensional coordinate system is denoted as the standard filling plan view. ;

[0031] Similarly, from Extract the container image from the top view directly above the filling station and label it as... , build The associated two-dimensional coordinate system;

[0032] Sure The two-dimensional coordinates of the center point of the container opening on the two-dimensional coordinate system ;

[0033] Get container opening radius ,by Draw a circle with the center and the radius of the container opening. Using the radius of a circle as the base, draw a circle. ;

[0034] Preserve the circle At In the associated two-dimensional coordinate system, and this two-dimensional coordinate system is denoted as the plan view to be filled. ;

[0035] By aligning coordinates and Superimposing them onto the same plane yields a planar image;

[0036] At this moment, the circle ,round Placed in the same plane, opposite the circle ,round Perform verification processing:

[0037] like If so, the result of the verification process is determined to be a normal filling situation;

[0038] like If the result of the verification process is determined to be an abnormal filling situation, then the verification process is considered to be successful.

[0039] As a further aspect of the present invention, in step two, the circle... ,round Perform a verification process. If the verification result indicates an abnormal filling situation, skip the filling operation for this container.

[0040] If the verification process determines that the filling is normal, then the container capacity and filling volume are further determined, and the filling operation is performed.

[0041] As a further aspect of the present invention, the specific method for determining the container capacity and filling volume, and performing the filling operation is as follows:

[0042] From the collection of images of filling stations Extract any one of the filling station images Then from the container image set Extract any container image ;

[0043] Determine the image of the filling station and container images The number of pixels in the middle, denoted as m;

[0044] Will The first pixel of the filling station in the top left corner is denoted as The last pixel of the filling station in the bottom right corner is denoted as ;

[0045] Extract the images of the filling station from left to right and top to bottom. Given m pixels of the filling station, we obtain the pixel sequence of the filling station. ;

[0046] Similarly, the sequence of container pixels is obtained: ;

[0047] from Extract any pixel from the filling station ;

[0048] from Extract any pixel that is related to the filling station The associated container pixels ;

[0049] extract pixel values as well as pixel values Where n is the counting index, and its value ranges from 1 to m;

[0050] Sure as well as Difference rate between pixel values , the difference rate The difference rate threshold preset by the operator Perform a comparison;

[0051] If the difference rate Then the container pixels Treat it as a foreground pixel;

[0052] If the difference rate Then the container pixels Treat them as background pixels;

[0053] Again Perform the above steps on all container pixels to determine the container image. The foreground and background pixels in the image are identified, and the background pixels are removed to obtain the foreground container image. ;

[0054] Again as well as Repeat the above steps to obtain a set of foreground container images: ;

[0055] right A fitting process is performed to obtain a panoramic image associated with the container, and the container volume is determined based on the panoramic image and the correlation between the panoramic image and the actual dimensions of the container. ;

[0056] Extract the pre-set filling percentage by the operator. To obtain the filling volume associated with the container. Perform the filling operation.

[0057] As a further aspect of the present invention, an intelligent filling system is provided, the system comprising:

[0058] The data acquisition module includes pressure sensors, a camera cluster, and an edge processor associated with the camera cluster;

[0059] A data storage module, including a memory, is used to store the analysis and calculation results of any of the steps described above, and to save an intelligent filling method;

[0060] The data processing module includes a terminal processor, which reads a smart filling method stored in the memory and runs it to implement the steps described in any of the above.

[0061] As a further aspect of the present invention, the system also includes the following:

[0062] The pressure sensor is used to monitor whether the container enters the filling station;

[0063] The camera cluster is used to acquire images of the filling station area.

[0064] The beneficial effects of this invention are:

[0065] (1) This invention uses pressure sensors and camera clusters on the bottom surface of the filling station to accurately monitor the entry and position of the container. When the container enters the filling station, the system can quickly generate a signal and trigger the camera cluster to acquire images, extract the positional relationship between the filling port and the container port in real time, and fit a standard filling plan and a plan to be filled for verification. This design can effectively avoid filling failure or material waste caused by abnormal container position and ensure the accuracy of filling operation. Secondly, the system can automatically determine the filling volume based on the container capacity and perform filling, realizing intelligent filling process management and solving the problem of low adaptability of traditional filling production lines. It realizes the automation and intelligence of the entire filling process.

