Plastic binary classification system and method based on dual-channel infrared camera

Abstract

The invention belongs to the technical field of spectral imaging, and particularly relates to a plastic dichotomy system and method based on a dual-channel infrared camera. Comprising the steps that S1, to-be-classified plastics are conveyed by a conveying mechanism, and images of the to-be-classified plastics are collected by a double-channel infrared camera; s2, the upper computer carries out binary classification judgment on the to-be-classified plastic based on the image of the to-be-classified plastic, and a judgment result is converted into a control parameter of an air injection mechanism; and S3, the air injection mechanism conducts separation operation on the to-be-classified plastic according to the control parameters, so that the to-be-classified plastic correspondingly falls into the first plastic collecting device or the second plastic collecting device. The problems that an existing plastic sorting technology is low in plastic recognition accuracy, long in test time consumption and low in precision can be solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of spectral imaging, and in particular relates to a plastic binary classification system and method based on a dual-channel infrared camera. Background Art

[0002] Plastics have been widely used in production and life due to their low cost, easy processing, strong durability and other advantages. They are important basic materials. At present, my country's plastics industry is developing rapidly. The irregular recycling and disposal of a large amount of plastic waste has caused great energy waste and serious pollution to the environment. At present, there are various technologies for identifying plastic types, but the recognition accuracy is low, the test takes a long time, and the accuracy is not high, which seriously restricts the production capacity of plastic recycling companies. The existing method of sorting and recycling plastics using spectral signals can greatly improve work efficiency and protect the environment. Existing spectral solutions for plastic sorting mostly use hyperspectral cameras or pseudo-multispectral methods composed of multiple single-spectral cameras for plastic sorting; hyperspectral cameras can only use array cameras, which obviously wastes resources for the binary classification of plastics, and the use of two single-spectral cameras for sorting has the disadvantages of not being able to share the same field of view and having high requirements for the algorithm. Summary of the invention

[0003] In view of this, the present invention aims to provide a plastic binary classification system and method based on a dual-channel infrared camera to solve the problems of low plastic recognition accuracy, long testing time and low precision in existing plastic sorting technologies.

[0004] To achieve the above object, the technical solution created by the present invention is implemented as follows: A plastic binary classification system based on a dual-channel infrared camera, comprising a conveying mechanism, a dual-channel infrared camera, a host computer, an air jet mechanism, a first plastic collecting device and a second plastic collecting device, wherein the dual-channel infrared camera is placed directly above the conveying mechanism, the dual-channel infrared camera is connected to the host computer, and the host computer is connected to the air jet mechanism; The conveying mechanism transports the plastics to be classified, and the dual-channel infrared camera collects images of the plastics to be classified; the upper computer performs a binary classification judgment on the plastics to be classified based on the images of the plastics to be classified, and converts the judgment result into a control parameter of the jet mechanism, and the jet mechanism performs a separation operation on the plastics to be classified according to the control parameters, so that the plastics to be classified fall to the first plastic collection device or the second plastic collection device accordingly.

[0005] Furthermore, the first plastic collecting device is placed at the end of the conveying mechanism to collect plastic dropped from the conveyor belt of the conveying mechanism; the installation position of the second plastic collecting device corresponds to the jet direction of the jet mechanism to collect plastic blown off the conveying mechanism by the jet mechanism.

[0006] Furthermore, the host computer includes a computer.

[0007] Furthermore, the jet mechanism includes an air valve, which is opened or closed according to the control parameters to adjust the jet state of the jet mechanism to achieve the separation operation of the mixed plastics.

[0008] Furthermore, the mixed plastic includes a first type of plastic and a second type of plastic, the first plastic collecting device collects the first type of plastic, and the second plastic collecting device collects the second type of plastic.

[0009] A plastic binary classification method based on a dual-channel infrared camera is implemented using a plastic binary classification system based on a dual-channel infrared camera, and specifically includes the following steps: S1: The conveyor mechanism transports the plastics to be classified, and the dual-channel infrared camera collects images of the plastics to be classified; S2: The upper computer performs binary classification of the plastic to be classified based on the image of the plastic to be classified, and converts the judgment result into the control parameter of the jet mechanism; S3: The jet mechanism performs separation operation on the plastics to be classified according to the control parameters, so that the plastics to be classified fall to the first plastic collecting device or the second plastic collecting device accordingly.

[0010] Furthermore, in step S1, two channels of a dual-channel infrared camera are used to simultaneously image the plastics to be classified, thereby obtaining a first infrared image and a second infrared image.

