Abstract
Coastal waste not only has a seriously destructive effect on human life and marine ecosystems, but it also poses a long-term economic and environmental threat. To solve the issues of a poor manual coastal waste sorting environment, such as low sorting efficiency and heavy tasks, we develop a novel deep convolutional neural network by combining several strategies to realize intelligent waste recognition and classification based on the state-of-the-art Faster R-CNN framework. Firstly, to effectively detect small objects, we consider multiple-scale fusion to get rich semantic information from the shallower feature map. Secondly, RoI Align is introduced to solve positioning deviation caused by the regions of interest pooling. Moreover, it is necessary to correct key parameters and take on data augmentation to improve model performance. Besides, we create a new waste object dataset, named IST-Waste, which is made publicly to facilitate future research in this field. As a consequence, the experiment shows that the algorithm’s mAP reaches 83%. Detection performance is significantly better than Faster R-CNN and SSD. Thus, the developed scheme achieves higher accuracy and better performance against the state-of-the-art alternative.
Highlights
IntroductionEnvironmental governance has never stopped, environmental pollution is still on the rise
The ultimate goal of our approach is to obtain effective and accurate context information to improve the detection performance of the Faster R-CNN
Coastal waste often contains a lot of small objects, such as cigarette butts, scraps of paper, broken glass, bottle caps, etc
Summary
Environmental governance has never stopped, environmental pollution is still on the rise. Coastal waste accounts for a very important proportion, and plastics are the main harmful pollutant [2]. Inthe the era era of of deep deep learning, evolve at at an amazing speed. We look back to well-known deep convolutional neuan amazing speed. We look back to well-known deep convolutional neural ral networks, namely Faster R-CNN. R-CNN of of many object candidate detection boxes by seR-CNN[28]. [28]permits permitsthe theextraction extraction many object candidate detection boxes by lective search. Each candidate area is cropped to the fixed-size image before selective search. Each candidate area is cropped to the fixed-size image before being being fed fedinto intothe thenetwork networkto toextract extractfeatures
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
