PathFinder: Attention-Driven Dynamic Non-Line-of-Sight Tracking with a Mobile Robot

arXiv:2404.05024v1 Announce Type: new
Abstract: The study of non-line-of-sight (NLOS) imaging is growing due to its many potential applications, including rescue operations and pedestrian detection by self-driving cars. However, implementing NLOS imaging on a moving camera remains an open area of research. Existing NLOS imaging methods rely on time-resolved detectors and laser configurations that require precise optical alignment, making it difficult to deploy them in dynamic environments. This work proposes a data-driven approach to NLOS imaging, PathFinder, that can be …

abstract applications arxiv attention cars cs.cv cs.ro detection detectors driving dynamic however imaging line mobile moving operations pathfinder pedestrian research robot self-driving study tracking type