AeroSat Vision Lab Pioneering AI and Satellite Innovation

Projects

Development of a Semi-Supervised Learning Model for Disaster Object Reconstruction in Partially Cloud-Covered Areas Using Edge Computing on a CanSAT Platform
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.

Enhancing Real-Time Maritime Object Tracking with Satellite-Based Edge AI and Deep Reinforcement Learning
Enhancing Real-Time Maritime Object Tracking with Satellite-Based Edge AI and Deep Reinforcement Learning

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.