[0011] Furthermore, in step S2, the specific steps of the upper computer performing binary classification judgment on the plastic to be classified based on the image of the plastic to be classified are as follows: S21: using two channels of a dual-channel infrared camera to simultaneously image a 100% diffuse reflection whiteboard to obtain a first whiteboard image and a second whiteboard image; S22: placing the dual-channel infrared camera in a dark room environment for shooting, and obtaining dark noise of the dual-channel infrared camera; S23: Calculate the reflectivity of the plastic to be classified in the i-th spectral band by the following formula : ; Where i is 1 or 2, is the reflectance of the plastic to be classified in the first spectral band, is the reflectance of the plastic to be classified in the second spectral band, is the first infrared image, is the second infrared image, is the first whiteboard image, is the second whiteboard image, is the dark noise of the dual-channel infrared camera; S24: Normalize the reflectance of the plastic to be classified in each spectral band to obtain the normalized spectral coefficient ND : ; S25: repeating steps S23 to S24, replacing the plastic to be classified with the first type of plastic and the second type of plastic in turn, to obtain a normalized spectral coefficient ND1 of the first type of plastic and a normalized spectral coefficient ND2 of the second type of plastic; S26: Normalized spectral coefficient ND1 of the first type of plastic and the normalized spectral coefficient of the plastic to be classified ND The absolute value of the difference is taken to obtain the first absolute value; the normalized spectral coefficient ND2 of the second type of plastic is compared with the normalized spectral coefficient of the plastic to be classified. ND Take the absolute value of the difference and obtain the second absolute value; S27: Compare the first absolute value with the second absolute value. If the first absolute value is greater than the second absolute value, the plastic to be classified is determined as the second type of plastic; otherwise, the plastic to be classified is determined as the first type of plastic.

[0012] Furthermore, in step S1 and step S2, the dual-channel infrared camera acquires the first infrared image, the second infrared image, the first whiteboard image, the second whiteboard image and the dark noise at the same exposure time.

[0013] Furthermore, in step S3, if the plastic to be classified is the first type of plastic, the air valve of the jet mechanism is set to a closed state, so that the plastic to be classified falls into the first collecting device; otherwise, the air valve of the jet mechanism is set to an open state, and the jet mechanism is used to blow the plastic to be classified into the second collecting device.

[0014] Compared with the prior art, the invention can achieve the following beneficial effects: (1) The invention creates a plastic binary classification system based on a dual-channel infrared camera. Compared with the existing infrared array imaging chip, which only has one linear array pixel for imaging, two linear array pixels are often prepared on the same chip to improve the chip yield when preparing the chip, and finally one linear array pixel is selected for camera preparation; and the existing plastic binary classification method all uses two single-channel infrared cameras for classification. This method uses another linear array pixel on the chip to enable one infrared camera to image two spectral channels, greatly reducing the classification cost.

[0015] (2) Compared with the camera form adopted by the existing classification methods, the plastic binary classification system based on the dual-channel infrared camera created by the present invention has the advantage of reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments and descriptions of the present invention are used to explain the present invention and do not constitute an improper limitation on the present invention. In the drawings: Figure 1 A schematic diagram of the structure of a plastic binary classification system based on a dual-channel infrared camera according to an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a dual-channel infrared camera according to an embodiment of the present invention; FIG3 (a) is a spectral response curve of the bandpass filter and the first pixel-level filter according to an embodiment of the present invention; FIG3( b ) is a spectral response curve of the bandpass filter and the second pixel-level filter according to an embodiment of the present invention; Figure 4 A schematic diagram of the process of the plastic binary classification method based on a dual-channel infrared camera described in an embodiment of the present invention.

[0017] Description of reference numerals: 1. Transmission mechanism; 2. Dual-channel infrared camera; 3. Host computer; 4. Jet mechanism; 5. First type of plastic; 6. Second type of plastic; 2-1. Optical path element; 2-2. Protective window; 2-3. Bandpass filter; 2-4. First pixel level filter; 2-5. Second pixel level filter; 2-6. First imaging line pixel; 2-7. Second imaging line pixel; 2-8. Photodetector. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the invention more clear, the invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the invention and do not constitute a limitation of the invention.

[0019] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0020] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0021] In the description of the invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the invention can be understood according to specific circumstances.

