Trash Detection Algorithm Suitable for Mobile Robots Using Improved YOLO

The illegal dumping of aluminum and plastic into cities and marine areas leads to negative impacts on the ecosystem and contributes to increased environ-mental pollution. Although volunteer trash pickup ac-tivities have increased in recent years, they require sig-nificant effort, time, and money. Therefore, we pro -pose automated trash pickup robot, which incorpo-rates autonomous movement and trash pickup arms. Although these functions have been actively devel-oped, relatively little research has focused on trash detection. As such, we have developed a trash detec-tion function by using deep learning models to im-prove the accuracy. First, we created a new trash dataset that classifies four types of trash with high ille-gal dumping volumes (cans, plastic bottles, cardboard, and cigarette butts). Next, we developed a new you only look once (YOLO)-based model with low parame-ters and computations. We trained the model on a cre-ated dataset and a dataset consisting of marine trash created during previous research. In consequence, the proposed models achieve the same detection accuracy as the existing models on both datasets, with fewer pa-rameters and computations. Furthermore, the pro -posed models accelerate the edge device's frame rate.