An intelligent monitoring device for garbage classification based on image recognition

Abstract

The present invention discloses an intelligent monitoring device for garbage classification based on image recognition, comprising: an image recognition module, which is used for taking garbage photos in all directions and at multiple angles, collecting garbage feature vector sets, and determining whether the garbage is recyclable if the garbage material can be matched through similarity comparison, and if the matching fails, storing the photos and feature vector sets in a database, waiting for the manual auxiliary module to determine the garbage material; a manual auxiliary module, which is used for classifying the garbage into recyclable garbage and non-recyclable garbage, the image recognition module cannot detect whether the garbage is recyclable, and requires staff to assist computer intelligent learning, and the staff determines the garbage material by using the taken photos and feature vector sets; the photos, feature vector sets and garbage materials are stored in a database, and the image recognition module completes the automatic intelligent determination of whether the garbage is recyclable by continuously updating the database.

Description

Technical Field

[0001] The present invention relates to the technical field of garbage classification, and in particular to an intelligent monitoring device for garbage classification based on image recognition. Background Art

[0002] Garbage refers to useless solid or fluid materials abandoned in human production and life. With the continuous progress of society, people's living standards and consumption have significantly improved, and more and more garbage has been generated. Garbage disposal has always been a headache. Common garbage disposal methods are garbage incineration or landfill, but both will pollute the environment. Landfill garbage disposal will not only pollute groundwater and emit odor, but also reduce the land use area. Incineration will inevitably produce toxic gases and harm organisms.

[0003] Sorting garbage can reduce processing costs, reduce air and land pollution, and facilitate resource recycling. Traditional garbage sorting relies on manual sorting by sorters, and the average length of service for a garbage sorter is 2 ～ 3 years, any longer will cause irreversible damage to the body. Therefore, an intelligent monitoring garbage sorting device is needed to complete the garbage sorting work. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent monitoring device for garbage classification based on image recognition to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: An intelligent monitoring device for garbage classification based on image recognition, comprising: an image recognition module and a manual assistance module;

[0006] The image recognition module is used to take photos of garbage from all directions and angles, collect garbage feature vector sets, and if the garbage material can be matched through similarity comparison, it can be determined whether the garbage can be recycled. If the match fails, the photos and feature vector sets are stored in the database, waiting for the manual auxiliary module to determine the garbage material;

[0007] The manual assistance module is used to classify garbage into recyclable garbage and non-recyclable garbage. The image recognition module cannot detect whether the garbage is recyclable, and requires staff to assist computer intelligent learning. The staff uses the taken photos and feature vector sets to determine the garbage material; the photos, feature vector sets and garbage materials are stored in a database, and the image recognition module completes the automatic intelligent judgment of whether the garbage is recyclable by continuously updating the database.

[0008] The database includes: garbage ID, garbage photos, garbage quality, garbage feature vector set, length, width, height of spring iron plate under different forces, and garbage material, wherein the garbage ID is named according to the order of the time when the garbage photos are inserted.

[0009] The manual assistance module is also used to assist in the identification of garbage materials in the database; recyclable garbage includes waste paper, plastic, glass, metal, and cloth. As time goes by, the garbage materials in the database will gradually be improved.

[0010] The image recognition module includes a feature vector set submodule and a garbage material search submodule;

[0011] The feature vector set submodule calculates a feature vector set after the junk photo to be checked is processed by the image recognition module;

[0012] The garbage material search submodule searches for garbage materials in the database according to the similarity comparison result.

[0013] Firstly, the image recognition module is used to calculate the feature vector set of the garbage to be detected, and then a similarity operation is performed with the feature vector set of all garbage data in the database to obtain a similarity value with each type of garbage.

[0014]

[0015] Among them, R, T, and S represent the bulk density, transmittance, and scalability of the garbage feature vector set to be detected, respectively. Ri represents the bulk density of the i-th feature vector set in the database, Ti represents the transmittance of the i-th feature vector set in the database, and Si represents the scalability of the i-th feature vector set in the database. represents the success rate of garbage classification, d represents the similarity, and the smaller the d value, the higher the similarity. When the d value is less than the threshold, the garbage material corresponding to the i-th feature vector set is the garbage material of the garbage to be detected. The feature vector set and garbage material data of the garbage to be detected are stored in the database.

