Object Detection of Macroplastic Waste Using Unmanned Aerial Vehicles in Urban Canal

Macroplastics are a global threat to the aquatic environment and will degrade into microplastics over time. Its presence in canal causes pollution and inhibits water flow, causing flooding in urban areas; therefore, it is essential to identify and monitor its presence. Addressing knowledge gaps is critical in determining solutions for mitigation purposes. In visual object detection studies, aerial mapping is developed with advanced technology, such as Unmanned Aerial Vehicles (UAV). This research aims to conduct aerial mapping experiments to find the right formula or technical reference for detecting macroplastic waste objects floating on the surface of the canal, including flight altitude, exposure to sunlight, and the influence of season on object detection. Aerial mapping will be done in densely populated urban canals in Southeast Asia, Indonesia, and Makassar City. The aerial mapping survey method will be used, and then the data will be processed in the digitization process and object detection with GIS. The analysis kernel in GIS tools will be used to see the distribution density of macroplastics. The research results show that autoblock occurs at heights of 5m and 10m, but this autoblock can be minimized at a flight height of 15 m. Apart from that, height also affects flight duration. The lower flying height will result in better visual accuracy and better resolution. However, at a height of 15m, macroplastic objects were still detected on a moderate scale. This research successfully distinguished various plastic waste materials, the most found being the soft polyolefin category in plastic bags. Monitoring results detected 321 items of macroplastics in the dry season and 1,163 in the rainy season, or a threefold increase with conditions spread thinly in the dry season. In the rainy season, they gather densely on one side of the canal.