An automatic garbage classification system based on volume

Abstract

This invention relates to the field of classification system technology, specifically to a volume-based automatic waste classification system. The system includes a feeding conveyor module, a perforated plate assembly, a support tube unit, a sorting conveyor module, a guide shield assembly, and a receiving conveyor module. Waste is transported to the perforated plate assembly via the feeding conveyor module. The perforated plate assembly has through-holes. The support tube unit is a tubular structure and is perpendicular to the surface of the perforated plate assembly. This volume-based automatic waste classification system effectively reduces the mixing of long, thin pieces of waste with smaller volumes of waste during the screening process, thus improving the classification efficiency of the automatic waste classification system.

Description

Technical Field

[0001] The present invention relates to the technical field of classification systems, and in particular to an automatic garbage classification system based on volume. Background Art

[0002] In the process of centralized treatment of large amounts of garbage, in order to meet the treatment needs, the garbage needs to be screened and classified according to volume. The most common classification method in traditional technology is to screen through a screen with vibration. Large-volume garbage remains on the screen, and small-volume garbage is screened and falls down; in actual work, due to the non-fixed shape of garbage, there are some long or rod-shaped garbage, such as various types of pipe garbage. During the screening process, the long-shaped garbage can easily pass through the screen holes and enter the small-volume garbage below. However, since the long-shaped garbage itself is large in volume, when the length is greater than a certain extent, it is not convenient for subsequent processing, and it needs to be picked out manually, which increases the cost of labor occupation. Summary of the invention

[0003] The object of the present invention is to provide a volume-based automatic garbage classification system to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a volume-based garbage automatic sorting system, comprising a feeding conveyor belt module, a mesh plate assembly, a supporting pipe unit, a combing conveyor belt module, a guide shield assembly and a receiving conveyor belt module, the garbage is transported to the mesh plate assembly through the feeding conveyor belt module, the mesh plate assembly is penetrated with sieve holes, the supporting pipe unit is a tubular structure, the supporting pipe unit is perpendicular to the surface of the mesh plate assembly, the upper end of the supporting pipe unit is correspondingly connected to the sieve holes opened on the mesh plate assembly, the lower end of the supporting pipe unit is open, the garbage on the mesh plate assembly is screened through the sieve holes, the garbage that can pass through the sieve holes will slide down through the supporting pipe unit, the combing conveyor belt module is arranged below the supporting pipe unit to receive the garbage that slides down in the supporting pipe unit, and a guide shield assembly is arranged between the supporting pipe unit and the combing conveyor belt module. The guide baffle assembly is composed of mutually parallel plate structures, the plane where the plate structures are located is parallel to the running direction of the combing conveyor belt module, the plane where the plate structures are located is parallel to the center line of the supporting pipe unit, and the guide baffle assembly corresponds to the supporting pipe unit up and down; when the long strips of garbage pass through the sieve holes on the mesh plate assembly, they are first limited by the supporting pipe unit and enter between the guide baffle assemblies, and the guide baffle assembly limits the long strips of garbage perpendicular to the running direction of the combing conveyor belt module, so that the long strips of garbage are parallel to the running direction of the combing conveyor belt module when they fall on the combing conveyor belt module, and the output end of the combing conveyor belt module is flush with a receiving conveyor belt module at a certain distance, and garbage with a length greater than twice the distance between the combing conveyor belt module and the receiving conveyor belt module can be transported by the combing conveyor belt module to the receiving conveyor belt module.

[0005] The output end of the mesh plate assembly is provided with a first-level receiving bucket, and the first-level receiving bucket is used to receive garbage that cannot pass through the sieve holes on the mesh plate assembly. A screened material receiving bucket is provided between the combing conveyor belt module and the receiving conveyor belt module, and the screened material receiving bucket is used to receive garbage dropped between the combing conveyor belt module and the receiving conveyor belt module. The output end of the receiving conveyor belt module is provided with a second-level receiving bucket for receiving garbage.

[0006] The mesh plate assembly is provided with a vibration unit, which has horizontal vibration and up and down vibration functions. The vibration unit causes the garbage on the mesh plate assembly to flow in a directional manner through horizontal vibration.

[0007] An industrial camera is arranged above the mesh plate assembly, and an operation processing module is arranged outside the industrial camera. A control algorithm is arranged in the operation processing module. The control algorithm detects the flow of garbage on the mesh plate assembly through the industrial camera, and the control algorithm performs feedback control on the vibration unit based on the detection of the industrial camera.