[0066] (2) This invention constructs a high-precision and high-reliability container detection system by combining a pressure sensor and an edge processor with an intelligent image acquisition system. Its core advantage lies in the use of a dual verification mechanism to ensure detection accuracy: the pressure sensor eliminates environmental interference through initial calibration and effectively avoids instantaneous false triggering by combining a time threshold counter; the signal retransmission function of the edge processor enhances the robustness of the system; at the same time, the camera cluster significantly improves the accuracy of container positioning and shape recognition by comparing the pixel-level of the container-free reference image and the real-time container image, under the guarantee of one-to-one physical mapping and unified image parameters; the two system processes form a closed-loop control through bus collaboration, which solves the problem of misjudgment caused by environmental interference in traditional filling equipment, and ensures data consistency through standardized image acquisition process, thus achieving a dual technological breakthrough of improved detection efficiency and reduced false detection rate.

[0067] (3) This invention achieves automatic verification of the spatial position of the filling port and the container port by constructing a standardized filling plan and a precise mapping of the real-time container image coordinate system; secondly, this solution achieves the determination of the filling port and container coverage relationship through the coordinate system alignment and superposition mechanism, identifies abnormal situations such as container offset and size discrepancy, and achieves production continuity through the abnormal situation handling mechanism, which significantly optimizes the production line efficiency while improving the stability of filling quality.

[0068] (4) This method determines the container capacity and filling amount by analyzing and processing image pixels, thus achieving precise filling operation. Its core advantage lies in using serialized pixel comparison technology to dynamically separate foreground and background pixels through the difference rate threshold, thereby obtaining an effective set of foreground container images and fitting a panoramic image of the container. This makes the determination of container volume more accurate and can accurately calculate the filling amount associated with the container based on the filling percentage preset by the operator, thereby ensuring the consistency and accuracy of filling. This image analysis-based method enhances the flexibility and adaptability of the filling process and can be applied to containers of different shapes and sizes, providing an efficient, accurate and widely applicable solution for the field of intelligent filling. Attached Figure Description

[0069] The invention will now be further described with reference to the accompanying drawings.

[0070] Figure 1 This is a schematic diagram of the system described in this invention;

[0071] Figure 2 This is a flowchart illustrating the method described in Embodiment 2 of the present invention;

[0072] Figure 3 This is a flowchart illustrating the method described in Embodiment 3 of the present invention;

[0073] Figure 4 This is a flowchart illustrating the method described in Embodiment 4 of the present invention. Detailed Implementation

[0074] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0075] Example 1

[0076] A smart filling system, such as Figure 1 As shown, the system includes the following:

[0077] The data acquisition module is interconnected with the physical object and includes a pressure sensor for real-time monitoring of whether there is a container at the filling station. When the value of the pressure sensor changes and remains stable for a period of time, it is considered that there is a container at the filling station. The pressure sensor is equipped with an edge processor to generate a first signal and transmit it to the terminal processor in the data processing module.

[0078] The pressure sensor values ​​are not fixed and calibrated here because the weight of the containers will vary when different containers are used for filling. Therefore, it is not possible to detect the presence of containers on the filling station based on a fixed weight value. Secondly, having operators manually input a fixed weight value before filling would increase the workload to some extent, since the production line operates 24 hours a day. In contrast, using a pressure sensor value that has been stable for a period of time can effectively improve the monitoring efficiency of whether there are containers on the filling station.

[0079] Secondly, the data acquisition module also includes a camera cluster, which contains multiple cameras arranged in different directions in the filling station area, enabling omnidirectional image acquisition within the filling station area.

[0080] The data storage module includes a memory used to store the calculation methods and results, or the analysis methods and results, of any step in this solution.

[0081] The data processing module serves as the data processing terminal of this system. It includes a terminal processor for processing and real-time performing the calculation and analysis steps described in this solution.

[0082] Used to issue detection commands to a cluster of cameras for image acquisition;

[0083] Used to transmit filling operation instructions to the filling station to perform the filling operation.

[0084] Example 2

[0085] This embodiment discloses a method for image acquisition using a camera cluster, such as... Figure 2 As shown, the specific steps include the following:

[0086] Before the filling operation, data preparation work needs to be carried out, including the numerical calibration of pressure sensors and the determination of lighting conditions for the camera cluster.

