PixelTrack: A Fast Adaptive Algorithm for Tracking Non-rigid Objects

TLDR

The authors introduce PixelTrack, a fast algorithm for tracking generic objects in videos. PixelTrack combines a generalized Hough transform detector with pixel‑based descriptors and a probabilistic segmentation using global foreground/background models, co‑training the two components for adaptive tracking. Evaluated on challenging standard videos, PixelTrack accurately tracks rigid and non‑rigid deformations, outperforms state‑of‑the‑art methods, and achieves very high speed.

Abstract

In this paper, we present a novel algorithm for fast tracking of generic objects in videos. The algorithm uses two components: a detector that makes use of the generalised Hough transform with pixel-based descriptors, and a probabilistic segmentation method based on global models for foreground and background. These components are used for tracking in a combined way, and they adapt each other in a co-training manner. Through effective model adaptation and segmentation, the algorithm is able to track objects that undergo rigid and non-rigid deformations and considerable shape and appearance variations. The proposed tracking method has been thoroughly evaluated on challenging standard videos, and outperforms state-of-the-art tracking methods designed for the same task. Finally, the proposed models allow for an extremely efficient implementation, and thus tracking is very fast.