[0008] The control algorithm specifically includes: using an industrial camera to collect images of the mesh plate assembly in a normal garbage-free state in advance, obtaining image information of all fixed components, extracting features from the collected fixed component images, and storing these feature data in a device information database as a basis for subsequently distinguishing between fixed components and garbage; setting a time threshold for determining if garbage is stuck, that is, how long does it take for the garbage to be judged as stuck without displacement; setting an area accumulation value, that is, providing feedback when the total area of ​​stuck garbage exceeds this value.

[0009] According to the set image acquisition frame rate, an industrial camera is used to capture real-time images of the garbage on the mesh plate assembly to obtain a continuous image sequence, and each captured image is grayed and filtered. For each processed image, the pre-stored feature information of the fixed parts of the equipment is used for identification. For each area in the image, the same type of features as when the equipment information was entered are extracted, and then matched with the fixed part features in the database. When the features of a certain area successfully match the fixed part features, the area is marked as a fixed part area and ignored in the subsequent garbage detection process to avoid misjudging it as stuck garbage.

[0010] Inter-frame analysis is performed on continuous image sequences to determine the movement state of the garbage. The difference image between two adjacent frames is calculated. For the t-th frame and the t+1-th frame, the difference is calculated pixel by pixel to obtain the differential image. In the differential image, the area with a value greater than a certain value indicates that a change has occurred between the two frames, that is, the garbage is moving.

[0011] Connected region analysis is performed on the differential image, and adjacent pixels with a difference greater than a certain value are divided into the same connected region. Each connected region can be regarded as a potential moving garbage region. A unique identifier is assigned to each connected region, and the position changes of these regions are tracked in subsequent image frames. The position of the region is described by calculating the center of mass position of the region, and the position changes of the same identified region in adjacent frames are compared. If the position change of a region in several consecutive frames is less than a certain threshold, it is determined that the garbage in the region is stuck.

[0012] When garbage jam is detected, the area of ​​the jammed garbage region is calculated. For each connected area determined to be jammed garbage, its area is approximately calculated by counting the number of pixels in the area. The area of ​​each detected jammed garbage is accumulated into a total area accumulation variable for subsequent comparison with the set area accumulation threshold.

[0013] The area accumulation variable is compared with the set area accumulation threshold in real time. If the area accumulation exceeds the threshold, the algorithm triggers the feedback mechanism. At this time, the calculation processing module sends a signal to the vibration unit, causing the vibration unit to vibrate up and down for a certain period of time.

[0014] Compared with the prior art, the present invention has the following beneficial effects:

[0015] The volume-based automatic garbage classification system of the present invention can sort out long strips of garbage passing through the sieve holes when screening and classifying garbage based on volume, thereby effectively reducing the mixing of long strips of garbage passing through the sieve holes in the small volume of garbage under the sieve during the garbage screening process, thereby improving the classification effect of the automatic garbage classification system.

[0016] The present invention cooperates with structures such as industrial cameras and vibration units to detect the flow of garbage through visual analysis. When a jamming problem occurs, the vibration unit drives the mesh plate assembly to vibrate up and down, so that the jammed garbage can be separated from the sieve holes, thereby realizing an automatic anti-jamming function.

[0017] The control algorithm of the present invention can improve the working efficiency of the mesh plate assembly; the algorithm can detect the area of ​​stuck garbage in real time, so that when the area of ​​stuck garbage is below a certain threshold, the mesh plate assembly can maintain normal screening work; when the area of ​​stuck garbage is above a certain threshold, the vibration unit is used to control the mesh plate assembly to vibrate up and down to achieve jamming and disengagement, thereby avoiding frequent up and down vibration of the mesh plate assembly, which affects the horizontal vibration screening and conveying work. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Schematic diagram of the volume-based automatic garbage classification system of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0020] See also Figure 1 The present invention provides a technical solution: a volume-based garbage automatic classification system, comprising a material conveyor belt module 1, a mesh plate assembly 2, a pipe support unit 3, a combing conveyor belt module 4, a guide shield assembly 5 and a receiving conveyor belt module 6. The garbage is transported to the mesh plate assembly 2 through the material conveyor belt module 1. The mesh plate assembly 2 is provided with sieve holes. The pipe support unit 3 is a tubular structure. The pipe support unit 3 is perpendicular to the surface of the mesh plate assembly 2. The upper end of the pipe support unit 3 is correspondingly connected to the sieve holes provided on the mesh plate assembly 2.

