Identification of garbage in the river based on the YOLO algorithm

Abstract

This paper discusses the identification of garbage using the YOLO algorithm. In the rivers, it is usually difficult to distinguish between garbage and plants, especially when it is done in real-time and at the time of too much light. Therefore, there is a need of an appropriate method. The HSV and SIFT methods were used as preliminary tests. The tests were quite successful even in close condition, however, there were still many problems faced in using this method since it is only based on pixel and shape readings. Meanwhile, YOLO algorithm was able to identify garbage and water hyacinth even though they were closed to each other.