Event Data Association via Robust Model Fitting for Event-based Object Tracking

arXiv:2110.12962v2 Announce Type: replace
Abstract: Event-based approaches, which are based on bio-inspired asynchronous event cameras, have achieved promising performance on various computer vision tasks. However, the study of the fundamental event data association problem is still in its infancy. In this paper, we propose a novel Event Data Association (called EDA) approach to explicitly address the event association and fusion problem. The proposed EDA seeks for event trajectories that best fit the event data, in order to perform unifying data …

abstract arxiv association asynchronous bio bio-inspired cameras computer computer vision cs.cv data event however novel object paper performance robust study tasks tracking type via vision