Robust infrared vehicle tracking across target pose change using L<inf>1</inf> regularization

Abstract

In this paper, we propose a robust vehicle tracker for Infrared (IR) videos motivated by the recent advance in compressive sensing (CS). The new eL 1 -PF tracker solves a sparse model representation of moving targets via L 1 regularized least squares. The sparse-model solution addresses real-world environmental challenges such as image noises and partial occlusions. To further improve tracking performance for frame-to-frame sequences involving large target pose changes, two extensions to the original L 1 tracker are introduced (eL 1 ). First, in the particle filter (PF) framework, pose information is explicitly modelled into the state space which significantly improves the effectiveness of particle sampling and propagation. Second, a probabilistic template update scheme is designed, which helps alleviating drift caused by a target pose change. The proposed tracker, named eL 1 -PF tracker, is tested on IR sequences from the DARPA Video Verification of Identity (VIVID) dataset. Promising results from the eL 1 -PF tracker are observed in these experiments in comparison with previous mean-shift and original L 1 -regularization trackers.