[0022] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0023] like Figure 1 As shown, the present invention proposes a plastic binary classification system based on a dual-channel infrared camera 2, comprising a conveying mechanism 1, a dual-channel infrared camera 2, a host computer 3, an air jet mechanism 4, a first plastic collecting device and a second plastic collecting device, wherein the dual-channel infrared camera 2 is placed directly above the conveying mechanism 1, the dual-channel infrared camera 2 is connected to the host computer 3, and the host computer 3 is connected to the air jet mechanism 4; The conveying mechanism 1 transports the plastics to be classified, and the dual-channel infrared camera 2 collects images of the plastics to be classified; the upper computer 3 performs a binary classification judgment on the plastics to be classified based on the images of the plastics to be classified, and converts the judgment result into a control parameter of the jet mechanism 4. The jet mechanism 4 performs a separation operation on the plastics to be classified according to the control parameters, so that the plastics to be classified fall to the first plastic collection device or the second plastic collection device accordingly.

[0024] The conveying mechanism 1 adopts a 800 mm wide V-shaped conveyor belt (manufacturer: Chaohua Rubber Conveyor Belt Manufacturing Co., Ltd.), and the jetting mechanism 4 adopts an air gun or a large dust blowing gun.

[0025] The present invention can sort two kinds of plastics, that is, the mixed plastics include the first type of plastics 5 and the second type of plastics 6, the first plastic collecting device collects the first type of plastics 5, and the second plastic collecting device collects the second type of plastics 6. The jet mechanism 4 of the present invention includes an air valve, which is opened or closed according to the control parameters to adjust the jet state of the jet mechanism 4 to achieve the separation operation of the mixed plastics. The sorting process of the present invention is efficient and convenient.

[0026] The first plastic collecting device is placed at the end of the conveying mechanism 1 to collect plastic dropped from the conveyor belt of the conveying mechanism 1 ; the installation position of the second plastic collecting device corresponds to the jet direction of the jet mechanism 4 to collect plastic blown off the conveying mechanism 1 by the jet mechanism 4 .

[0027] The host computer 3 includes a computer.

[0028] like Figure 2 As shown, the dual-channel infrared camera 2 mainly includes an optical path element 2-1, a protective window 2-2, a bandpass filter 2-3, a first pixel-level filter 2-4 and a second pixel-level filter 2-5; wherein the optical path element 2-1 is used for optical imaging; a groove is provided in the center of the protective window 2-2 for placing the bandpass filter 2-3; the bandpass filter 2-3 is installed in the groove for transmitting light of a specified passband. As shown in Fig. 3 (a) to (b), the passband response of the bandpass filter 2-3 includes the passband ranges of two pixel-level filters. The first pixel-level filter 2-4 and the second pixel-level filter 2-5 are both configured to transmit light of a single band; the optical axis of the optical path element 2-1 is perpendicular to the protective window 2-2, the bandpass filter 2-3, the first pixel-level filter 2-4, the second pixel-level filter 2-5, the first imaging line pixel 2-6 and the second imaging line pixel 2-7. The bandpass filter 2-3 and the first pixel-level filter 2-4 are relatively parallel and overlapped in the vertical direction. The bandpass filter 2-3 and the second pixel-level filter 2-5 are relatively parallel and overlapped in the vertical direction. The first pixel-level filter 2-4 is bonded to the target surface of the first imaging line pixel 2-6, and the second pixel-level filter 2-5 is bonded to the target surface of the second imaging line pixel 2-7.

[0029] The first imaging line pixel 2-6 and the second imaging line pixel 2-7 are both placed on the focal plane of the optical path element 2-1, and are used to receive light passing through the bandpass filter 2-3 and the two pixel-level filters, and convert the optical signal into an electrical signal; the bandpass filter 2-3 is installed on the shell of the protective window 2-2, and the two pixel-level filters and the two imaging line pixels are all arranged in the installation space of the entire photodetector 2-8, and the spectral response range of the two imaging line pixels in the photodetector 2-8 is correspondingly greater than the spectral response range of the two pixel-level filters (the spectral response range of the first imaging line pixel 2-6 is greater than the spectral response range of the first pixel-level filter 2-4, and the spectral response range of the second imaging line pixel 2-7 is greater than the spectral response range of the second pixel-level filter 2-5).