[0021] The lower end of the support pipe unit 3 is open, and the garbage on the mesh plate assembly 2 is screened through the sieve holes. The garbage that can pass through the sieve holes will slide down through the support pipe unit 3. The combing conveyor belt module 4 is arranged below the support pipe unit 3 to receive the garbage that slides down from the support pipe unit 3. A guide baffle assembly 5 is arranged between the support pipe unit 3 and the combing conveyor belt module 4. The guide baffle assembly 5 is composed of mutually parallel plate structures. The plane where the above plate structures are located is parallel to the running direction of the combing conveyor belt module 4. The plane where the above plate structures are located is parallel to the center line of the support pipe unit 3. The guide baffle assembly 5 corresponds to the support pipe unit 3 up and down.

[0022] When the long strips of garbage pass through the sieve holes on the mesh plate assembly 2, they are first limited by the supporting pipe unit 3 and enter between the guide baffle assembly 5. The guide baffle assembly 5 limits the long strips of garbage perpendicular to the running direction of the combing conveyor belt module 4, so that the long strips of garbage are parallel to the running direction of the combing conveyor belt module 4 when they fall on the combing conveyor belt module 4. The output end of the combing conveyor belt module 4 is flush with a receiving conveyor belt module 6 at a certain distance. Garbage with a length greater than twice the distance between the combing conveyor belt module 4 and the receiving conveyor belt module 6 can be transported by the combing conveyor belt module 4 to the receiving conveyor belt module 6. The sieve holes on the mesh plate assembly 2 are circular, and the aperture of the sieve holes is the same as the inner diameter of the support pipe unit 3; the guide shield assembly 5 is composed of parallel plate structures, and the spacing between the plate structures is equal to the inner diameter of the support pipe unit 3, so that the garbage can just enter between the parallel plate structures after being discharged through the support pipe unit 3, but avoid the parallel plate structures being too large. The larger the spacing, the worse the limiting effect on the long strips of garbage, and the lower the parallelism between the long strips of garbage and the running direction of the combing conveyor belt module 4; the lower part of a support pipe unit 3 corresponds to a guide shield assembly 5 composed of two parallel plate structures.

[0023] A first-level receiving bucket 7 is provided at the output end of the mesh plate assembly 2, and the first-level receiving bucket 7 is used to receive garbage that cannot pass through the sieve holes on the mesh plate assembly 2. A screened material receiving bucket 8 is provided between the combing conveyor belt module 4 and the receiving conveyor belt module 6. The screened material receiving bucket 8 is used to receive the garbage dropped between the combing conveyor belt module 4 and the receiving conveyor belt module 6. A second-level receiving bucket 9 for receiving garbage is provided at the output end of the receiving conveyor belt module 6.

[0024] A vibration unit 21 is provided on the mesh plate assembly 2. The vibration unit 21 has horizontal vibration and up and down vibration functions. The vibration unit 21 is composed of two groups of linear vibration motors. One group of linear vibration motors is parallel to the upper surface of the mesh plate assembly 2 and is used for horizontal vibration; the other group of linear vibration motors is perpendicular to the upper surface of the mesh plate assembly 2 and is used for up and down vibration. The vibration unit 21 causes the garbage on the mesh plate assembly 2 to flow in a directional manner through horizontal vibration.

[0025] An industrial camera 22 is arranged above the mesh plate assembly 2, and an operation processing module 23 is arranged outside the industrial camera 22. The operation processing module 23 is composed of a central processing unit, a cache chip, a storage chip and an additional circuit. A control algorithm is arranged in the operation processing module 23. The control algorithm detects the flow of garbage on the mesh plate assembly 2 through the industrial camera 22. The control algorithm performs feedback control on the vibration unit 21 based on the detection of the industrial camera 22.