[0016] The image recognition module also includes:

[0017] The garbage sorting submodule uses a mechanical arm to move the garbage into the image recognition module area one by one, ensures that there is only one type of garbage in the shooting area, weighs the garbage, and stores the weighing result in the database, where the weighing result is recorded as M;

[0018] The shooting area submodule is used to clean the shooting area to ensure that the garbage photos are complete and clear. At the same time, a light-emitting device is installed on the surface of the shooting area, and a spring iron plate with a light intensity detector is installed on the top. Fixed spring iron plates with scales are installed on the left and rear, and movable spring iron plates are installed on the right, front and top. A camera is installed separately on the light intensity detector display screen.

[0019] The shooting and collection submodule collects the original garbage images and stores them in the database when the five spring iron plates are not under stress, so that the staff can identify them. When the five spring iron plates are under stress of 10 Newtons, the garbage photos are collected, and the scale readings in the photos are extracted to record the length, width, height and light receiving and luminous intensity of the garbage. The length, width and height are recorded as D1, W1 and H1, and the results are stored in the database. When the five spring iron plates are under stress of 20 Newtons, the photos are taken again, and the length, width and height of the scale in the photos are extracted and marked as D2, W2 and H2, and the results are stored in the database.

[0020] The GPS synchronization submodule has built-in GPS chips in all cameras and the speed control submodule to ensure that the same type of garbage is photographed at the same time. Whether the cameras are working normally is determined based on whether the number of photos taken at the same time is equal to the number of cameras.

[0021] The GPS synchronization submodule, GPS is a high-precision radio navigation positioning system based on artificial earth satellites, which provides clocks for devices that need to be synchronized with its high precision and all-weather; the GPS synchronization submodule provides an accurate clock for each camera equipped with a GPS chip to ensure time synchronization of all cameras.

[0022] The shooting and collecting submodule includes:

[0023] The image preprocessing submodule first uses grayscale and binary techniques to remove the junk photo background, then cuts out individual characters from the processed image and matches them with the pre-prepared digital module to extract the Arabic numerals in the photo;

[0024] The digital extraction submodule obtains the length, width and height of the corresponding garbage according to the digital pattern on the scale;

[0025] Detect the light intensity submodule, read the light intensity display screen photo, use grayscale and binary method to remove the background, then cut out single characters, and compare with the pre-prepared digital module to extract the Arabic numerals in the photo, which is the received light intensity.

[0026] The garbage sorting submodule includes:

[0027] The garbage pre-processing submodule uses a robotic arm to separate the garbage;

[0028] The garbage size processing submodule has a shooting area detection space of 2cm*2cm*2cm to 100cm*100cm*100cm. Garbage below 2cm*2cm*2cm is considered unrecyclable, and garbage exceeding 100cm*100cm*100cm needs to be split first.

[0029] The garbage sorting submodule also includes:

[0030] The speed adjustment submodule is used to intelligently adjust the conveyor belt speed. As the database is improved, the speed of garbage classification will be significantly improved.

[0031] The feature vector set includes: bulk density, light transmittance, and elasticity of the garbage after compression;

[0032] The bulk density refers to the weight of garbage per unit volume;

[0033] The light transmittance refers to the light intensity after the incident light intensity remains unchanged and passes through the test medium;

[0034] The elasticity is affected by external forces and the size of the fluctuation in the shape of the garbage material. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0036] Figure 1 This is a working diagram of the garbage classification intelligent monitoring device with image recognition in the present invention;

[0037] Figure 2 This is a schematic diagram of the structure of the image recognition module in the present invention;

[0038] Figure 3 It is a schematic diagram of the structure of the feature vector set in the present invention. DETAILED DESCRIPTION

[0039] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0040] like Figure 1 As shown, an embodiment of the present invention provides a garbage classification intelligent monitoring device based on image recognition, including: an image recognition module and a manual assistance module;

[0041] The image recognition module is used to take photos of garbage from all directions and angles, collect garbage feature vector sets, and if the garbage material can be matched through similarity comparison, it can be determined whether the garbage can be recycled. If the match fails, the photos and feature vector sets are stored in the database, waiting for the manual auxiliary module to determine the garbage material;

[0042] The manual assistance module is used to classify garbage into recyclable garbage and non-recyclable garbage. The image recognition module cannot detect whether the garbage is recyclable, and requires staff to assist computer intelligent learning. The staff uses the taken photos and feature vector sets to determine the garbage material; the photos, feature vector sets and garbage materials are stored in a database, and the image recognition module completes the automatic intelligent judgment of whether the garbage is recyclable by continuously updating the database.

