Event-based feature tracking with probabilistic data association

TLDR

Event‑based sensors create challenges for feature tracking in robot vision. The paper proposes a soft probabilistic data association for event‑based feature tracking. Probabilities are estimated in an EM framework jointly with optical flow, while affine deformation of the initial point is used to assess persistence and allow variable temporal integration. Experiments on egomotion and high‑speed vehicle sequences demonstrate that the method outperforms standard frame‑based cameras.

Abstract

Asynchronous event-based sensors present new challenges in basic robot vision problems like feature tracking. The few existing approaches rely on grouping events into models and computing optical flow after assigning future events to those models. Such a hard commitment in data association attenuates the optical flow quality and causes shorter flow tracks. In this paper, we introduce a novel soft data association modeled with probabilities. The association probabilities are computed in an intertwined EM scheme with the optical flow computation that maximizes the expectation (marginalization) over all associations. In addition, to enable longer tracks we compute the affine deformation with respect to the initial point and use the resulting residual as a measure of persistence. The computed optical flow enables a varying temporal integration different for every feature and sized inversely proportional to the length of the flow. We show results in egomotion and very fast vehicle sequences and we show the superiority over standard frame-based cameras.