[0087] The pressure sensor calibration operation involves adjusting the initial value of the pressure sensor to 0, indicating that there are no containers on the filling platform, and then calibrating the real-time pressure value of the pressure sensor (the pressure value is then set to...). The data is transmitted to the edge processor connected to the pressure sensor for processing. If the edge processor detects a pressure value... If the value is greater than 0, the edge processor's built-in counter T is triggered. The initial value of counter T is also 0 (0 seconds or 0 milliseconds, the specific value is determined by the operator based on the actual situation). When the pressure value... When the value is greater than 0, the counter T starts timing at this moment, and T increases with time. If the length of the counter T is detected to be greater than the time threshold preset by the operator, it indicates that the value of the pressure sensor is in a stable state, further confirming that there is a container on the pressure sensor, that is, there is a container at the filling station.

[0088] At this point, the edge processor connected to the pressure sensor will generate a first signal and transmit the first signal generated by the edge processor to the terminal processor in the data processing module via the system bus;

[0089] If the terminal processor in the data processing module receives the first signal transmitted by the edge processor, it generates a detection command and transmits it to the camera cluster.

[0090] If the terminal processor in the data processing module confirms that it has failed to receive the first signal transmitted by the edge processor, it will feed back the confirmed failure information to the edge processor connected to the pressure sensor and request a retransmission of the first signal.

[0091] The lighting conditions for the camera cluster need to be determined before the camera cluster starts shooting, and will not be adjusted afterward. This is because if the lighting changes during the image shooting process, it will cause significant differences between the captured images, leading to misjudgments in subsequent operations.

[0092] Before the camera cluster receives the detection command transmitted from the terminal processor and acquires images of the filling station area, it needs to take images of the filling station area without containers for reference in subsequent image data processing (when the shooting conditions (such as lighting, number of cameras) change, the images of the containerless areas need to be updated).

[0093] Define the total number of cameras in the camera cluster, denoted as . And the camera cluster is represented as: ,in, They represent the first to the second. One camera, and This is a counting index, representing the total number of cameras in the camera cluster;

[0094] via camera cluster A comprehensive, all-around photographic coverage of the entire filling station area was taken, resulting in images that show the entire filling station area. Zhang Image, according to camera cluster The sorting order of the cameras will be The set of images on the filling station is denoted as: Among them, determine any image of the filling station. The associated camera is ,and For a counting index, The value range is 1 to ;

[0095] Collection of filling station images Save;

[0096] Once the camera cluster receives the detection command (there is a container on the filling station), then the camera cluster is used. The filling station area containing containers was photographed, and the photographed filling station area containing containers was captured. Zhang Image According to Camera Cluster The sorting order of the cameras is denoted as the container image set, and is represented as: ;

[0097] The container images and filling station images in the container image set and filling station image set are correlated with the actual dimensions on a one-to-one basis, so as to accurately determine their corresponding size and position in actual space based on the position, size and other information of each part of the container or filling station in the image.

[0098] The container images and filling station images are both captured by the same type of camera, with the same number of pixels and the same image resolution (the number of pixels in each image is also the same, m), to avoid measurement errors caused by differences in image quality.

[0099] The purpose of this embodiment is to provide accurate preliminary data support for the filling operation, ensuring that the pressure sensor can accurately detect the presence of the container and the camera cluster can acquire images that are accurately correlated with the actual size of the object, thereby ensuring the accuracy of the filling operation and the reliability of subsequent image data processing.

[0100] Example 3

[0101] This embodiment further discloses a method for determining abnormal filling conditions and normal filling conditions based on embodiment 2, such as... Figure 3 As shown, the specific steps include the following:

[0102] Based on the steps described in Example 2, a set of filling station images can be obtained: And a collection of container images: ;

[0103] Next, from the image set of the filling station: Extract the top-view image of the filling station and label it as... This step can be achieved by designating a camera specifically for capturing a top-down view of the filling station when setting up the cameras, and then directly extracting the image captured by that camera.

[0104] Image of filling station To construct a two-dimensional coordinate system, where each coordinate point corresponds to a pixel, the method is as follows:

[0105] Image of filling station The bottom left pixel serves as the origin of the two-dimensional coordinate system in the filling station image. The left boundary serves as the origin and vertical axis of the two-dimensional coordinate system, as shown in the image of the filling station. The lower boundary is used as the origin of the two-dimensional coordinate system, and the horizontal axis is used to construct the image of the filling station. The associated two-dimensional coordinate system;

[0106] Next, obtain the two-dimensional coordinates of the center point of the filling nozzle on the two-dimensional coordinate system, denoted as . Generally, the center point of the filling port corresponds to the center point of the filling table surface. In special cases, the operator shall determine the center point based on the actual situation.