[0026] The control algorithm specifically includes: using the industrial camera 22 to collect images of the mesh plate assembly 2 in a normal garbage-free state in advance, obtaining image information of all fixed components, extracting features from the collected fixed component images, and storing these feature data in the device information database as a basis for distinguishing fixed components from garbage in the future; setting a time threshold for judging that garbage is stuck, that is, how long does it take for the garbage to be judged as stuck without displacement; setting an area accumulation value, that is, providing feedback when the total area of ​​stuck garbage exceeds this value. The time threshold, area accumulation value, etc. are all set manually according to needs.

[0027] According to the set image acquisition frame rate, the industrial camera 22 is used to collect real-time images of the garbage on the mesh plate assembly 2 to obtain a continuous image sequence, and each collected image is grayed and filtered; the graying process averages the values ​​of the three RGB channels of each pixel in the color image as the gray value of the pixel, and the formula is as follows: ,in is the grayscale value, R, G, and B are the values ​​of the red, green, and blue channels of the color pixel respectively;

[0028] Image filtering uses a template to cover each pixel in the image, calculates the average value of the pixels in the area covered by the template, and uses this average value as the new value of the center pixel of the template. The filter template, let the coordinates of the pixels in the template be , the pixel value is , the pixel value after filtering ,in is the coordinate of the center pixel of the template, , , .

[0029] For each processed image, the pre-stored feature information of the fixed parts of the equipment is used for identification. For each area in the image, the same type of features as when the equipment information was entered, such as edge, shape, texture, and color, are extracted, and then matched with the fixed part features in the database. For example, in edge feature matching, the edges in the image can be detected using algorithms such as Hough transform and compared with the edge model of the fixed part; for shape feature matching, the similarity between the image area and the shape of the fixed part can be calculated using a shape descriptor-based method; texture feature matching can be judged by calculating the distance between the texture feature vector of the image area and the texture feature vector of the fixed part; color feature matching compares the color histogram of the image area with the color histogram of the fixed part. When the features of a certain area successfully match the fixed part features, the area is marked as a fixed part area, and the area is ignored in the subsequent garbage detection process to avoid misjudging it as stuck garbage.

[0030] Inter-frame analysis is performed on continuous image sequences to determine the movement state of the garbage. The difference image between two adjacent frames is calculated. For the t-th frame and the t+1-th frame, the difference is calculated pixel by pixel to obtain the differential image. In the differential image, the area with a value greater than a certain value indicates that a change has occurred between the two frames, that is, the garbage is moving.

[0031] Connected region analysis is performed on the differential image, and adjacent pixels with a difference greater than a certain value are divided into the same connected region. Each connected region can be regarded as a potential moving garbage region. A unique identifier is assigned to each connected region, and the position changes of these regions are tracked in subsequent image frames. The position of the region is described by calculating the center of mass position of the region, and the position changes of the same identified region in adjacent frames are compared. If the position change of a region in several consecutive frames is less than a certain threshold, it is determined that the garbage in the region is stuck.

[0032] The calculation of the centroid position of the region specifically includes: assuming that the connected region contains N pixels, The coordinates of the pixel point in the image coordinate system are ,calculate Center of mass coordinates of the direction , , the sum is for all pixels in the connected area The coordinates are accumulated and then divided by the total number of pixels N in the connected area; calculate Center of mass coordinates of the direction , , and similarly for all pixels in the connected area The coordinates are accumulated and then divided by the total number of pixels N; the coordinates of the centroid position of the connected area are obtained as follows: .

[0033] When garbage jam is detected, the area of ​​the jammed garbage region is calculated. For each connected area determined to be jammed garbage, its area is approximately calculated by counting the number of pixels in the area. The area of ​​each detected jammed garbage is accumulated into a total area accumulation variable for subsequent comparison with the set area accumulation threshold.

[0034] The area accumulation variable is compared with the set area accumulation threshold in real time. If the area accumulation exceeds the threshold, the algorithm triggers the feedback mechanism. At this time, the operation processing module 23 sends a signal to the vibration unit 21, causing the vibration unit 21 to vibrate up and down for a certain period of time. The up and down vibration of the vibration unit 21 can drive the mesh plate assembly 2 to vibrate up and down. At this time, the garbage stuck in the sieve hole will be separated from the sieve hole through the up and down vibration.

[0035] The garbage is transported to the mesh plate assembly 2 through the unloading conveyor belt module 1, and the vibration unit 21 drives the mesh plate assembly 2 to vibrate horizontally. Through the horizontal vibration, the garbage on the mesh plate assembly 2 is directed to flow toward the first-level receiving bucket 7. Small-volume garbage falls through the sieve holes on the mesh plate assembly 2, and large-volume garbage enters the first-level receiving bucket 7.

