Identification of plastic waste with unmanned aerial vehicle (UAV) using deep learning and internet of things (IoT)

Humans produce waste in their daily lives and activities. Waste comes from domestic and industrial activities, including organic and inorganic types. This study aimed to develop a model for a waste identification system to evaluate the plastic waste management that currently being uncommercial. Waste identification can be done quickly, precisely, and accurately using advanced technology, such as edge computing embedded on drones that can capture waste in rivers with various environmental conditions. Different types of waste can be identified according to predetermined specifications as guide data that is further processed using image processing software object detection methods based on mobile SVD. Based on our research in The Cinagara Caringin area, Bogor, this research managed to achieve an accuracy rate of 92 %. Therefore, this study successfully proposed a new method to automatically identify the type of waste using edge computing technology and make a significant contribution to efforts to mitigate the waste problem.