KR20230071431A - Apparatus for PET sorting based on artificial intelligence - Google Patents

Abstract

The present invention relates to a PET sorting device based on artificial intelligence.
The PET sorting device according to the present invention photographs a plurality of plastic wastes put into a conveyor from a learning unit and a vision sensor that learns a pre-constructed learning model that learns to sort plastic waste colors included in a waste image taken of plastic waste. An image acquisition unit that acquires an image of waste, an analysis unit that inputs the obtained image of waste into a learned learning model, and extracts location information on plastic waste of a specific color set in advance; A spectrum acquisition unit that sets a light irradiation area using location information, transmits the set light irradiation area to a spectral sensor, and receives the spectrum of plastic waste located in the light irradiation area from the spectral sensor, and the obtained spectrum a determination unit that determines whether the plastic waste located in the light irradiation area corresponds to PET, and a control unit that sets the location information of the plastic waste determined to be PET as final sorting coordinates and transmits it to a pickup robot. include
As described above, according to the present invention, by providing a total platform capable of automatically sorting and separating recycled PET, it is possible to automate the sorting process in the recycling field and improve sorting accuracy and sorting speed.

Description

PET sorting device based on artificial intelligence {Apparatus for PET sorting based on artificial intelligence}

The present invention relates to a PET sorting device based on artificial intelligence. More specifically, the PET sorting device selects the material of PET (polyethylene terephthalate) to be recycled using an artificial intelligence algorithm and collects only PET of a designated color. It's about the device.

As non-face-to-face consumption such as parcel delivery and food delivery increases due to the prolonged COVID-19 crisis, a lot of recyclable waste such as plastic is being generated. Usually, 30-40% of recycled goods are not sorted and are landfilled or incinerated. When plastic waste is landfilled, it accumulates in the human body in the form of microplastics through various routes, which can negatively affect health.

Therefore, the importance of the screening process for plastic waste is emerging. However, since plastic waste is used in various materials depending on its use and shape, it is difficult to classify the material in the manual process.

In addition, in the case of color-added PET, since the quality of the recycled raw material may be deteriorated, consumers should separate and discharge it, but in most cases, they do not accurately recognize it. Therefore, since plastic waste is sorted manually according to the type or color of plastic waste, most sorting companies have a problem in that time and labor costs increase due to sorting. Plastic waste is buried as it is and cannot improve the environmental pollution problem.

The background technology of the present invention is disclosed in Korean Patent Registration No. 10-1270354 (Announcement on May 27, 2013).

As described above, according to the present invention, it is to provide a PET sorting device that selects the material of PET (polyethylene terephthalate) to be recycled using an artificial intelligence algorithm and collects only PET of a designated color.

In the artificial intelligence-based PET sorting device according to an embodiment of the present invention to achieve this technical problem, the color of the plastic waste included in the waste image photographed of the plastic waste is selected, and the atypical plastic is learned to select A learning unit that learns a pre-built learning model, an image acquisition unit that acquires a waste image of a plurality of plastic wastes put on a conveyor from the vision sensor, An analysis unit that extracts location information on the plastic waste of a specific color, sets a light irradiation area using the extracted location information of the plastic of a specific color, transmits the set light irradiation area to the spectroscopy sensor, and A spectrum acquisition unit receiving a spectrum of plastic waste located in the light irradiation area from a spectral sensor, a determination unit determining whether or not the plastic waste located in the light irradiation area corresponds to PET by using the acquired spectrum, and A control unit may be configured to set location information of the plastic waste determined to be PET as final sorting coordinates and transmit the result to a pickup robot.

The learning unit builds a learning model based on the HSV Color algorithm and Dection, and measures each HSV (Hue, Saturation, Value) value and A pre-built learning model may be trained using a position value corresponding to the HSV value.

The analysis unit may input the waste image into a learning model on which learning is completed, and extract a region of interest for plastic waste having a specific color and a position value of a center point of the region of interest through the learning model.

The analysis unit sets the starting point of the conveyor as reference coordinates, sets the position value of the center point of the region of interest as relative coordinate values using the conveyor width, moving speed, and the reference coordinate value, and sets the relative coordinate value to the set relative coordinate value. Coordinate values on the conveyor can be obtained by applying geometry transformation.

The determination unit sets each spectrum range according to the type of the plastic waste, and if each spectrum of the plastic waste located within the coordinate value on the conveyor is located in the spectrum range corresponding to PET, the corresponding plastic waste is classified. It can be judged by PET.

The control unit may apply a conversion matrix to coordinate values on the conveyor to obtain robot pick-up coordinate values, and extract the obtained robot pick-up coordinate values as final sorting coordinates.

The control unit may enable the robot to pick up plastic waste made of a material other than PET by using the final sorting coordinate values of the plastic waste determined to be PET.