[0043] The working principle of the above technical solution is: the camera takes photos of garbage from all directions and angles, and collects the feature vector set of the garbage. If the garbage material can be matched through similarity comparison, it can be determined whether the garbage is recyclable. If the match fails, the photos and the feature vector set are stored in the database, waiting for the manual auxiliary module to determine the garbage material; the staff determines the garbage material through the taken photos and the feature vector set and stores it in the database.

[0044] The beneficial effects of the above technical solution are: by determining the composition of garbage through photos and feature vector sets, workers can stay away from garbage plants and reduce physical harm; at the same time, as database information is continuously improved, more and more garbage can be compared with the garbage material by comparing the feature vector sets, so that the image recognition module can automatically and intelligently determine whether the garbage can be recycled.

[0045] In another embodiment, the technical solution of the present invention is an intelligent monitoring device for garbage classification based on image recognition, including the database, and the database fields include: garbage ID, garbage photos, garbage quality, garbage feature vector set, length, width, height of the spring iron plate under different forces, and garbage material, wherein the garbage ID is named in the order of the time when the garbage photos were inserted.

[0046] The working principle of the above technical solution is: the database stores all garbage information, among which the garbage material needs to be determined by staff, and the remaining fields are all intelligently identified by computers; at the same time, as time goes by, the garbage material field will become more perfect, and eventually the intelligent identification of garbage materials will be realized.

[0047] In another embodiment, the technical solution of the present invention is an intelligent monitoring device for garbage classification based on image recognition, including a manual assistance module for assisting in the identification of garbage materials in the database; recyclable garbage includes waste paper, plastic, glass, metal, and cloth. Over time, the garbage materials in the database will gradually be improved.

[0048] The working principle of the above technical solution is: garbage is divided into recyclable garbage and non-recyclable garbage. Recyclable garbage includes waste paper, plastic, glass, metal, and cloth. The staff identifies the garbage material to determine whether the garbage is recyclable.

[0049] like Figure 2As shown, the technical solution of the present invention is a garbage classification intelligent monitoring device based on image recognition, and the image recognition module includes a feature vector set submodule and a garbage material search submodule;

[0050] The feature vector set submodule calculates a feature vector set after the junk photo to be checked is processed by the image recognition module;

[0051] The garbage material search submodule searches for garbage materials in the database according to the similarity comparison result.

[0052] The working principle of the above technical solution is:

[0053] Firstly, the image recognition module is used to calculate the feature vector set of the garbage to be detected, and then a similarity operation is performed with the feature vector set of all garbage data in the database to obtain a similarity value with each type of garbage.

[0054]

[0055] Among them, R, T, and S represent the bulk density, transmittance, and scalability of the garbage feature vector set to be detected, respectively. Ri represents the bulk density of the i-th feature vector set in the database, Ti represents the transmittance of the i-th feature vector set in the database, and Si represents the scalability of the i-th feature vector set in the database. represents the success rate of garbage classification, d represents the similarity, and the smaller the d value, the higher the similarity. When the d value is less than the threshold, the garbage material corresponding to the i-th feature vector set is the garbage material of the garbage to be detected. The feature vector set and garbage material data of the garbage to be detected are stored in the database.

[0056] In another embodiment, the technical solution of the present invention is a garbage classification intelligent monitoring device based on image recognition, including an image recognition module:

[0057] The garbage sorting submodule uses a mechanical arm to move the garbage into the image recognition module area one by one, ensures that there is only one type of garbage in the shooting area, weighs the garbage, and stores the weighing results in the database;

[0058] The shooting area submodule is used to clean the shooting area to ensure that the garbage photos are complete and clear. At the same time, a light-emitting device is installed on the surface of the shooting area, and a spring iron plate with a light intensity detector is installed on the top. Fixed spring iron plates with scales are installed on the left and rear, and movable spring iron plates are installed on the right, front and top. A camera is installed separately on the light intensity detector display screen.

