Jia-Ying Lu

Abstract Accurate multi-temporal terrain change detection in mountainous regions is crucial for disaster monitoring and environmental management; however, it remains challenging due to the complex topography, dense vegetation, and occlusion. This study proposes an integrated, automated framework for terrain change detection that combines 2D semantic segmentation and 3D geometric analysis, utilizing UAV imagery and point cloud data.

1. Introduction Marine ecosystems are the entities on which thousands of marine creatures depend for survival and reproduction. Human activities and climate change have put increasing pressure on marine ecosystems, leading to a decrease in marine biodiversity [1]. Marine protected areas (MPAs) are frequently established and powerful tools for conserving species. However, global marine biodiversity has continued to deteriorate [2], indicating a great need for more efficient MPA management.