TEDU CMPE491/492 Senior Project
ThermalNet is a deep learning-based system designed to enhance feature matching between RGB and thermal images, addressing challenges in low-light and low-texture environments. The project aims to optimize real-time feature alignment by leveraging multi-scale feature extraction, coarse-to-fine matching, and sub-pixel refinement techniques. Developed in collaboration with Raventech and Gürbağ Defense, ThermalNet's applications span defense, surveillance, aerial monitoring, and navigation, offering improved accuracy and usability in thermal image analysis.
Batuhan Yıldız
Can Mızraklı
Gökay Toğa