[0036] Small-volume garbage falls into the supporting pipe unit 3 through the sieve holes on the mesh plate assembly 2, reaches the combing conveyor belt module 4 through the guide shield assembly 5, is transported by the combing conveyor belt module 4, falls between the combing conveyor belt module 4 and the receiving conveyor belt module 6, and finally enters the under-screen receiving bucket 8; during the screening process of the mesh plate assembly 2, some long-shaped garbage will also fall into the supporting pipe unit 3 through the sieve holes. The supporting pipe unit 3 is limited to keep the long-shaped garbage in a roughly vertical state during the falling process. After entering the baffle assembly 5, the guide baffle assembly 5 limits the long strips of garbage to prevent the long strips of garbage from falling down perpendicular to the running direction of the combing conveyor belt module 4; because the combing conveyor belt module 4 is in the process of rapid transportation, the bottom of the long strips of garbage contacts the upper surface of the combing conveyor belt module 4. Driven by the combing conveyor belt module 4, the bottom of the long strips of garbage moves to the right and falls onto the combing conveyor belt module 4 parallel to the surface of the guide baffle assembly 5, so that the long strips of garbage are as parallel to the running direction of the combing conveyor belt module 4 as possible.

[0037] When the length of the long strips of garbage is greater than twice the distance between the combing conveyor belt module 4 and the receiving conveyor belt module 6, the long strips of garbage can be pushed to the receiving conveyor belt module 6 through the transmission of the combing conveyor belt module 4, and then transmitted to the secondary receiving bucket 9 through the receiving conveyor belt module 6 for classification, thereby reducing the probability of garbage that is too long appearing in the receiving bucket 8 of the screened material.

[0038] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A volume-based garbage automatic classification system, comprising a feeding conveyor belt module, a mesh plate assembly, a pipe support unit, a combing conveyor belt module, a guide shield assembly and a receiving conveyor belt module, characterized in that: The garbage is transported to the mesh plate assembly through the unloading conveyor belt module, and the mesh plate assembly is penetrated with sieve holes. The support pipe unit is a tubular structure, and the support pipe unit is perpendicular to the surface of the mesh plate assembly. The upper end of the support pipe unit is correspondingly connected to the sieve holes opened on the mesh plate assembly, and the lower end of the support pipe unit is open. The garbage on the mesh plate assembly is screened through the sieve holes, and the garbage that can pass through the sieve holes will slide down through the support pipe unit. The combing conveyor belt module is arranged below the support pipe unit to receive the garbage that slides down in the support pipe unit. A guide baffle assembly is arranged between the support pipe unit and the combing conveyor belt module, and the guide baffle assembly is composed of plate structures parallel to each other, and the plane where the above-mentioned plate structures are located is parallel to the combing belt module. The running direction of the combing conveyor belt module is parallel, the plane where the plate-like structure is located is parallel to the center line of the supporting pipe unit, and the guide baffle assembly corresponds to the supporting pipe unit up and down; when the long strips of garbage pass through the sieve holes on the mesh plate assembly, they are first limited by the supporting pipe unit and enter between the guide baffle assemblies, and the guide baffle assembly limits the long strips of garbage perpendicular to the running direction of the combing conveyor belt module, so that the long strips of garbage are parallel to the running direction of the combing conveyor belt module when they fall on the combing conveyor belt module, and the output end of the combing conveyor belt module is aligned with a receiving conveyor belt module at a certain distance, and garbage with a length greater than twice the distance between the combing conveyor belt module and the receiving conveyor belt module can be transported by the combing conveyor belt module to the receiving conveyor belt module; The mesh plate assembly is provided with a vibration unit, which has horizontal vibration and up and down vibration functions. The vibration unit makes the garbage on the mesh plate assembly flow in a directional manner through horizontal vibration; an industrial camera is provided above the mesh plate assembly, and an operation processing module is provided outside the industrial camera. A control algorithm is provided in the operation processing module, and the control algorithm detects the flow of garbage on the mesh plate assembly through the industrial camera. The control algorithm performs feedback control on the vibration unit based on the detection of the industrial camera; the control algorithm specifically includes: using the industrial camera to collect images of the mesh plate assembly in a normal garbage-free state in advance, obtaining image information of all fixed components, extracting features from the collected fixed component images, and storing these feature data in the equipment information database as a basis for distinguishing fixed components from garbage in the future; setting a time threshold for judging whether the garbage is stuck, that is, how long the garbage is judged to be stuck if it has no displacement; setting an area accumulation value, that is, providing feedback when the total area of ​​stuck garbage exceeds this value.

