Littering quantification is an important step for improving cleanliness ofcities. When human interpretation is too cumbersome or in some casesimpossible, an objective index of cleanliness could reduce the littering byawareness actions. In this paper, we present a fully automated computer visionapplication for littering quantification based on images taken from the streetsand sidewalks. We have employed a deep learning based framework to localize andclassify different types of wastes. Since there was no waste dataset available,we built our acquisition system mounted on a vehicle. Collected imagescontaining different types of wastes. These images are then annotated fortraining and benchmarking the developed system. Our results on real casescenarios show accurate detection of littering on variant backgrounds.
展开▼
