Based On YOLOV8 Intelligent Trash Can Garbage Classification Detection Algorithm

Songzhe Pan; Ning Wang; Yuyun Lin; Jianhao Tang

doi:10.54097/67mska34

Authors

Songzhe Pan
Ning Wang
Yuyun Lin
Jianhao Tang

DOI:

https://doi.org/10.54097/67mska34

Keywords:

Convolutional neural network, small object detection, YOLOV.

Abstract

Since 2019, China has begun to vigorously implement a garbage sorting system across the country, with Shanghai being the first city to fully implement garbage sorting. For example, residents do not have a strong sense of classification and lack of classification knowledge, resulting in low classification accuracy. The management of the wharf is relatively loose, and the garbage collection, transportation and treatment links sometimes fail to strictly distinguish between various types of garbage, which affects the classification effect. Waste collection facilities are rudimentary, and sorting labels may not be uniform and oversimplified, which is not conducive to fine sorting. Therefore, it is urgent to solve the problem of garbage classification and become an urgent problem for all countries to study. The problem of sorting valuable garbage after garbage collection. The rapid development of deep learning provides the technical demand for intelligence. In this paper, the YOLOV8 algorithm is used to train the garbage classification model, and about 10,000 custom garbage datasets with 4 categories are used to classify food waste, hazardous waste, recyclable waste and other waste. In this paper, methods such as 0s, pandas, and numpy are used in Python programming. For model deployment, models can be deployed using trained weight files and configuration files, and models can be integrated into tools such as OpenCV, TensorFlow, etc., for real-time detection or integration into other applications.

References

Guo Wei. Ethical thinking on the problem of municipal solid waste in China [D]. Hunan University of Science and Technology, 2019.

Dong Ziyuan. Design and implementation of garbage classification system based on deep learning[D]. University of Chinese Academy of Sciences (Shenyang Institute of Computing Technology, Chinese Academy of Sciences), 202

Chen Xianchang. Research on deep learning algorithm and application based on convolutional neural network [D]. Zhejiang Gongshang University, 2014.

ZHOU Yueqi. Research on vehicle compaction line detection method based on convolutional neural network YOLO [D]. Zhejiang Academy of Science and Technology,2020.

Wang Lin. Research on improved object detection algorithm based on YOLO [D]. Jiangnan University, 2020. North University of China Dissertation 67

Li Jinyu, Chen Xiaolei, Zhang Aihua, et al.Review of garbage classification methods based on deep learning[J].Computer Engineering, 2022:1-9.

Zhang Wei. Garbage detection and classification based on YOLO neural network [J]. Electronic Science and Technology, 2022, 35(10),45-50.

Zhang Xujuan. Research on deep learning model of garbage classification based on image recognition [D]. Lanzhou: Northwest Normal University, 2021.

Shao Wenjie. Research on garbage detection method based on deep convolutional neural network [D]. Nanjing:Nanjing University of Posts and Telecommunications, 2022.

Su Zhe.Research on image classification method of domestic waste based on deep learning [D]. Lanzhou:Northwest Normal University,2021.