Projects

Enhancing Real-Time Maritime Object Tracking with Satellite-Based Edge AI and Deep Reinforcement Learning UAAT-TAMUS Collaborative Project (2024/12-2025/11)

(1) Implement Edge AI on satellites to process remote sensing data, enabling real-time detection and tracking of maritime activities in the Taiwan Strait.
(2) Create an integrated communication network using LEO satellites and UAVs/Ships to optimize data rates and ensure reliable data transmission.

基於罐頭衛星 (CanSAT) 平台以邊緣運算的半監督學習模型(Semi Super vised Learning Model)為重建部分雲層遮蔽災害物件區域之開發 Development of a Semi-Supervised Learning Model for Disaster Object Reconstruction in Partially Cloud-Covered Areas Using Edge Computing on a CanSAT Platform

This research aims to develop a semi-supervised learning model that reconstructs disaster-affected areas obscured by cloud cover. By integrating this model into edge computing devices onboard satellites, the project seeks to enhance real-time disaster detection and prediction capabilities. A key innovation of this research is its implementation in a CanSAT, a small satellite platform, demonstrating the feasibility of real-time disaster monitoring in space.