Beach Litter Detection and Monitoring Using UAV Image and Deep Neural Network under Imbalanced Data

Beach litters such as plastic bottles and styrofoam destroys coast ecosystems and creates aesthetic discomfort that lowers the value of the beach. Also, these beach litters are consumed by marine creatures, causing secondary ecosystem destruction. In order to solve this beach litters problem, it is necessary to study the generation and distribution pattern of waste and the cause of the inflow. However, the data for the study were only sample data collected in some areas of the beach. Also, most of the data covers only the total amount of beach litters. The total amount obtained from the sampling method was difficult to represent the total amount of beach litters.

UAV(Unmanned Aerial Vehicle) and Deep Neural Network can be effectively used to detect and monitor beach litter. Using UAV, it is possible to easily survey the entire beach. Recently, Object Detection technologies based on the Convolutional Neural Network have produced remarkable results in the general object recognition field. The Deep Neural Network can also identify the type of coastal litters. Therefore, using UAV and Deep Neural Network, it is possible to acquire spatial information by type of beach litters.

This paper proposes a Beach litter detection algorithm based on UAV and Deep Neural Network and a Beach litter monitoring process using it. It also offers optimal shooting altitude and image duplication to detect small beach litter such as plastic bottles and styrofoam pieces found on the beach. We are also suggest to effectively methods for training on imbalanced data.

In this study, DJI Mavic 2 Pro was used. The camera on the UAV is a 1-inch CMOS with a resolution of 20MP. The images obtained through UAV are produced as orthoimages and input into a pre-trained neural network algorithm.