Object Tracking with Sparse Representation based on HOG and LBP Features
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Visual object tracking is a fundamental problem in the field of computer vision, as it needs a proper model to account for drastic appearance changes that are caused by shape, textural, and illumination variations. In this paper, we propose a feature-based visual-object-tracking method with a sparse representation. Generally, most appearance-based models use the gray-scale pixel values of the input image, but this might be insufficient for a description of the target object under a variety of conditions. To obtain the proper information regarding the target object, the following combination of features has been exploited as a corresponding representation: First, the features of the target templates are extracted by using the HOG (histogram of gradient) and LBPs (local binary patterns); secondly, a feature-based sparsity is attained by solving the minimization problems, whereby the target object is represented by the selection of the minimum reconstruction error. The strengths of both features are exploited to enhance the overall performance of the tracker; furthermore, the proposed method is integrated with the particle-filter framework and achieves a promising result in terms of challenging tracking videos.
Abstract
Visual object tracking is a fundamental problem in the field of computer vision, as it needs a proper model to account for drastic appearance changes that are caused by shape, textural, and illumination variations. In this paper, we propose a feature-based visual-object-tracking method with a sparse representation. Generally, most appearance-based models use the gray-scale pixel values of the input image, but this might be insufficient for a description of the target object under a variety of conditions. To obtain the proper information regarding the target object, the following combination of features has been exploited as a corresponding representation: First, the features of the target templates are extracted by using the HOG (histogram of gradient) and LBPs (local binary patterns); secondly, a feature-based sparsity is attained by solving the minimization problems, whereby the target object is represented by the selection of the minimum reconstruction error. The strengths of both features are exploited to enhance the overall performance of the tracker; furthermore, the proposed method is integrated with the particle-filter framework and achieves a promising result in terms of challenging tracking videos.
참고문헌 (28)
- D. Comaniciu, "Kernelbased object tracking", IEEE Trans. Pattern Anal. Mach. Intell, 25(5), pp.564~575 (2003)
- P. Perez, "Colorbased probabilistic tracking", Proc. Eur. Conf. Computer Vision, pp.661~675 (2002)
- S. Avidan, "Ensemble tracking", IEEE Trans. Pattern Anal. Mach. Intell, 29(2), pp.261~271 (2007)
- D. Ross, "Incremental learning for robust visual tracking", Int. J. Computer Vision, 77(1-3), pp.125~141 (2008)
- H. Grabner, "On-line boosting and vision", Proc. IEEE Conf. Comput. Vision Pattern Recogn, pp.260~267 (2006)
- S. Wang, "Superpixel tracking", Proc. IEEE Int. Conf. Computer Vision, pp.1323~1330 (2011)
- A. Adam, "Robust fragments-based tracking using the integral histogram", Proc. IEEE Conf. Computer Vision Pattern Recognition, pp.798~805 (2006)
- S. Avidan, "Support vector tracking", IEEE Trans. Pattern Anal. Machine Intelligent, 26(8), pp.1064~1072 (2004)
- Q. Yu, "Online tracking and reacquisition using co-trained generative and discriminative trackers", Proc. Eur. Conf. Computer Vision, pp.678~679 (2008)
- W. Zhong, "Robust object tracking via sparsity-based collaborative model", Proc. IEEE Conf. Comput. Vision Pattern Recogn, pp.1838~1845 (2012)
- X. Mei, "Robust visual tracking using ℓ1 minimization", ICCV, pp.1436~1443 (2009)
- B. Liu, "Robust and fast collaborative tracking with two stage sparse optimization", ECCV, pp.624~637 (2010)
- A. Adam, "Robust fragments-based tracking using the integral histogram", CVPR, pp.798~805 (2006)
- J. Wright, "Robust face recognition via sparse representation", pp.210~227 (2009)
- J. Yang, "Image super-resolution via sparse representation", TIP, pp.2861~2873 (2010)
- B. Liu, "Robust tracking using local sparse appearance model and kselection", CVPR, pp.1313~1320 (2011)
- X. Li, "Robust Visual Tracking Based on Incremental Tensor Subspace Learning", Proc. ICCV, pp.1~8 (2007)
- B. Han, "Robust Feature based Object Tracking", SPIE DSS 2007 (2007)
- P. Tissainayagama, "Object tracking in image sequences using point features", Pattern Recognition, 38(1), pp.105~113 (2005)
- Zuren Feng, "A Multiple Features Image Tracking Algorithm", Fifth International Symposium on Computational Intelligence and Design, pp.77~80 (2012)
- Huiyu Zhoua, "Object tracking using SIFT features and mean shift", Computer Vision and Image Understanding, 113(3), pp.345~352 (2009)
- S. Fazli, "Particle Filter Based Object Tracking with Sift and Color Feature", Second International Conference on Machine Vision, pp.89~93 (2009)
- B. Babenko, "Visual tracking with on-line multiple instance learning", CVPR, pp.983~990 (2009)
- Z. Kalal, "P-N learning: Bootstrapping binary classifiers by structural constraints", CVPR, pp.49~56 (2010)
- J. Kwon, "Visual tracking decomposition", CVPR, pp.1269~1276 (2010)
- M. Everingham, "The PASCAL Visual Object Classes Challenge" (2010)
- G. R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface", Intel Technology Journal, pp.13~27 (1998)
- Dong Wang, "Online Object Tracking With Sparse Prototypes", IEEE Transaction on Image Processing, 22(1), pp.314~325 (2013)