A Model for Floating Garbage Detection and Quantification Using Fixed Camera

A large amount of plastic waste generated from production and living activities is polluting and threatening aquatic habitats. Large amounts of this plastic waste found in the oceans originate from land. It finds its way to the vast ocean through rivers and other waterways. In this study, we present a model, which is an algorithm consisting of 5 main steps to detect and quantify floating waste based on images obtained from a fixed camera. In which the image obtained from the camera will be calibrated to the bird's-eye view, then the floating waste will be detected and quantified using the pre-trained Mask R-CNN model. Experimental results show that our model has the potential to be applied in automated tasks of monitoring and quantifying floating waste along the riverbank from images obtained by fixed cameras on autonomous surface vehicles.