In this way, according to the present invention, by providing a total platform capable of automatically sorting and separating recycled PET, it is possible to automate the sorting process of recycled parcels, and improve sorting accuracy and sorting speed.

In addition, according to the present invention, it is possible to quickly select only plastic waste having a specific color from among a plurality of plastic wastes by using a learning model based on the HSV Color algorithm and Dection.

1 is a diagram for explaining an automatic sorting and separating system according to an embodiment of the present invention.
Figure 2 is a configuration diagram for explaining the PET sorting device shown in Figure 1.
3 is a flowchart illustrating a method of sorting PET using an automatic sorting and separating system for recycled PET according to an embodiment of the present invention.
4 is a photograph of plastic waste.
5 is an exemplary diagram for explaining step S340 shown in FIG. 2 .

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. In this process, the thickness of lines or the size of components shown in the drawings may be exaggerated for clarity and convenience of description.

In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or operator. Therefore, definitions of these terms will have to be made based on the content throughout this specification.

Hereinafter, an automatic sorting and separating system for recycled PET according to an embodiment of the present invention will be described in more detail with reference to FIGS. 1 and 2.

1 is a diagram for explaining an automatic sorting and separating system according to an embodiment of the present invention.

As shown in FIG. 1, the automatic sorting and separating system according to an embodiment of the present invention includes a conveyor 100, a vision sensor 200, a spectral sensor 300, a PET sorting device 400, and a sorting robot 500. include

First, the conveyor 100 serves to transport the plastic waste from one point to another.

The vision sensor 200 is located on one side of the conveyor 100 and photographs the transported plastic waste. Then, the vision sensor 200 transmits the captured image of the waste to the PET sorting device 400 to be described later.

The spectral sensor 300 radiates light within a set light irradiation area and measures a spectrum reflected from plastic waste located within the light irradiation area.

To explain this again, the spectral sensor 300 receives the light irradiation area set from the PET sorting device 400. Then, the spectral sensor 300 radiates light into the set light irradiation area. For example, assuming that the light irradiation area is approximately 950 nm to 1650 nm, the spectral sensor 300 measures a spectrum within approximately 950 nm to 1650 nm. Then, the measured spectrum is transmitted to the PET sorting device 400.

The PET sorting device 400 inputs the waste image received from the vision sensor 200 to the learned learning model, has a specific color, and acquires location information on plastic waste estimated to be PET. Then, the PET sorting device 400 sets a light irradiation area using the acquired location information, and transmits information about the set light irradiation area to the spectral sensor 300 .

Next, the PET sorting device 400 receives the spectrum of the plastic waste located in the light irradiation area from the spectral sensor 300 and determines whether the corresponding plastic waste is PET by using the received spectrum.

Finally, the sorting robot 500 is located on one side of the conveyor 100 and picks up the plastic waste except PET. To elaborate, the sorting robot 500 receives location information about the PET from the PET sorting device 400 . Then, the sorting robot 500 picks up and separates only plastic waste other than PET by using the received location information.

FIG. 2 is a configuration diagram for explaining the PET sorting device 400 shown in FIG. 1 .

As shown in FIG. 2, the PET screening device 400 according to an embodiment of the present invention includes an image acquisition unit 410, a learning unit 420, an analysis unit 430, a spectrum acquisition unit 440, and a determination unit. 450 and a control unit 460.

The image acquiring unit 410 acquires a waste image of the plastic waste from the vision sensor 200 .

The learning unit 420 builds a learning model based on the HSV Color algorithm. Then, the learning unit 420 inputs the waste image to the built learning model, and trains the learning model to extract an area of the plastic waste having a specific color and to output a position value for the extracted area.

Here, the learning model is composed of at least one algorithm among a convolutional neural network (CNN) algorithm, a single shot detector (SSD) algorithm, and a you only look once (YOLO) algorithm.

Next, the analysis unit 430 inputs the waste image including the screening target to the learning model on which learning is completed. Then, the learning model selects plastic waste having a predetermined color from the waste image, and outputs location information of the selected plastic waste. Here, the location information represents a pixel coordinate value in an image.

The analyzer 430 converts the output location information of the plastic waste into two-dimensional coordinate values on the conveyor 100 .

The spectrum acquisition unit 440 sets the light irradiation area using the 2D coordinate values on the conveyor 100 . And the set light irradiation area is transferred to the spectral sensor 300 . Then, the spectral sensor 300 radiates light into the received light irradiation area and measures a spectrum of light reflected from the plastic waste located within the light irradiation area. When the spectrum measurement is completed, the spectrum acquisition unit 440 receives the measured spectrum from the spectral sensor 300 .

The determination unit 450 analyzes the material of the plastic waste using the received spectrum, and determines whether the plastic waste located in the light irradiation area corresponds to PET according to the analysis result.

