ABSTRACT
Sparse representation is widely used in visual tracking thanks to its efficiency and ability to handle appearance changes. In this paper, we propose to improve the original mean shift tracking algorithm, by defining its target model and candidates with a sparse approximation. The Method of Optimal Directions MOD is employed to learn an over-complete dictionary, afterward the Orthogonal Matching Pursuit OMP is used to present the appearance model with the potential atoms of the dictionary. We project the generated vector into the successive frames to detect the target region. Thus, the exploitation of the spatial information is demonstrated by the process of back-projecting the signature vector template in each frame. Our tracker attempts to perfectly localize random objects in different scenarios, and proved to be robust against different challenges. In fact, the proposed approach guarantees a total separation between the target and its background. Our tracker proved to be more stable and less prone to drift away.
- Amit Adam, Ehud Rivlin, and Ilan Shimshoni. 2006. Robust fragments-based tracking using the integral histogram. In Computer vision and pattern recognition, 2006 IEEE Computer Society Conference on, Vol. 1. IEEE, 798--805. Google ScholarDigital Library
- Michal Aharon, Michael Elad, and Alfred Bruckstein. 2006. r mk-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on signal processing 54, 11 (2006), 4311--4322. Google ScholarDigital Library
- Nasir Ahmed, T_ Natarajan, and Kamisetty R Rao. 1974. Discrete cosine transform. IEEE transactions on Computers 100, 1 (1974), 90--93. Google ScholarDigital Library
- Amir Aliabadian, Esmaeil Akbarpour, and Mohammad Yosefi. 2012. Kernel Based Approach toward Automatic object Detection and Tracking in Surveillance Systems. International Journal of Soft Computing and Engineering 2 (2012), 82--87.Google Scholar
- R Venkatesh Babu, Patrick Pérez, and Patrick Bouthemy. 2007. Robust tracking with motion estimation and local kernel-based color modeling. Image and Vision Computing 25, 8 (2007), 1205--1216. Google ScholarDigital Library
- Sebastian Brutzer, Benjamin Höferlin, and Gunther Heidemann. 2011. Evaluation of background subtraction techniques for video surveillance. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 1937--1944. Google ScholarDigital Library
- Dorin Comaniciu, Visvanathan Ramesh, and Peter Meer. 2000. Real-time tracking of non-rigid objects using mean shift. In Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on, vol. 2. IEEE, 142--149.Google ScholarCross Ref
- Dorin Comaniciu, Visvanathan Ramesh, and Peter Meer. 2003. Kernel-based object tracking. Pattern Analysis and Machine Intelligence, IEEE Transactions on 25, 5 (2003), 564--577. Google ScholarDigital Library
- Geoff Davis, Stephane Mallat, and Marco Avellaneda. 1997. Adaptive greedy approximations. Constructive approximation 13, 1 (1997), 57--98.Google Scholar
- Dawei Du, Honggang Qi, Qingming Huang, Wei Zeng, and Changhua Zhang. 2013. Abnormal event detection in crowded scenes based on Structural Multi-scale Motion Interrelated Patterns. In Multimedia and Expo (ICME), 2013 IEEE International Conference on. IEEE, 1--6.Google Scholar
- Kjersti Engan, Sven Ole Aase, and J Hakon Husoy. 1999. Method of optimal directions for frame design. In Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on, Vol. 5. IEEE, 2443--2446. Google ScholarDigital Library
- Kjersti Engan, Sven Ole Aase, and John Håkon Husøy. 2000. Multi-frame compression: Theory and design. Signal Processing 80, 10 (2000), 2121--2140. Google ScholarDigital Library
- Sam Hare, Stuart Golodetz, Amir Saffari, Vibhav Vineet, Ming-Ming Cheng, Stephen L Hicks, and Philip HS Torr. 2016. Struck: Structured output tracking with kernels. IEEE transactions on pattern analysis and machine intelligence 38, 10 (2016), 2096--2109. Google ScholarDigital Library
- João F Henriques, Rui Caseiro, Pedro Martins, and Jorge Batista. 2015. High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence 37, 3 (2015), 583--596.Google ScholarDigital Library
- Baiyang Liu, Junzhou Huang, Casimir Kulikowski, and Lin Yang. 2013. Robust visual tracking using local sparse appearance model and k-selection. IEEE transactions on pattern analysis and machine intelligence 35, 12 (2013), 2968--2981. Google ScholarDigital Library