[0107] Then extract the radius of the filling nozzle and mark it as... In two-dimensional coordinates As the center, the radius of the filling nozzle Using the radius of a circle as the base, you can draw a circle. , wherein the circle This refers to the liquid outlet area of ​​the filling port.

[0108] The measured circle Save it in the two-dimensional coordinate system obtained in the above steps, and denote this two-dimensional coordinate system as: Standard Filling Plane Diagram ;

[0109] For a collection of container images: Repeat the above steps, from Extract the container image from the top-down view directly above the filling station and label it as: From container image The two-dimensional coordinates of the center point of the container opening in the two-dimensional coordinate system are obtained and denoted as . ;

[0110] Synchronous build of container images The associated two-dimensional coordinate system;

[0111] Next, extract all container images taken from the front and side of the filling station area from the container image set. Using image separation technology, obtain the image of the container opening area and its actual size, i.e., the width of the container opening. The width of the container opening is equal to its diameter; take half of the diameter to obtain the container opening diameter. In two-dimensional coordinates As the center, the diameter of the container opening Using the radius of a circle as the base, we can construct a circle. and the circle Saved in container image In the associated two-dimensional coordinate system, and denoted as the two-dimensional coordinate system at this time: the plan view to be filled. .

[0112] This yields the standard filling plan. and a floor plan of the area to be filled. The standard filling plan Images taken without containers; standard filling plan. The image shows the liquid outlet area at the filling port and a plan view of the area to be filled. The image was taken with the container in place, and is a plan view of the area to be filled. The container opening area is shown in the image;

[0113] Plan of the area to be filled Compared with standard filling plan The two coordinate systems are then merged to obtain a planar image, which involves aligning the two coordinate systems and superimposing them onto the same plane.

[0114] At this moment, the circle and circle Given the same plane, determine the circle. ,round The positional relationship between them, if If the result of the verification process is determined to be a normal filling situation; if If so, the result of the verification process is determined to be an abnormal filling situation;

[0115] If the final result of the verification process is determined to be an abnormal filling situation, the filling operation of the current container is skipped, and the next container is transported to the filling station via the conveyor belt on the filling station (the container with the abnormal filling situation will be sent for inspection and handled by the operator).

[0116] If the verification process indicates that the filling is normal, then determine the container capacity and filling volume, and perform the filling operation.

[0117] This embodiment extracts a top-down view image of the filling station and constructs a two-dimensional coordinate system to determine the center point and radius of the filling port, forming a standard filling plan. Similarly, it obtains relevant information about the container opening from the container image to construct a plan to be filled. After merging and aligning the two, it determines whether the filling is normal based on the positional relationship between the circles. If it is abnormal, the current container filling is skipped; if it is normal, the capacity and filling amount are determined and filling is performed. The aim is to use image recognition and coordinate positioning technology to achieve automated and precise detection and control of the filling process, ensuring the accuracy and reliability of the filling operation.

[0118] Example 4

[0119] This embodiment, based on embodiments 2 and 3, further discloses a method for determining the container capacity and filling volume, and performing the filling operation, such as... Figure 4 As shown, the specific steps include the following:

[0120] When the verification process in Example 3 results in a normal filling condition, the filling station image set is extracted from the method described in Example 2. And a collection of container images: ;

[0121] From the determined set of container images: Extract any container image Then from the image set of the filling station: Extract any one of the filling station images ;

[0122] Image of the filling station The first pixel in the top left corner is denoted as the first pixel. The last pixel in the bottom right corner is denoted as Images of the filling station were extracted in order from left to right and from top to bottom. From the m pixels in the image, we obtain the pixel sequence of the filling station: ;

[0123] Extract the container image again The first pixel in the top left corner And the last pixel And extract the container image according to the method described above. Given m pixels, we obtain the container pixel sequence: ;

[0124] From the determined filling station image sequence and container image sequences Extract any two pixels: filling station pixels and filling station pixels The associated container pixels Then extract the pixels of the filling station. The pixel value, denoted as Then extract the container pixels. The pixel value, denoted as Where n is the counting index, and its value ranges from 1 to m;

[0125] For the determined pixel value and pixel values The pixel value difference rate is calculated using the following formula:

[0126] ;

[0127] Confirm the pixels of the filling station and container pixels Difference rate of pixel values ​​between ;

