Detection Is Tracking: Point Cloud Multi-Sweep Deep Learning Models Revisited

arXiv:2402.15756v1 Announce Type: new
Abstract: Conventional tracking paradigm takes in instantaneous measurements such as range and bearing, and produces object tracks across time. In applications such as autonomous driving, lidar measurements in the form of point clouds are usually passed through a "virtual sensor" realized by a deep learning model, to produce "measurements" such as bounding boxes, which are in turn ingested by a tracking module to produce object tracks. Very often multiple lidar sweeps are accumulated in a buffer …

abstract applications arxiv autonomous autonomous driving cloud cs.cv deep learning detection driving eess.sp form lidar paradigm sensor sweep through tracking type virtual