Robust infrared vehicle tracking across target pose change using L<inf>1</inf> regularization
Lists
Only you see this
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 <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -PF tracker solves a sparse model representation of moving targets via L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> 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 <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> tracker are introduced (eL <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> ). 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 <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -PF tracker, is tested on IR sequences from the DARPA Video Verification of Identity (VIVID) dataset. Promising results from the eL <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -PF tracker are observed in these experiments in comparison with previous mean-shift and original L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -regularization trackers.
BibTeX
@inproceedings{ling2010robust,
author = {Haibin Ling and Li Bai and Erik Blasch and Xue Mei},
title = {{Robust infrared vehicle tracking across target pose change using L\<inf\>1\</inf\> regularization}},
booktitle = {FUSION},
year = {2010},
url = {https://openreview.net/forum?id=vrGLtRxnMf},
}Loading related content...