[0128] Then the determined difference rate The difference rate threshold is preset in conjunction with the operator based on the actual situation. Perform a comparison; if the difference rate Greater than the difference rate threshold Then the container pixels Considered as foreground pixels, if the difference rate Less than or equal to the difference rate threshold Then the container pixels Treat them as background pixels;

[0129] At this point, the pixels Processing complete, container image Other pixels in the same way are processed as pixels. By processing the image using the method described above, the container image can ultimately be determined. The image contains all foreground and background pixels. Then, all background pixels are removed (the background portion is removed, and the pixels of the container itself are retained), resulting in a foreground container image that contains only the foreground pixels associated with the container. This image is denoted as [image name missing]. ;

[0130] At this point, the container image... After processing, the image set of the filling station is then processed: And a collection of container images: By repeating the above steps, a set of container images can be obtained: The foreground container images associated with all container images in the set are denoted as the foreground container image set, according to the sorting order of the container image set. ;

[0131] For the foreground container image set: Image fitting is performed to obtain a panoramic image associated with the container itself. Based on the determined correlation between the panoramic image and the actual dimensions of the container, the container volume is further determined, denoted as . ;

[0132] Then extract the filling percentage preset by the operator. Combined container volume Determine the filling volume associated with the current container. And operate the filling port to perform the filling operation, the filling volume is .

[0133] This embodiment extracts the filling station image set and the container image set from Embodiment 2. One image is taken from each set, and pixels are extracted in a specific order to form a sequence. Next, the pixel value difference rate between the filling station pixels and the container pixels is calculated. Based on the comparison of the difference rate with a preset threshold, foreground and background pixels are distinguished, and the container foreground pixels are retained to generate a foreground container image, forming a foreground container image set. Then, image fitting is performed on the foreground container image set to obtain a panoramic image of the container. The container volume is determined by combining this with the actual object size correlation. Then, based on the operator's preset filling percentage, the specific filling amount is determined, and finally, the filling port is operated to perform the filling operation. Through image processing and pixel analysis, the container volume is measured, providing crucial information for subsequent filling, thereby improving the automation and intelligence level of the entire filling process.

[0134] All data in the formulas described above are numerical calculations performed with dimensions removed. Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0135] The above description is merely an example and illustration of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the invention or exceed the scope defined in the claims, they should all fall within the protection scope of the present invention.

[0136] It should be stated that all user data collected in this application was collected with the user's consent and authorization. Furthermore, the uses of user data are legal and compliant, and the use and processing of user data comply with the relevant laws, regulations, and standards of the relevant regions.

Claims

1. A smart filling method, characterized in that, The method comprises the following steps: Step one, configure a pressure sensor on the bottom surface of the filling table to monitor whether a container enters the filling table, if not, continue to monitor; If yes, generate a first signal and transmit it to the terminal processor, and the terminal processor confirms the first signal to generate a detection instruction and transmit it to the camera cluster installed in the filling table area for image acquisition; The specific way of image acquisition is to transmit the detection instruction generated by the terminal processor to the camera cluster through the system bus; Let the camera cluster be denoted as A1, A2,..., A j where j is a count index, representing the total number of cameras in the camera cluster; A camera cluster is used to cover the entire filling table area in all directions, and when there is no container in the filling table area, the camera cluster performs shooting work to obtain j images, denoted as a filling table image set P1, P2,..., P j , wherein P i corresponds to A i , i is a count index, and the value range is 1 to j; When the camera cluster receives the detection instruction, the filling table area is photographed again, and j images obtained by photographing are recorded as a container image set P ' 1, P ' 2,..., P ' j Wherein the association between the container image and the filling table image and the actual size is one-to-one. Step two, extract the positional relationship between the filling port and the filling table, and jointly fit the images collected by the camera cluster into a standard filling plan; Based on the images collected by the camera cluster, extract the positional relationship between the container port and the filling table, and fit the to-be-filled plan; Verify the to-be-filled plan and the standard filling plan, and determine the abnormal filling condition and the normal filling condition based on the verification result; If the verification result is an abnormal filling condition, skip this filling operation and repeat steps one and two; If the verification result is a normal filling condition, go to step three; Step three, extract the images collected by the camera cluster again to construct a panoramic image of the current container and determine the container capacity; Based on the determined container capacity, further determine the filling amount and perform the filling operation.

