Instant water body variation detection via analysis on remote sensing imagery

Abstract

Water resources are critical for human survival and require continuous monitoring for protection. Machine learning methods have been successfully applied to the identification of water bodies by analyzing remote sensing images. The proposed method first performs pixel-level classification to detect abnormal changes using visual word patterns, then applies a block division method for parallel processing based on a MapReduce structure. This approach allows for accurate and rapid detection of water body variations with instant feedback. Experiments on self-collected datasets demonstrate superior efficiency compared to comparative methods.

Yirui Wu

Young Professor, CCF Senior Member

My research interests include Computer Vision, Artifical Intelligence, Multimedia Computing and Intelligent Water Conservancy.