Title: Efficient object tracking algorithm using modified colour-texture descriptor

Authors: Prajna Parimita Dash; Dipti Patra

Addresses: Department of ECE, Birla Institute of Technology, Mesra, Ranchi, India ' IPCV Lab, National Institute of Technology, Rourkela, Odisha, India

Abstract: In this paper, rotation invariant local binary pattern and local contrast measure have been joined together for describing the texture feature. In addition to this, colour features have also been included in the feature vector of the object tracking algorithm. Thus the texture can be characterised by two orthogonal properties like, the spatial structure (local binary pattern) and the strength of the pattern (contrast). Covariance matrix of the feature vector has been taken as the object descriptor in the proposed algorithm. The performance of the proposed method has been compared by different performance measures, such as the detection rate, tracking speed and coverage test. The proposed method has also been tested for various challenging situations, such as occlusion, camera motion, non-rigidity, and changes in illumination. The experimental results show that the proposed method outperforms the existing methods in terms of performance indices.

Keywords: object tracking; covariance matrix; rotation invariant LBP; local binary patterns; local contrast measures; LCM; Ohta colour model; texture features; colour features; occlusion; camera motion; non-rigidity; illumination changes.

DOI: 10.1504/IJCISTUDIES.2015.069843

International Journal of Computational Intelligence Studies, 2015 Vol.4 No.1, pp.102 - 112

Received: 25 Sep 2013
Accepted: 26 Dec 2014
Published online: 13 Jun 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article