Robust Tracking in Low Light and Sudden Illumination Changes - Robotics Institute Carnegie Mellon University

Robust Tracking in Low Light and Sudden Illumination Changes

Hatem Said Alismail, Brett Browning, and Simon Lucey
Conference Paper, Proceedings of International Conference on 3D Vision (3DV '16), pp. 389 - 398, October, 2016

Abstract

We present an algorithm for robust and real-time visual tracking under challenging illumination conditions characterized by poor lighting as well as sudden and drastic changes in illumination. Robustness is achieved by adapting illumination-invariant binary descriptors to dense image alignment using the Lucas and Kanade algorithm. The proposed adaptation preserves the Hamming distance under least-squares minimization, thus preserving the photometric invariance properties of binary descriptors. Due to the compactness of the descriptor, the algorithm runs in excess of 400 fps on laptops and 100 fps on mobile devices.

BibTeX

@conference{Alismail-2016-5612,
author = {Hatem Said Alismail and Brett Browning and Simon Lucey},
title = {Robust Tracking in Low Light and Sudden Illumination Changes},
booktitle = {Proceedings of International Conference on 3D Vision (3DV '16)},
year = {2016},
month = {October},
pages = {389 - 398},
}