[0059] The shooting and collection submodule collects garbage images and stores them in the database for manual identification when the five spring iron plates are not subjected to force. When the five spring iron plates are subjected to a force of 10 Newtons, garbage photos are collected, and the scale readings in the photos are extracted to record the length, width, height and light receiving and luminous intensity of the garbage. The length, width and height are recorded as D1, W1 and H1, and the results are stored in the database. When the five spring iron plates are subjected to a force of 20 Newtons, photos are taken again, and the length, width and height of the scale in the photos are extracted and marked as D2, W2 and H2, and the results are stored in the database.

[0060] The GPS synchronization submodule has built-in GPS chips in all cameras and the speed control submodule to ensure that the same type of garbage is photographed at the same time. Whether the cameras are working normally is determined based on whether the number of photos taken at the same time is equal to the number of cameras.

[0061] The working principle of the above technical solution is as follows: the garbage sorting submodule uses a mechanical arm to move the garbage into the image recognition module area one by one, ensures that there is only one type of garbage in the shooting area and weighs the garbage, stores the weighing result in the database, and the weighing result is recorded as M; the shooting area submodule is used to clean the shooting area to ensure that the garbage photos are complete and clear; at the same time, a light-emitting device is installed on the surface of the shooting area, and the emitted light intensity is fixed at 10dBm. A spring iron plate with a light intensity detector is installed on the top, and a fixed spring iron plate with a scale is installed on the left and rear. The right, front and top are movable spring iron plates, and a camera is installed separately on the light intensity detector display screen. The light intensity detector is used to detect the light intensity after the light passes through the measured garbage, and the scale is used to measure the length, width and height of the compressed garbage. The shooting and collection submodule, when the five spring iron plates are not under stress, collects the original image of the garbage and stores it in the database for staff identification; when the five spring iron plates are all under stress of 10 Newtons, collect garbage photos, extract the scale readings in the photos, record the length, width, height and light receiving and luminous intensity of the garbage, and record the length, width and height as D1, W1, and H1, and store the results in the database; when the five spring iron plates are stressed to 20 Newtons, take photos again, extract the length, width and height of the scale in the photos, mark them as D2, W2, H2, and store the results in the database; the change in the appearance of the garbage under different stresses determines the elasticity of the garbage. The GPS synchronization submodule, all cameras and the speed control submodule have built-in GPS chips to ensure that the same type of garbage is photographed at the same time, and whether the camera is working normally is determined based on whether the number of photos taken at the same time is equal to the number of cameras. As the database continues to improve, the speed of garbage sorting and processing will gradually increase. The GPS synchronization submodule ensures the time synchronization of all cameras and determines that each group of photos taken is the same type of garbage.

[0062] In another embodiment, the technical solution of the present invention is an intelligent monitoring device for garbage classification based on image recognition, including a GPS synchronization submodule. GPS is a high-precision radio navigation positioning system based on artificial satellites, which provides clocks for devices that need to be synchronized with its high precision and all-weather. The GPS synchronization submodule provides an accurate clock for each camera equipped with a GPS chip to ensure time synchronization of all cameras.

[0063] The working principle of the above technical solution is: the GPS chip receives the clock provided by the artificial satellite to ensure that all cameras equipped with the GPS chip work at the same time.

[0064] In another embodiment, the technical solution of the present invention is a garbage classification intelligent monitoring device based on image recognition, and the shooting and collection submodule includes an image preprocessing submodule, a digital extraction submodule and a light intensity detection submodule.

[0065] The image preprocessing submodule first removes the junk photo background using grayscale and binary method techniques, then cuts out individual characters from the processed image and matches them with the pre-prepared digital module to extract the Arabic numerals in the photo;

[0066] The digital extraction submodule obtains the length, width and height of the corresponding garbage according to the digital pattern on the scale;

[0067] The light intensity detection submodule reads the light intensity display screen photo, removes the background using grayscale and binary methods, then cuts out individual characters, compares them with the pre-prepared digital module, extracts the Arabic numerals in the photo, and obtains the received light intensity.

[0068] The working principle of the above technical solution is: through computer image recognition technology, the numbers in the photo are obtained, and then matched according to the pre-prepared digital modules to obtain the length, width, height and light intensity of the garbage.

