Automatic area estimation of algal blooms in water bodies from UAV images using texture analysis

Abstract

Algal blooms, the spread of algae on the surface of water bodies, have adverse effects not only on aquatic ecosystems but also on human life. The adverse effects of harmful algal blooms (HABs) necessitate a convenient solution for detection and monitoring. Unmanned aerial vehicles (UAVs) have recently emerged as a tool for algal bloom detection, efficiently providing on-demand images at high spatiotemporal resolutions. This study developed an image processing method for algal bloom area estimation from the aerial images (obtained from the internet) captured using UAVs. As a remote sensing method of HAB detection, analysis, and monitoring, a combination of histogram and texture analyses was used to efficiently estimate the area of HABs. Statistical features like entropy (using the Kullback–Leibler method) were emphasized with the aid of a gray-level co-occurrence matrix. The results showed that the orthogonal images demonstrated fewer errors, and the morphological filter best detected algal blooms in real time, with a precision of 80%. This study provided efficient image processing approaches using on-board UAVs for HAB monitoring.