Picture of a black hole

Strathclyde Open Access research that creates ripples...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of research papers by University of Strathclyde researchers, including by Strathclyde physicists involved in observing gravitational waves and black hole mergers as part of the Laser Interferometer Gravitational-Wave Observatory (LIGO) - but also other internationally significant research from the Department of Physics. Discover why Strathclyde's physics research is making ripples...

Strathprints also exposes world leading research from the Faculties of Science, Engineering, Humanities & Social Sciences, and from the Strathclyde Business School.

Discover more...

Adaptive template matching algorithm based on SWAD for robust target tracking

Di Caterina, G. and Soraghan, J. J. (2012) Adaptive template matching algorithm based on SWAD for robust target tracking. Electronics Letters, 48 (5). pp. 261-262. ISSN 0013-5194

[img]
Preview
Text (Di-Caterina-Soraghan-EL-2012-Adaptive-template-matching-algorithm-based-on-SWAD-for-robust)
Di_Caterina_Soraghan_EL_2012_Adaptive_template_matching_algorithm_based_on_SWAD_for_robust.pdf - Accepted Author Manuscript

Download (1MB) | Preview

Abstract

The sum of absolute differences (SAD) is widely used in video coding and disparity computation for its simplicity. However, SAD is not very common in tracking applications owing to issues like partial occlusion and target changes, which can dramatically affect its performance. Presented is a novel adaptive template matching algorithm for target tracking, based on a sum of weighted absolute differences (SWAD). The target template is updated using an infinite impulse response filter, while a weighting kernel is adopted to reduce the effects of partial occlusion. Simulation results demonstrate that the proposed tracker outperforms conventional SAD in terms of efficiency and accuracy, and its performance is comparable with more complex trackers, such as the mean shift algorithm