[0069] In another embodiment, the technical solution of the present invention is a garbage classification intelligent monitoring device based on image recognition, and the garbage sorting submodule includes a garbage pre-processing submodule and a garbage size processing submodule;

[0070] The garbage pre-processing submodule uses a robotic arm to separate the garbage;

[0071] The garbage size processing submodule has a shooting area detection space of 2cm*2cm*2cm to 100cm*100cm*100cm. Garbage below 2cm*2cm*2cm is considered unrecyclable, and garbage exceeding 100cm*100cm*100cm needs to be split first.

[0072] The working principle of the above technical solution is: use a robotic arm to separate the garbage, split the oversized garbage, discard the oversized garbage, and ensure that the garbage photos are complete and clear.

[0073] In another embodiment, the garbage classification intelligent monitoring device based on image recognition in the technical solution of the present invention further includes a garbage sorting submodule:

[0074] The speed adjustment submodule is used to intelligently adjust the conveyor belt speed. As the database is improved, the speed of garbage classification will be significantly improved.

[0075] The beneficial effects of the above technical solution are: factors affecting the conveyor belt speed include: computer operation speed, database perfection, camera shooting speed, and garbage size. Intelligently adjusting the conveyor belt speed can improve the efficiency of garbage sorting.

[0076] like Figure 3 As shown, the technical solution of the present invention is a garbage classification intelligent monitoring device based on image recognition, and the feature vector set includes: bulk density, light transmittance, and elasticity of the garbage after compression;

[0077] The bulk density refers to the weight of garbage per unit volume;

[0078] The light transmittance refers to the light intensity after the incident light intensity remains unchanged and passes through the test medium;

[0079] The elasticity is affected by external forces and the size of the fluctuation in the shape of the garbage material.

[0080] The working principle of the above technical solution is:

[0081] When the spring iron plate is subjected to a force of 10 Newtons, the weight / (length*width*height) weighed by the garbage sorting submodule represents the bulk density of the garbage, that is, R=M / D1*W1*H1;

[0082] The unit of light intensity detector is dBm. The conversion formula between power unit mw and dBm is mw=10^(dBm value / 10). The calculation formula can be used to get the light source emission power P0 and the power after passing through the garbage being tested P1. The transmittance T of the garbage can be obtained by (P0-P1) / P0.

[0083] When the spring iron plate is subjected to a force of 20 Newtons, its bulk density R1 = M / D1*W2*H2. The elasticity S of the garbage can be obtained by the calculation formula (R-R1) / R.