Finally, the controller 460 extracts location information on plastic waste that is not determined to be PET, and transmits the extracted location information to the sorting robot 500 .

Hereinafter, a method of sorting PET using the automatic sorting and separating system for recycled PET according to an embodiment of the present invention will be described in more detail with reference to FIGS. 3 to 5 .

3 is a flowchart illustrating a method of sorting PET using an automatic sorting and separating system for recycled PET according to an embodiment of the present invention.

As shown in FIG. 3 , the PET selection method using the automatic sorting separation system according to an embodiment of the present invention is divided into a step of learning a learning model and a step of selecting PET using the learned model.

In the step of learning the learning model, first, the PET sorting device 400 collects waste images (S310).

4 is a photograph of plastic waste.

As shown in FIG. 4 , plastic waste is formed in various shapes, colors, and sizes depending on the material and use, and the plastic waste put into the conveyor 100 is formed in an irregular shape according to the degree of compression. In addition, examining the color of the plastic waste in the state of being initially stored in the sorting workplace and the plastic waste after cleaning, the plastic waste is discolored by the chemicals used during cleaning.

Therefore, the user takes pictures of the plastic waste that has been put into the sorting workplace, the plastic waste that has been cleaned using chemicals, or the plastic waste that has been compressed, and sends the captured image of the waste to the PET sorting device 400. Enter

Next, the learning unit 420 inputs the waste image to the learning model and learns to select plastic waste having a specific color (S320).

To explain this again, the learning model classifies the background color of the conveyor 100 and the color of the plastic waste based on the HSV Color algorithm and Dection.

Therefore, the learning unit 420 learns the position value corresponding to the candidate region selected through each HSV (Hue, Saturation, Value (Hue, Saturation, Value)) value measured for each of the plurality of plastic wastes included in the waste image. It is input to the model for supervised learning.

Then, the learning model outputs the position value of the object extracted from the input waste image.

When the learning of the learning model is completed through steps S310 and S320, the PET sorting device 400 according to an embodiment of the present invention selects PET of a specific color using the learned learning model.

First, the PET sorting device 400 receives a waste image of plastic waste to be sorted from the vision sensor 200 (S330).

When plastic waste to be sorted is put on the conveyor 100, the vision sensor 200 performs imaging according to a preset frame rate.

At this time, the vision sensor 200 is set the frame rate calculated through Equation 1 below in order to obtain an image synchronized with the conveyor 100.

Here, the conveyer belt velocity represents the moving speed of the conveyor 100, and the field of view of camera represents the observable area of the vision sensor 200.

For example, it is assumed that the maximum speed of the conveyor 100 is 1,000 mm/sec and the observable area of the vision sensor is 520x370 mm. Then, when the moving speed of the conveyor 100 and the observable area are substituted into Equation 1, 4.8 [frames / sec] is calculated.

Then, the vision sensor photographs the plastic waste put on the conveyor 100 approximately every 5 [frames / sec], and transmits the captured image of the waste to the PET sorting device 400.

Then, the analysis unit 430 determines whether plastic waste exists in the waste image by inputting the received waste image into the learned learning model (S340).

In other words, the learning model distinguishes the color of the conveyor 100 and the color of plastic waste to determine whether or not plastic waste exists in the waste image.

5 is an exemplary diagram for explaining step S340 shown in FIG. 2 .

As shown in FIG. 5 , when it is determined that plastic waste exists, the learning model extracts a region corresponding to the plastic waste as a region of interest.

Next, the analysis unit 430 acquires location information of plastic waste having a specific color from the learning model (S350).

The learning model determines whether the plastic waste included in the extracted region of interest corresponds to a specific color. To explain this again, the learning model determines whether the HSV value of the region of interest corresponds to a specific HSV value. Then, the learning model extracts a region of interest corresponding to a specific HSV value and outputs coordinate values of the extracted region of interest.

For example, assuming that the HSV values of transparent PET after washing are 44 (H), 29 (S), and 98 (V), the analyzer 430 analyzes 44 (H), 29 (S), and 98 (V) values. A region of interest having a value of is extracted, and coordinate values of the extracted region of interest are extracted.

When step S350 is completed, the spectrum acquisition unit 440 acquires a spectrum of the plastic waste having a specific color from the spectral sensor 300 (S360).

In detail, the analyzer 440 sets the starting point of the conveyor 100 as reference coordinates, and obtains relative coordinate values with respect to the center point of the region of interest using the conveyor width, moving speed, and reference coordinate values. Here, the center point of the region of interest represents the coordinate values of the region of interest obtained in step S350.

Next, the analysis unit 440 obtains coordinate values on the conveyor by applying geometry transformation to the relative coordinate values.

The spectrum acquisition unit 440 sets the light irradiation area using the obtained coordinate values on the conveyor. Then, the spectrum acquisition unit 440 transfers the set light irradiation area to the spectral sensor 300 .

