Real-Time Object Tracking Algorithm Based on Adaptive Compressive Feature Selection
QI Mei-Bin1,2, LU Lei1, YANG Xun1, YANG Yan-Fang3, JIANG Jian-Guo1,2
1.School of Computer and Information, Hefei University of Technology, Hefei 230009 2.Engineering Research Center of Safety Critical Industrial Measurement and Control Technology, Ministry of Education, Hefei University of Technology, Hefei 230009 3.School of Electronic Science and Applied Physics, Hefei University of Technology, Hefei 230009
Abstract Low dimensional features adopted by compressive tracking algorithm can not reconstruct the object effectively. To solve this problem, a real-time object tracking algorithm based on adaptive compressive feature selection is proposed in this paper. The high dimensional features meeting the requirement of object reconstruction are extracted. Then the lower dimensional features with a higher discrimination are selected as appearance model of the object to reduce the computational complexity. To select features adaptively a difference method is adopted to control the feature dimensionality. The experimental results demonstrate that the proposed algorithm are more robust and effective in real time than other state-of-the-art tracking algorithms.
[1] Ross D A, Lim J, Lin R S, et al. Incremental Learning for Robust Visual Tracking. International Journal of Computer Vision, 2008, 77(1/2/3): 125-141 [2] Mei X, Ling H. Robust Visual Tracking Using l1 Minimization // Proc of the 12thInternational Conference on Computer Vision. Kyoto, Japan, 2009: 1436-1443 [3] Wang D, Lu H C, Yang M H. Online Object Tracking with Sparse Prototypes.Trans on Image Processing, 2013, 22(1): 314-325 [4] Li H X, Shen C H, Shi Q F. Real-Time Visual Tracking Using Compressive Sensing // Proc of the 24thConference on Computer Vision and Pattern Recognition.Providence, USA, 2011: 1305-1312 [5] Grabner H, Grabner M, Bischof H. Real-Time Tracking via On-line Boosting // Proc of the British Machine Vision Conference. Edinburgh, UK, 2006, I: 47-56 [6] Babenko B, Yang M H, Belongie S. Visual Tracking with Online Multiple Instance Learning // Proc of theConference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 983-990 [7] Hare S, Saffari A, Torr P H S. Struck: Structured Output Tracking with Kernels // Proc of theInternational Conference on Computer Vision. Barcelona, Spain, 2011: 263-270 [8] Zhang K H, Zhang L, Yang M H. Real-Time Compressive Tracking // Proc of the 12th European Conference on Computer Vision. Flo-rence, Italy, 2012: 866-879 [9] Donoho D L. Compressed Sensing.Trans on Information Theory, 2006, 52(4): 1289-1306 [10] Baraniuk R, Davenport M, DeVore R, et al. A Simple Proof of the Restricted Isometry Property for Random Matrices. Constructive Approximation, 2008, 28(3): 253-263 [11] Achlioptas D. Database-Friendly Random Projections: Johnson-Lindenstrauss with Binary Coins. Journal of Computer and System Sciences, 2003, 66(4): 671-687 [12] Ng A Y, Jordan M I. On Discriminative vs. Generative Classifiers: A Comparison of Logistic Regression and Naive Bayes [EB/OL]. [2014-01-20]. http:// papers.nips.cc/paper/2020-on-discriminative-vs-generative-classifiers-a-comparison-of-logistic-regression-and-naive-bayes.pdf [13] Diaconis P, Freedman D. Asymptotics of Graphical Projection Pursuit. The Annals of Statistics, 1984, 12(3): 793-815 [14] Collins R T, Liu Y X, Leordeanu M. Online Selection of Discriminative Tracking Features.Trans on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643 [15] Zhang K H, Zhang L, Yang M H. Real-Time Object Tracking via Online Discriminative Feature Selection.Trans on Image Processing, 2013, 22(12): 4664-4677
2015, Vol. 28 
