Abstract：The classical mean shift algorithm is extended to be the adaptive bandwidth mean shift algorithm,and then the adaptive bandwidth mean shift object tracking algorithm(ABMSOT) is proposed.The former gives the general adaptive bandwidth mean shift framework for seeking the local maxima,and the latter can simultaneously tracks the position,scale and orientation in real time.For ABMSOT,the feature histogram weighted by a kernel with adaptive bandwidth is used to represent the target model and the candidate model.Similarity of the target model and the candidate model is measured by Bhattacharyya coefficient.A two step method is used iteratively to find the most probable target position,scale and orientation.The first step finds the object position using a mean shift iteration,and the second step finds the bandwidth matrix which best describes scale and orientation of the object region.The convergence of the two algorithms is proved theoretically.Experiments show that ABMSOT can successfully track the position,scale and orientation in real time.
[1] Comaniciu D,Ramesh V,Meer P,et al.Real-time tracking of non-rigid objects using mean shift[A].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].Los Alamitos,CA,USA:IEEE Computer Society,2000.142-149.
[2] Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[3] Chen H T,Liu T L.Trust-region methods for real-time tracking[A].Proceedings of the IEEE International Conference on Computer Vision[C].Piscataway,NJ,USA:IEEE,2001.717-722.
[4] Yang C J,Duraiswami R,Davis L.Efficient mean-shift tracking via a new similarity measure[A].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].Los Alamitos,CA,USA:IEEE Computer Society,2005.176-183.
[5] Bradski G R.Computer vision face tracking for use in a perceptual user interface[EB/OL].http://download.intel.com/technology/itj/q21998/pdf/camshift.pdf.
[6] Comaniciu D.Bayesian kernel tracking[A].Proceedings of the 24th DAGM Symposium on Pattern Recognition[C].Berlin,Germany:Springer-Verlag,2002.438-445.
[7] Xu D,Wang Y M,An J W.Applying a new spatial color histogram in mean-shift based tracking algorithm[EB/OL].http://pixel.otago.ac.nz/ipapers/72.pdf,2005.
[8] Birchfield S T,Rangarajan S.Spatiograms versus histograms for region-based tracking[A].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].Los Alamitos,CA,USA:IEEE Computer Society,2005.1158-1163.
[9] Jeong M H,You B J,Oh Y,et al.Adaptive mean-shift tracking with novel color model[A].Proceedings of the IEEE International Conference on Mechatronics and Automation[C].Piscataway,NJ,USA:IEEE,2005.1329-1333.
[10] Yang C,Duraiswami R,Elgammal A,et al.Real-time kernel-based tracking in joint feature-spatial spaces[EB/OL].http://www.cs.umd.edu/Library/TRs/CS-TR-4567/CS-TR-4567.pdf.
[11] Elgammal A,Duraiswami R,Davis L S.Probabilistic tracking in joint feature-spatial spaces[A].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].Piscataway,NJ,USA:IEEE,2003.781-788.
[12] Nedovic V,Liem M,Corzilius M,et al.Kernel-based object tracking using adaptive feature selection[EB/OL].http://staff.science.uva.nl/～vnedovic/ProfileProject2005/projectReport.pdf,2005.
[13] Weng M Y,He M Q,Zhang Y F.An adaptive implementation of the kernel-based object tracking method[A].Proceedings of the IEEE International Conference on Innovative Computing,Information and Control[C].Piscataway,NJ,USA:IEEE,2006.354-357.
[14] Peng N S,Yang J,Liu Z.Mean shift blob tracking with kernel histogram filtering and hypothesis testing[J].Pattern Recognition Letters,2005,26(5):605-614.
[15] Porikli F,Tuzel O.Object tracking in low-frame-rate video[A].Proceedings of SPIE (vol.5685)[C].Bellingham,WA,USA:SPIE,2005.72-79.
[16] Zhu Z W,Ji Q,Fujimura K,et al.Combining Kalman filtering and mean shift for real time eye tracking under active IR illumination[A].Proceedings of the International Conference on Pattern Recognition[C].Piscataway,NJ,USA:IEEE,2002.318-321.
[17] Shan C F,Wei Y C,Tan T N,et al.Real time hand tracking by combining particle filtering and mean shift[A].Proceedings of the 6th IEEE International Conference on Automatic Face and Gesture Recognition[C].Piscataway,NJ,USA:IEEE,2004.669-674.
[18] Leung A P,Gong S G.Mean-shift tracking with random sampling[EB/OL].http://www.bmva.ac.uk/bmvc/2006/papers/266.pdf,2006.
[19] Shen C H,Brooks M J,van den Hengel A.Fast global kernel density mode seeking:Applications to localization and tracking[J].IEEE Transactions on Image Processing,2007,16(5):1457-1469.
[20] Collins R T.Mean-shift blob tracking through scale space[A].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].Los Alamitos,CA,USA:IEEE Computer Society,2003.234-240.
[21] Zivkovic Z,Krose B.An EM-like algorithm for color-histogram-based object tracking[A].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].Los Alamitos,CA,USA:IEEE Computer Society,2004.798-803.
[22] Zivkovic Z,Krose B.A probabilistic model for an EM-like object tracking algorithm using color-histograms[A].Proceedings of the 6th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance[C].Piscataway,NJ,USA:IEEE,2004.73-82.
[23] Yilmaz A.Object tracking by asymmetric kernel mean shift with automatic scale and orientation selection[A].Procceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Los Alamitos,CA,USA:IEEE Computer Society,2007.1-6.
[24] 齐苏敏,黄贤武,伊怀峰.基于各向异性核函数的均值漂移跟踪算法[J].电子与信息学报,2007,29(3):686-689.
[25] Cheng Y Z.Mean shift,mode seeking,and clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
