Use of unmanned aerial vehicles for efficient beach litter monitoring.
Cecilia Martin, Stephen Parkes, Qiannan Zhang, Xiangliang Zhang, Matthew F McCabe, Carlos M Duarte
Author Information
Cecilia Martin: King Abdullah University of Science and Technology (KAUST), Red Sea Research Center (RSRC), Thuwal 23955-6900, Saudi Arabia. Electronic address: cecilia.martin@kaust.edu.sa.
Stephen Parkes: King Abdullah University of Science and Technology (KAUST), Water Desalination and Reuse Center (WDRC), Thuwal 23955-6900, Saudi Arabia.
Qiannan Zhang: King Abdullah University of Science and Technology (KAUST), Computer, Electrical and Mathematical Sciences and Engineering Division, Thuwal 23955-6900, Saudi Arabia.
Xiangliang Zhang: King Abdullah University of Science and Technology (KAUST), Computer, Electrical and Mathematical Sciences and Engineering Division, Thuwal 23955-6900, Saudi Arabia.
Matthew F McCabe: King Abdullah University of Science and Technology (KAUST), Water Desalination and Reuse Center (WDRC), Thuwal 23955-6900, Saudi Arabia.
Carlos M Duarte: King Abdullah University of Science and Technology (KAUST), Red Sea Research Center (RSRC), Thuwal 23955-6900, Saudi Arabia.
A global beach litter assessment is challenged by use of low-efficiency methodologies and incomparable protocols that impede data integration and acquisition at a national scale. The implementation of an objective, reproducible and efficient approach is therefore required. Here we show the application of a remote sensing based methodology using a test beach located on the Saudi Arabian Red Sea coastline. Litter was recorded via image acquisition from an Unmanned Aerial Vehicle, while an automatic processing of the high volume of imagery was developed through machine learning, employed for debris detection and classification in three categories. Application of the method resulted in an almost 40 times faster beach coverage when compared to a standard visual-census approach. While the machine learning tool faced some challenges in correctly detecting objects of interest, first classification results are promising and motivate efforts to further develop the technique and implement it at much larger scales.