2. The volume-based automatic garbage classification system according to claim 1, characterized in that: The output end of the mesh plate assembly is provided with a first-level receiving bucket, and the first-level receiving bucket is used to receive garbage that cannot pass through the sieve holes on the mesh plate assembly. A screened material receiving bucket is provided between the combing conveyor belt module and the receiving conveyor belt module, and the screened material receiving bucket is used to receive garbage dropped between the combing conveyor belt module and the receiving conveyor belt module. The output end of the receiving conveyor belt module is provided with a second-level receiving bucket for receiving garbage.

3. The volume-based automatic garbage classification system according to claim 1, characterized in that: According to the set image acquisition frame rate, an industrial camera is used to acquire real-time images of the garbage on the mesh plate assembly to obtain a continuous image sequence, and each acquired image is grayed and filtered; Grayscale processing takes the average value of the three RGB channels of each pixel in the color image as the grayscale value of the pixel. The formula is as follows: ,in is the grayscale value, R, G, and B are the values ​​of the red, green, and blue channels of the color pixel respectively; Image filtering uses a template to cover each pixel in the image, calculates the average value of the pixels in the area covered by the template, and uses this average value as the new value of the center pixel of the template. The filter template, let the coordinates of the pixels in the template be , the pixel value is , the pixel value after filtering ,in is the coordinate of the center pixel of the template, , , ; For each processed image, the pre-stored feature information of the fixed parts of the equipment is used for identification. For each area in the image, the same type of features as when the equipment information was entered are extracted, and then matched with the fixed part features in the database. When the features of a certain area successfully match the fixed part features, the area is marked as a fixed part area and ignored in the subsequent garbage detection process to avoid misjudging it as stuck garbage.

4. The volume-based automatic garbage classification system according to claim 3 is characterized by: Inter-frame analysis is performed on continuous image sequences to determine the movement state of the garbage. The difference image between two adjacent frames is calculated. For the t-th frame and the t+1-th frame, the difference is calculated pixel by pixel to obtain the differential image. In the differential image, the area with a value greater than a certain value indicates that a change has occurred between the two frames, that is, the garbage is moving.

5. The volume-based automatic garbage classification system according to claim 4, characterized in that: Connected region analysis is performed on the differential image. Adjacent pixels with a difference greater than a certain value are divided into the same connected region. Each connected region can be regarded as a potential moving garbage region. A unique identifier is assigned to each connected region, and the position changes of these regions are tracked in subsequent image frames. The position of the region is described by calculating the centroid position of the region, and the position changes of the same identified region in adjacent frames are compared. If the position change of a region in several consecutive frames is less than a certain threshold, the garbage in the region is determined to be stuck. The calculation of the centroid position of the region specifically includes: assuming that the connected region contains N pixels, The coordinates of the pixel point in the image coordinate system are ,calculate Center of mass coordinates of the direction , , the sum is for all pixels in the connected area The coordinates are accumulated and then divided by the total number of pixels N in the connected area; calculate Center of mass coordinates of the direction , , and similarly for all pixels in the connected area The coordinates are accumulated and then divided by the total number of pixels N; the coordinates of the centroid position of the connected area are obtained as follows: .

6. The volume-based automatic garbage classification system according to claim 5, characterized in that: When garbage jam is detected, the area of ​​the jammed garbage region is calculated. For each connected region of garbage that is determined to be jammed, its area is approximately calculated by counting the number of pixels in the region; The area of ​​stuck garbage detected each time is accumulated into a total area accumulation variable for subsequent comparison with the set area accumulation threshold.

7. The volume-based automatic garbage classification system according to claim 6, characterized in that: The area accumulation variable is compared with the set area accumulation threshold in real time. If the area accumulation exceeds the threshold, the algorithm triggers the feedback mechanism. At this time, the calculation processing module sends a signal to the vibration unit, causing the vibration unit to vibrate up and down for a certain period of time.

Images