2. A smart filling method as claimed in claim 1, wherein, In step one, the specific way of generating a detection instruction is: The initial value of the calibrated pressure sensor is 0; The value Q of the pressure sensor is obtained in real time through the edge processor connected to the pressure sensor; If Q > 0, a counter T built in the edge processor is triggered to start timing from 0 second, and T increases with time, if the length of the counter T timing is greater than the time threshold T preset by the operator yu Then it is determined that there is a container on the pressure sensor, a first signal is generated by the edge processor, and transmitted to the terminal processor through the system bus.

3. A smart filling method according to claim 2, characterized in that, In step two, the specific way of determining the abnormal filling condition and the normal filling condition based on the verification result is: A filling table image is extracted from P1, P2,..., P j and labeled as P α ; P α The first pixel point in the lower left corner as the origin, P α The left side boundary as the vertical axis, P α The lower side boundary as the horizontal axis to construct P α The associated two-dimensional coordinate system; Obtain the two-dimensional coordinates G1 of the center point of the filling port in the two-dimensional coordinate system, and extract the filling port radius r1 to draw a circle with G1 as the center and r1 as the radius, obtaining circle O1; Save the circle O1 at P α In the associated two-dimensional coordinate system, and the two-dimensional coordinate system at this time is recorded as the standard filling plan R Pα ; By analogy, from P ' 1, P ' 2,..., P ' j extract the container image from the top view of the filling station directly above, labeled P β , build the two-dimensional coordinate system associated with P β . determining P β a two-dimensional coordinate G2 corresponding to the center point of the container port on the two-dimensional coordinate system; Obtain the container port radius r2, draw a circle with G2 as the center and r2 as the radius, obtaining circle O2; Save the circle O2 in P β In the associated two-dimensional coordinate system, and the two-dimensional coordinate system at this time is recorded as the to-be-filled plan view R Pβ ; By aligning the coordinates, R Pβ With R Pα Superimposing them onto the same plane yields a planar image; At this time, circles O1 and O2 are placed in the same plane, and circles O1 and O2 are verified: If O1∈O2, it is determined that the verification result is a normal filling condition; If O1 O2, then the result of the check processing is determined to be an abnormal filling condition.

4. A smart filling method as claimed in claim 3, wherein, In step two, if it is determined that the verification result is an abnormal filling condition, skip the filling operation of the container; If it is determined that the verification result is a normal filling condition, further determine the capacity and filling amount of the container, and perform the filling operation.

5. A smart filling method as claimed in claim 4, characterized in that, The specific way of determining the capacity and filling amount of the container and performing the filling operation is: from the set of filling station images P1, P2,..., P j extracts an arbitrary filling station image P i from the set of container images P ' 1, P ' 2,..., P ' j extracts an arbitrary container image P ' i ; determining the filling station image P i and the container image P ' i the number of mid-pixels, and is denoted by m; P i The first pixel point of the filling table in the upper left corner is denoted as I1, and the last pixel point of the filling table in the lower right corner is denoted as I m ; The filling table pixel points in the filling table image P are extracted in the order from left to right and from top to bottom, obtaining a filling table pixel point sequence I1, I2,..., I i m m ; Similarly, the container pixel point sequence I is obtained ' 1, I ' 2,..., I ' m ; from I1, I2,..., I m any one of the filling station pixels I n ; From I ' 1, I ' 2,..., I ' m extracting any one of the container pixel points I n associated with the pixel point I ' n ; extracting I n pixel value F n and I ' n pixel value F ' n wherein n is a count index, and has a value range of 1 to m; Determination I n And I ' n The difference rate θ of the pixel values between them, compare the difference rate θ with the difference rate threshold θ yu preset by the operator; If θ > θ yu , then I ' n is a foreground pixel. If θ≤ θ yu , then view I ' n as a background pixel. perform the above steps on all the container pixels in P ' i to determine the foreground pixels and the background pixels in P ' i , eliminate the background pixels, and obtain the foreground container image P '' i ; P1, P2,..., P j and P ' 1, P ' 2,..., P ' j Repeat the above steps to obtain the foreground container image set: P '' 1, P '' 2,..., P '' j ; P ' 1,P ' 2,...,P ' j fitting, obtaining a panoramic image associated with the container, and determining the volume V of the container based on the panoramic image of the container and the association between the panoramic image of the container and the real dimensions. Extract the filling percentage δ preset by the operator to obtain the filling amount δ*V associated with the container, and perform the filling operation.

Images