[0030] The present invention as a whole is composed of a conveying mechanism 1, a dual-channel infrared camera 2, a host computer 3, an air jet mechanism 4, a first plastic collecting device and a second plastic collecting device, wherein the conveyor belt of the conveying mechanism 1 transports a collection of mixed plastics; the dual-channel infrared camera 2 is used to obtain infrared images of the plastics to be classified in real time, and transmit the infrared images to a computer in real time; the computer calculates the reflectivity of the plastics to be classified, and performs a binary classification judgment on the plastics to be classified based on the reflectivity of the mixed plastics and the infrared image, that is, executes the judgment operation function, and then converts the judgment result into the working parameter of the air valve. When the recognition result is the first type of plastic 5, the air valve does not work, and the plastics to be classified fall normally along the conveyor belt to the first plastic collecting device; when the recognition result is the second type of plastic 6, the air valve works to blow the plastics to be classified into the second plastic collecting device.

[0031] like Figure 4 As shown, the present invention provides a plastic binary classification method based on a dual-channel infrared camera 2, which is implemented using a plastic binary classification system based on a dual-channel infrared camera 2, and specifically includes the following steps: S1: The conveying mechanism 1 transports the plastic to be classified, and the dual-channel infrared camera 2 collects images of the plastic to be classified.

[0032] In step S1, two channels of the dual-channel infrared camera 2 are used to simultaneously image the plastics to be classified, thereby obtaining a first infrared image and a second infrared image.

[0033] S2: The host computer 3 performs binary classification judgment on the plastic to be classified based on the image of the plastic to be classified, and converts the judgment result into control parameters of the jet mechanism 4; The binary classification is to distinguish between two types of plastics by calculating the reflectance and normalized spectral coefficient of the plastic to be classified.

[0034] In step S2, the host computer 3 performs the following specific steps to perform binary classification on the plastic to be classified based on the image of the plastic to be classified: S21: using two channels of the dual-channel infrared camera 2 to simultaneously image the 100% diffuse reflection whiteboard to obtain a first whiteboard image and a second whiteboard image; S22: placing the dual-channel infrared camera 2 in a dark room environment for shooting, and obtaining dark noise of the dual-channel infrared camera 2; S23: Calculate the reflectivity of the plastic to be classified in the i-th spectral band by the following formula : ; Where i is 1 or 2, is the reflectance of the plastic to be classified in the first spectral band, is the reflectance of the plastic to be classified in the second spectral band, is the first infrared image, is the second infrared image, is the first whiteboard image, is the second whiteboard image, is the dark noise of dual-channel infrared camera 2; S24: Normalize the reflectance of the plastic to be classified in each spectral band to obtain the normalized spectral coefficient ND : ; S25: repeating steps S23 to S24, replacing the plastic to be classified with the first type plastic 5 and the second type plastic 6 in turn, to obtain the normalized spectral coefficient ND1 of the first type plastic 5 and the normalized spectral coefficient ND2 of the second type plastic 6; S26: Normalized spectral coefficient ND1 of the first type of plastic 5 and the normalized spectral coefficient of the plastic to be classified ND The absolute value of the difference is taken to obtain the first absolute value; the normalized spectral coefficient ND2 of the second type of plastic 6 and the normalized spectral coefficient of the plastic to be classified are ND Take the absolute value of the difference and obtain the second absolute value; S27: Compare the first absolute value with the second absolute value. If the first absolute value is greater than the second absolute value, the plastic to be classified is determined as the second type of plastic 6; otherwise, the plastic to be classified is determined as the first type of plastic 5.

[0035] In step S1 and step S2, the dual-channel infrared camera 2 collects the first infrared image, the second infrared image, the first whiteboard image, the second whiteboard image and the dark noise at the same exposure time.

[0036] S3: The jet mechanism 4 performs separation operation on the plastics to be classified according to the control parameters, so that the plastics to be classified fall to the first plastic collecting device or the second plastic collecting device accordingly.

[0037] In step S3, if the plastic to be classified is the first type of plastic 5, the air valve of the jet mechanism 4 is set to a closed state, so that the plastic to be classified falls into the first collecting device; otherwise, the air valve of the jet mechanism 4 is set to an open state, and the jet mechanism 4 is used to blow the plastic to be classified into the second collecting device.

[0038] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the disclosure of the present invention can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0039] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A plastic binary classification system based on a dual-channel infrared camera, characterized by: It includes a conveying mechanism, a dual-channel infrared camera, a host computer, an air jet mechanism, a first plastic collecting device and a second plastic collecting device, wherein the dual-channel infrared camera is placed directly above the conveying mechanism, the dual-channel infrared camera is connected to the host computer, and the host computer is connected to the air jet mechanism; The conveying mechanism transports the plastics to be classified, and the dual-channel infrared camera collects images of the plastics to be classified; the host computer performs binary classification on the plastics to be classified based on the images of the plastics to be classified, and converts the judgment results into control parameters of the jet mechanism, and the jet mechanism separates the plastics to be classified according to the control parameters, so that the plastics to be classified fall to the first plastic collection device or the second plastic collection device accordingly.

