An implementation of Object Tracking using Modified Mean Shift Algorithm
Keywords:
Abstract
Visual object tracking is a challenging problem in computer vision. To achieve the goal of object tracking we need to obtain a feature vector which is capable of identifying the object to be tracked despite of presence of translation in the view field, at the minimum.The change in scale of the object due to motion along the perpendicular to the line of sight adds to its complexity. In this work we have be able to implement an object tracking system using the MATLAB environment. The system uses the mean shift algorithm, which is based on color channel histogram analysis and the algorithm is modified that it includes the object texture information using the LBP operator. We have been able to enhance the object tracking capability of the system.
References
- D Comaniciu, V Ramesh, P Meer, Kernel-based object tracking, Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2003, 25(5): 564-577.
- D Comaniciu, V Ramesh, P Meer, Real-time tracking of non-rigid objects using mean shift. IEEE Conference on, 2000:142-149.
- H Liu, Z Yu, H Zha, et al. Robust human tracking based on multi-cue integration and mean-shift. Pattern Recognition Letters, 2009, 30(9): 827-837.
- H Wang, C Liu, L Xu, et al. Multiple feature fusion for tracking of moving objects in video surveillance Computational Intelligence and Security, 2008. CIS'08 International Conference on. IEEE, 2008, 1: 554-559.
- R T Collins, Y Liu, M Leordeanu, Online selection of discriminative tracking features. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2005, 27(10) 1631-1643.
- Y Dia, W Wei, Y Lin, An improved Mean-shift tracking algorithm based on color and texture feature. Journal of Zhejiang University (Engineering Science), 2012, 46(2) 212-217.
- T Ojala, M Pietikäinen, D Harwood, A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 1996, 29(1): 51-59.
- T Ojala, M Pietikainen, et al. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2002,24(7): 971-987.
- G Bishop, G Welch, An introduction to the kalman filter Proc of SIGGRAPH, Course, 2001, 8(27599-23175): 41.
- Object Tracking Using Meanshift Algorithm Combined with Kalman Filter on Robotic Fish International Symposium on Knowledge Acquisition and Modeling (KAM 2015)
- Spatio-Temporal Closed-Loop Object Detection Leonardo Galteri, Lorenzo Seidenari, Marco Bertini, and Alberto Del Bimbo, Member, IEEE IEEE TRANSACTIONS ON IMAGE PROCESSING 2017 ISBN 1057-7149
- Improved Target Tracking Based on Spatio-Temporal Learning Songmin Jia1et al Proceedings of IEEE International Conference on Information and Automation China 2016
Downloads
Published
Issue
Section
License
Copyright (c) IJSRST
This work is licensed under a Creative Commons Attribution 4.0 International License.