[0084] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent monitoring device for garbage classification based on image recognition, characterized in that: include: The image recognition module is used to take photos of garbage from all directions and angles and collect garbage feature vector sets. If the garbage material can be matched through similarity comparison, it can be determined whether the garbage can be recycled. If the match fails, the photos and feature vector sets are stored in the database, waiting for the manual auxiliary module to determine the garbage material; A manual assistance module is used to classify garbage into recyclable garbage and non-recyclable garbage. When the image recognition module cannot determine whether the garbage is recyclable, a staff member is required to assist the computer in intelligent learning, and the staff member determines the garbage material by using the photographed photos and feature vector sets; the photos, feature vector sets and garbage materials are stored in a database, and the image recognition module completes the automatic intelligent determination of whether the garbage is recyclable by continuously updating the database; The database includes: garbage ID, garbage photos, garbage quality, garbage feature vector set, length, width, height of spring iron plate under different forces, and garbage material, wherein the garbage ID is named according to the order of insertion time of garbage photos; The image recognition module also includes: The garbage sorting submodule uses a mechanical arm to move the garbage into the image recognition module area one by one, ensures that there is only one type of garbage in the shooting area, weighs the garbage, and stores the weighing result in the database, where the weighing result is recorded as M; The shooting area submodule is used to clean the shooting area to ensure that the garbage photos are complete and clear. At the same time, a light-emitting device is installed on the surface of the shooting area, and a spring iron plate with a light intensity detector is installed on the top. Fixed spring iron plates with scales are installed on the left and rear, and movable spring iron plates are installed on the right, front and top. A camera is installed separately on the light intensity detector display screen. The shooting and collection submodule collects the original garbage images and stores them in the database when the five spring iron plates are not under stress, so that the staff can identify them. When the five spring iron plates are under stress of 10 Newtons, the garbage photos are collected, and the scale readings in the photos are extracted to record the length, width, height and light intensity of the garbage. The length, width and height are recorded as D1, W1 and H1, and the results are stored in the database. When the five spring iron plates are under stress of 20 Newtons, the photos are taken again, and the length, width and height of the scale in the photos are extracted and marked as D2, W2 and H2, and the results are stored in the database. GPS synchronization submodule, all cameras and speed control submodules have built-in GPS chips to ensure that the same type of garbage is photographed at the same time. The camera is judged to be working properly based on whether the number of photos taken at the same time is equal to the number of cameras; First, the image recognition module is used to calculate the feature vector set of the garbage to be detected, and then a similarity operation is performed with the feature vector set of all garbage data in the database to obtain the similarity value with each type of garbage: Among them, R, T, and S represent the bulk density, transmittance, and scalability of the garbage feature vector set to be detected, respectively; Ri represents the bulk density of the i-th feature vector set in the database, Ti represents the transmittance of the i-th feature vector set in the database, and Si represents the scalability of the i-th feature vector set in the database. Represents the success rate of garbage classification, Represents similarity, The smaller the value, the higher the similarity; When the value is less than the threshold, the garbage material corresponding to the i-th feature vector set is the garbage material of the garbage to be detected; the feature vector set of the garbage to be detected and the garbage material data are stored in the database; The feature vector set includes: bulk density, light transmittance, and scalability of the compressed garbage; The bulk density refers to the weight of garbage per unit volume; The light transmittance refers to the light intensity after passing through the test medium without changing the incident light intensity. The elasticity refers to the fluctuation of the shape of the garbage material under the influence of external forces; When the spring iron plate is subjected to a force of 10 Newtons, the weight / (length*width*height) weighed by the garbage sorting submodule represents the bulk density of the garbage, that is, R=M / D1*W1*H1; The unit of light intensity detector is dBm. The conversion formula between power unit mw and dBm is mw=10^(dBm value / 10). The calculation formula can be used to get the light source emission power P0 and the power P1 after passing through the garbage being tested. The transmittance T of the garbage can be obtained by (P0-P1) / P0. The bulk density R1=M / D2*W2*H2 when the spring iron plate is subjected to a force of 20 Newtons. The elasticity S of the garbage can be obtained by the calculation formula (R-R1) / R.

2. The garbage classification intelligent monitoring device based on image recognition according to claim 1 is characterized in that: The manual assistance module is also used to assist in the identification of garbage materials in the database; recyclable garbage includes waste paper, plastic, glass, metal, and cloth.

3. The garbage classification intelligent monitoring device based on image recognition according to claim 1 is characterized in that: The GPS synchronization submodule provides a precise clock for each camera equipped with a GPS chip, ensuring that all cameras are time synchronized.

4. The garbage classification intelligent monitoring device based on image recognition according to claim 1 is characterized in that: The shooting and collecting submodule includes: The image preprocessing submodule first removes the junk photo background using grayscale and binary methods, then cuts out individual characters from the processed image and matches them with the pre-prepared digital module to extract the Arabic numerals in the photo; The digital extraction submodule obtains the length, width and height of the corresponding garbage according to the digital pattern on the scale; Detect the light intensity submodule, read the light intensity display screen photo, use grayscale and binary method to remove the background, then cut out single characters, and compare with the pre-prepared digital module to extract the Arabic numerals in the photo, which is the received light intensity.

5. The garbage classification intelligent monitoring device based on image recognition according to claim 1 is characterized in that: The garbage sorting submodule includes: The garbage pre-processing submodule uses a robotic arm to separate the garbage; The garbage size processing submodule has a shooting area detection space of 2cm*2cm*2cm to 100cm*100cm*100cm. Garbage smaller than 2cm*2cm*2cm is deemed unrecyclable, and garbage exceeding 100cm*100cm*100cm needs to be split first.

6. The garbage classification intelligent monitoring device based on image recognition according to claim 1 is characterized in that: The garbage sorting submodule also includes: The speed adjustment submodule is used to intelligently adjust the conveyor belt speed.

Images