2. The plastic binary classification system based on a dual-channel infrared camera according to claim 1 is characterized in that: The first plastic collecting device is placed at the end of the conveying mechanism to collect plastic dropped from the conveyor belt of the conveying mechanism; the installation position of the second plastic collecting device corresponds to the jet direction of the jet mechanism to collect plastic blown off the conveying mechanism by the jet mechanism.

3. The plastic binary classification system based on a dual-channel infrared camera according to claim 1 is characterized in that: The host computer includes a computer.

4. The plastic binary classification system based on a dual-channel infrared camera according to claim 2 is characterized in that: The jet mechanism comprises an air valve, which is opened or closed according to the control parameter to adjust the jet state of the jet mechanism and realize the separation operation of the mixed plastics.

5. The plastic binary classification system based on a dual-channel infrared camera according to claim 4 is characterized in that: The mixed plastics include a first type of plastics and a second type of plastics. The first plastic collecting device collects the first type of plastics, and the second plastic collecting device collects the second type of plastics.

6. A plastic binary classification method based on a dual-channel infrared camera, implemented by using the plastic binary classification system based on a dual-channel infrared camera according to claim 5, characterized in that: The specific steps include: S1: The conveying mechanism transports the plastics to be classified, and the dual-channel infrared camera collects images of the plastics to be classified; S2: the host computer performs binary classification judgment on the plastic to be classified based on the image of the plastic to be classified, and converts the judgment result into control parameters of the jet mechanism; S3: The jet mechanism performs separation operation on the plastics to be classified according to the control parameters, so that the plastics to be classified fall to the first plastic collecting device or the second plastic collecting device accordingly.

7. The plastic binary classification method based on a dual-channel infrared camera according to claim 6 is characterized in that: In step S1, two channels of the dual-channel infrared camera are used to simultaneously image the plastics to be classified, thereby obtaining a first infrared image and a second infrared image.

8. The plastic binary classification method based on a dual-channel infrared camera according to claim 7 is characterized in that: In step S2, the host computer performs the following specific steps for performing binary classification on the plastic to be classified based on the image of the plastic to be classified: S21: using two channels of the dual-channel infrared camera to simultaneously image a 100% diffuse reflection whiteboard to obtain a first whiteboard image and a second whiteboard image; S22: placing the dual-channel infrared camera in a dark room environment for shooting, and obtaining dark noise of the dual-channel infrared camera; S23: Calculate the reflectivity of the plastic to be classified in the i-th spectral band by the following formula : ； Where i is 1 or 2, is the reflectance of the plastic to be classified in the first spectral band, is the reflectance of the plastic to be classified in the second spectral band, is the first infrared image, is the second infrared image, is the first whiteboard image, is the second whiteboard image, is the dark noise of the dual-channel infrared camera; S24: normalizing the reflectance of the plastic to be classified in each spectral band to obtain a normalized spectral coefficient ND : ； S25: repeating steps S23 to S24, replacing the plastic to be classified with the first type of plastic and the second type of plastic in turn, to obtain a normalized spectral coefficient ND1 of the first type of plastic and a normalized spectral coefficient ND2 of the second type of plastic; S26: Normalized spectral coefficient ND1 of the first type of plastic and the normalized spectral coefficient of the plastic to be classified ND The absolute value of the difference is taken to obtain the first absolute value; the normalized spectral coefficient ND2 of the second type of plastic is compared with the normalized spectral coefficient of the plastic to be classified. ND Take the absolute value of the difference and obtain the second absolute value; S27: Compare the first absolute value with the second absolute value. If the first absolute value is greater than the second absolute value, the plastic to be classified is determined as the second type of plastic; otherwise, the plastic to be classified is determined as the first type of plastic.

9. The plastic binary classification method based on a dual-channel infrared camera according to claim 8, characterized in that: In step S1 and step S2, the dual-channel infrared camera collects the first infrared image, the second infrared image, the first whiteboard image, the second whiteboard image and the dark noise under the same exposure time.

10. The plastic binary classification method based on a dual-channel infrared camera according to claim 6, characterized in that: In step S3, if the plastic to be classified is the first type of plastic, the air valve of the jet mechanism is set to a closed state, so that the plastic to be classified falls into the first collecting device; otherwise, the air valve of the jet mechanism is set to an open state, and the jet mechanism is used to blow the plastic to be classified into the second collecting device.

Images