Picture of smart phone in human hand

World leading smartphone and mobile technology research at Strathclyde...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of Open Access research papers by University of Strathclyde researchers, including by Strathclyde researchers from the Department of Computer & Information Sciences involved in researching exciting new applications for mobile and smartphone technology. But the transformative application of mobile technologies is also the focus of research within disciplines as diverse as Electronic & Electrical Engineering, Marketing, Human Resource Management and Biomedical Enginering, among others.

Explore Strathclyde's Open Access research on smartphone technology now...

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