- Rhys Martin and Ognjen Arandjelović. 2010. Multiple-object tracking in cluttered and crowded public spaces. In Advances in Visual Computing. Springer, 89--98. Google ScholarDigital Library
- Xue Mei and Haibin Ling. 2011. Robust visual tracking and vehicle classification via sparse representation. IEEE transactions on pattern analysis and machine intelligence 33, 11 (2011), 2259--2272. Google ScholarDigital Library
- Jifeng Ning, Lei Zhang, David Zhang, and Chengke Wu. 2012. Robust mean-shift tracking with corrected background-weighted histogram. IET computer vision 6, 1 (2012), 62--69.Google Scholar
- Bruno A Olshausen and David J Field. 1996. Natural image statistics and efficient coding. Network: computation in neural systems 7, 2 (1996), 333--339.Google Scholar
- Yagyensh Chandra Pati, Ramin Rezaiifar, and PS Krishnaprasad. 1993. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. In Signals, Systems and Computers, 1993. 1993 Conference Record of The Twenty-Seventh Asilomar Conference on. IEEE, 40--44.Google ScholarCross Ref
- Akhil Pratap Singh and Agya Mishra. 2011. Wavelet Based Watermarking on Digital Image. Indian Journal of Computer Science and Engineering 1, 2 (2011), 86--91.Google Scholar
- Oumaima Sliti, Habib Hamam, and Hamid Amiri. 2018. CLBP for scale and orientation adaptive mean shift tracking. Journal of King Saud University-Computer and Information Sciences 30, 3 (2018), 416--429.Google ScholarCross Ref
- Oumaima Sliti, Habib Hamam, Faouzi Benzarti, and Hamid Amiri. 2014. A more robust mean shift tracker using joint monogenic signal analysis and color histogram. In Pattern Recognition (ICPR), 2014 22nd International Conference on. IEEE, 2453--2458. Google ScholarDigital Library
- Chetna Sachdeva Snekha and Rajesh Birok. {n. d.}. Real Time Object Tracking Using Different Mean Shift Techniques-a Review. International Journal of Soft Computing and Engineering (IJSCE) ISSN ({n. d.}), 2231--2307.Google Scholar
- Michael J Swain and Dana H Ballard. 1991. Color indexing. International journal of computer vision 7, 1 (1991), 11--32. Google ScholarDigital Library
- Chongjing Wang, Xu Zhao, Zhe Wu, and Yuncai Liu. 2013. Motion pattern analysis in crowded scenes based on hybrid generative-discriminative feature maps. In Image Processing (ICIP), 2013 20th IEEE International Conference on. IEEE, 2837--2841.Google ScholarCross Ref
- Yi Wu, Jongwoo Lim, and Ming-Hsuan Yang. 2013. Online object tracking: A benchmark. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2411--2418. Google ScholarDigital Library
- Changjiang Yang, Ramani Duraiswami, and Larry Davis. 2005. Efficient mean-shift tracking via a new similarity measure. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, Vol. 1. IEEE, 176--183. Google ScholarDigital Library
- Alper Yilmaz, Khurram Shafique, and Mubarak Shah. 2003. Target tracking in airborne forward looking infrared imagery. Image and Vision Computing 21, 7 (2003), 623--635.Google ScholarCross Ref
- Kaihua Zhang and Huihui Song. 2013. Real-time visual tracking via online weighted multiple instance learning. Pattern Recognition 46, 1 (2013), 397--411. Google ScholarDigital Library
- Kaihua Zhang, Lei Zhang, Qingshan Liu, David Zhang, and Ming-Hsuan Yang. 2014. Fast visual tracking via dense spatio-temporal context learning. In European Conference on Computer Vision. Springer, 127--141.Google ScholarCross Ref
Index Terms
- Method of optimal directions for visual tracking
Recommendations
Robust Visual Tracking Using Local Sparse Appearance Model and K-Selection
Online learned tracking is widely used for its adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of errors during the self-updating, especially for occluded scenarios. The recent ...
Hand-Eye Camera Calibration with an Optical Tracking System
ICDSC '18: Proceedings of the 12th International Conference on Distributed Smart CamerasThis paper presents a method for hand-eye camera calibration via an optical tracking system (OTS) faciltating robotic applications. The camera pose cannot be directly tracked via the OTS. Because of this, a transformation matrix between a marker-plate ...
Efficient visual tracking via sparse representation and back-projection histogram
AbstractSparse modeling has been successfully applied in object tracking methods. When the algorithms lose track of the target, it usually keeps locating a part of the background or starts locating another different object, which has a similar appearance ...
Comments