Aadhar is a masters student in the Mechanical Engineering department. His research interests include computer vision, sensor fusion, and perception for autonomous systems. His research focuses on the image fusion of thermal and visual images for search and rescue missions. Previously he was working as a research engineer at Mahindra Research Valley, India. He has completed his undergraduate degree in Mechanical Engineering from the National Institute of Technology Kurukshetra, India. His hobbies include traveling, hiking, and running.
Detecting humans from airborne visual and thermal imagery is a fundamental challenge for Wilderness Search-and-Rescue (WiSAR) teams, who must perform this function accurately in the face of immense pressure. The ability to fuse these two sensor modalities can potentially reduce the cognitive load on human operators and/or improve the effectiveness of computer vision object detection models. However, the fusion task is particularly challenging in the context of WiSAR due to hardware limitations and extreme environmental factors. This work presents Misaligned Image Synthesis and Fusion using Information from Thermal and Visual (MISFIT-V), a novel two-pronged unsupervised deep learning approach that utilizes a Generative Adversarial Network (GAN) and a cross-attention mechanism to capture the most relevant features from each modality. Experimental results show MISFIT-V offers enhanced robustness against misalignment and poor lighting/thermal environmental conditions compared to existing visual-thermal image fusion methods.
@inproceedings{ChauhanRemyEtAl2023,author={Chauhan, A. and Remy, I. and Broyles, D. and Leung, K.},title={{{MISFIT-V}: Misaligned Image Synthesis and Fusion using Information from Thermal and Visual}},year={2023},arxiv={2309.13216},category={afsl},img={ChauhanRemyEtAl2023.png},note={(submitted)},keywords={preprint},owner={karenl7}}
