Texture Extraction in Video Tracking with Comparison of LBP and DWT
M. Sangam, Niranjan Lal, Manoj Diwakar
Available Online April 2013.
- Object tracking using mean shift algorithm based on similarity between features of target region and candidate region. Candidate region is the current frame of tracking process. For similarity calculation color histogram and texture features are used. For texture feature extraction there are two methods LBP and discrete wavelet transform. In this paper comparison between these two approaches is done. Texture feature of target and candidate frame are extracted and integrated with color histogram. These features are together used for estimating the maximum similar candidate area with target area. This paper compares two methods of texture feature extraction. One is local binary pattern (LBP) and other one is discrete wavelet transform (DWT). These methods are compared on the basis of their computing time, performance and implementation.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - M. Sangam AU - Niranjan Lal AU - Manoj Diwakar PY - 2013/04 DA - 2013/04 TI - Texture Extraction in Video Tracking with Comparison of LBP and DWT BT - Proceedings of the Conference on Advances in Communication and Control Systems-2013 PB - Atlantis Press SP - 369 EP - 374 SN - 1951-6851 UR - https://www.atlantis-press.com/article/6337 ID - Sangam2013/04 ER -