Then, the spectral sensor 300 radiates light into the received light irradiation area and acquires a spectrum corresponding to the plastic waste.

When the spectrum obtained through step S360 is transmitted to the determination unit 450, the determination unit 450 compares the received spectrum with a preset spectrum range to determine whether the corresponding plastic waste corresponds to PET (S370). .

First, the determination unit 450 collects each spectral range according to the type of plastic waste.

Then, the determination unit 450 compares the spectrum received from the spectrum acquisition unit 440 with a pre-stored spectrum range. For example, when the PET sorting device 400 wants to sort out transparent PET, the determination unit 450 compares the received spectrum with a spectrum range corresponding to the transparent PET. And, if the received spectrum corresponds to the spectrum range, the determination unit 450 determines that the corresponding plastic waste is PET.

Next, the control unit 460 transmits the coordinate values of the plastic waste that is not determined to be PET to the sorting robot 500 so that the sorting robot 500 picks up the remaining plastic waste excluding PET of a specific color ( S380).

In other words, the control unit 460 converts the coordinate values on the conveyor where the plastic waste determined to be PET is located into pickup coordinate values.

Then, the control unit 460 sets the converted pick-up coordinate value as the final sorting coordinate value, and transmits the set final sorting coordinate value to the sorting robot 500 . Then, the sorting robot 500 picks up plastic waste made of a material other than PET having a specific color by using the received final sorting coordinate values. That is, only transparent PET is left on the conveyor 100 so that it can be transported to a specific place.

As described above, the automatic sorting and separating system according to the present invention provides a total platform capable of automatically sorting and separating recycled PET, thereby automating the sorting process in the recycling field and improving sorting accuracy and sorting speed.

In addition, the automatic sorting and sorting system according to the present invention can quickly select only plastic waste having a specific color from among a plurality of plastic wastes by using a learning model based on the HSV Color algorithm and Dection.

Although the present invention has been described with reference to the embodiments shown in the drawings, this is only exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. will be. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the claims below.

100: conveyor
200: vision sensor
300: spectral sensor
400: PET sorting device
410: image acquisition unit
420: learning unit
430: analysis unit
440: spectrum acquisition unit
450: judgment unit
460: control unit
500: pickup robot

Claims (7)

In the PET sorting device based on artificial intelligence,
A learning unit that selects the color of plastic waste included in a waste image of plastic waste and learns a pre-established learning model for learning to select atypical plastic.
An image acquisition unit for acquiring a waste image of a plurality of plastic wastes put into the conveyor from a vision sensor;
An analysis unit for inputting the obtained waste image into a learning model for which learning has been completed and extracting location information on plastic waste of a predetermined color;
A light irradiation area is set using the location information of the extracted plastic of a specific color, the set light irradiation area is transmitted to the spectral sensor, and then the spectrum of the plastic waste located in the light irradiation area is transferred from the spectral sensor. receiving spectrum acquisition unit;
A determination unit for determining whether the plastic waste located in the light irradiation area corresponds to PET by using the obtained spectrum; and
Automatic sorting and separation system comprising a control unit for setting the location information of the plastic waste determined to be PET as final sorting coordinates and transmitting it to a pickup robot. According to claim 1,
The learning unit,
Build a learning model based on the HSV Color algorithm and Dection,
Automatic learning of a pre-built learning model using each HSV (Hue, Saturation, Value (Hue, Saturation, Value)) value measured for each of the plurality of plastic wastes included in the waste image and the position value corresponding to the HSV value sorting separation system. According to claim 2,
The analysis unit,
Automatic sorting and separation system for inputting the waste image into a learning model for which learning has been completed, and extracting a region of interest for plastic waste having a specific color and a position value for a center point of the region of interest through the learning model. According to claim 3,
The analysis unit,
Setting the start point of the conveyor as reference coordinates, setting the position value of the center point of the region of interest as a relative coordinate value using the conveyor width, moving speed, and the reference coordinate value,
An automatic sorting and separation system that acquires coordinate values on the conveyor by applying geometry transformation to the set relative coordinate values. According to claim 4,
The judge,
Setting each spectrum range according to the type of plastic waste,
If each spectrum of the plastic waste located within the coordinates on the conveyor is located in a spectrum range corresponding to PET, the automatic sorting and separation system determines that the corresponding plastic waste is PET. According to claim 5,
The control unit,
Automatic sorting and separation system for obtaining robot pick-up coordinate values by applying a conversion matrix to coordinate values on the conveyor, and extracting the obtained robot pick-up coordinate values as final sorting coordinates. According to claim 6,
The control unit,
An automatic sorting and separation system that allows a robot to pick up plastic waste made of materials other than PET using the final sorting coordinates of plastic waste determined to be PET.

Images