research-article

Online Selection of Discriminative Tracking Features

Authors:

Robert T. Collins,

Marius LeordeanuAuthors Info & Claims

IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 27, Issue 10

Pages 1631 - 1643

https://doi.org/10.1109/TPAMI.2005.205

Published: 01 October 2005 Publication History

Abstract

This paper presents an online feature selection mechanism for evaluating multiple features while tracking and adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. Given a set of seed features, we compute log likelihood ratios of class conditional sample densities from object and background to form a new set of candidate features tailored to the local object/background discrimination task. The two-class variance ratio is used to rank these new features according to how well they separate sample distributions of object and background pixels. This feature evaluation mechanism is embedded in a mean-shift tracking system that adaptively selects the top-ranked discriminative features for tracking. Examples are presented that demonstrate how this method adapts to changing appearances of both tracked object and scene background. We note susceptibility of the variance ratio feature selection method to distraction by spatially correlated background clutter and develop an additional approach that seeks to minimize the likelihood of distraction.

References

[1]

Y. Bar-Shalom and T. Fortmann, <i>Tracking and Data Association.</i> Academic Press, 1988.]]

Digital Library

[2]

C. Bishop, <i>Neural Networks for Pattern Recognition.</i> Clarendon Press, 1997.]]

Digital Library

[3]

S. Blackman and R. Popoli, <i>Design and Analysis of Modern Tracking Systems.</i> Artech House, 1999.]]

[4]

G. Bradski, “Computer Vision Face Tracking for Use in a Perceptual User Interface,” <i>Proc. IEEE Workshop Applications of Computer Vision,</i> pp. 214-219, 1998.]]

Digital Library

[5]

Y. Cheng, “Mean-Shift, Mode Seeking, and Clustering,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 17, no. 8, pp. 790-799, Aug. 1995.]]

Digital Library

[6]

R. Collins A. Lipton H. Fujiyoshi and T. Kanade, “Algorithms for Cooperative Multi-Sensor Surveillance,” <i>Proc. IEEE,</i> vol. 89,no. 10, pp. 1456-1477, Oct. 2001.]]

[7]

D. Comaniciu V. Ramesh and P. Meer, “Kernel-Based Object Tracking,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 25, no. 5, pp. 564-577, May 2003.]]

Digital Library

[8]

T. Cootes G. Edwards and C. Taylor, “Active Appearance Models,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 23, no. 6, pp. 681-685, June 2001.]]

Digital Library

[9]

J. Davis, “Recognizing Movement Using Motion Histograms,” Technical Report No. 487, MIT, Mar. 1999.]]

[10]

A. Elgammal R. Duraiswami and L. Davis, “Probabilistic Tracking in Joint Feature-Spatial Spaces,” <i>Proc. IEEE Conf. Computer Vision and Pattern Recognition,</i> vol. 1, pp. 781-788, June 2003.]]

[11]

W. Freeman and M. Roth, “Orientation Histograms for Hand Gesture Recognition,” <i>Proc. IEEE Workshop Automatic Face and Gesture Recognition,</i> June 1995.]]

[12]

E. Hayman and J.O. Eklundh, “Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation,” <i>Proc. European Conf. Computer Vision,</i> pp. 469-486, 2002.]]

Digital Library

[13]

S. Huang S. Kumar M. Mitra W. Zhu and R. Zabih, “Spatial Color Indexing and Applications,” <i>Int'l J. Computer Vision,</i> vol. 35, no. 3, pp. 245-268, 1999.]]

Digital Library

[14]

M. Irani and P. Anandan, “A Unified Approach to Moving Object Detection in 2D and 3D Scenes,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 20, no. 6, pp. 577-589, June 1998.]]

Digital Library

[15]

M. Isard and A. Blake, “CONDENSATION—Conditional Density Propagation for Visual Tracking,” <i>Int'l J. Computer Vision,</i> vol. 29, no. 1, pp. 5-28, 1998.]]

Digital Library

[16]

D. Koller K. Daniilidis and H. Nagel, “Model-Based Object Tracking in Monocular Image Sequences of Road Traffic Scenes,” <i>Int'l J. Computer Vision,</i> vol. 10, no. 3, pp. 257-281, 1993.]]

[17]

B. Manjunath and W. Ma, “Texture Features for Browsing and Retrieval of Image Data,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 18, no. 8, pp. 837-842, Aug. 1996.]]

Digital Library

[18]

Y. Liu K. Schmidt J. Cohn and S. Mitra, “Facial Asymmetry Quantification for Expression Invariant Human Identification,” <i>Computer Vision and Image Understanding,</i> vol. 91, nos. 1/2, pp. 138-159, July 2003.]]

Digital Library

[19]

Y. Liu and J. Palmer, “A Quantified Study of Facial Asymmetry in 3D Faces,” <i>Proc. IEEE Int'l Workshop Modeling of Faces and Gestures,</i> pp. 222-229, Oct. 2003.]]

Digital Library

[20]

Y. Liu, et al., “Discriminative MR Image Feature Analysis for Automatic Schizophrenia and Alzheimer's Disease Classification,” <i>Proc. Seventh Int'l Conf. Medical Image Computing and Computer Aided Intervention,</i> pp. 393-401, Oct. 2004.]]

[21]

I. Matthews and S. Baker, “Active Appearance Models Revisited,” <i>Int'l J. Computer Vision,</i> vol. 60, no. 2, pp. 135-164, Nov. 2004.]]

Digital Library

[22]

I. Matthews T. Iashikawa and S. Baker, “The Template Update Problem,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 26, no. 6, pp. 810-815, June 2004.]]

Digital Library

[23]

C. Rasmussen and G. Hager, “Joint Probabilistic Techniques for Tracking Multi-Part Objects,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 23, no. 6, pp. 560-576, June 2001.]]

Digital Library

[24]

D. Reid, “An Algorithm for Tracking Multiple Targets,” <i>IEEE Trans. Aerospace and Electronic Systems,</i> vol. 17, pp. 122-130, Jan. 1981.]]

[25]

S. Smith and J. Brady, “ASSET-2: Real-Time Motion Segmentation and Shape Tracking,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 17, no. 8, pp. 814-820, Aug. 1995.]]

Digital Library

[26]

C. Stauffer and W.E.L. Grimson, “Learning Patterns of Activity Using Real-Time Tracking,” <i>IEEE Trans. Pattern Analysis and Machine Intelligence,</i> vol. 22, no. 8, pp. 747-757, Aug. 2000.]]

Digital Library

[27]

H. Stern and B. Efros, “Adaptive Color Space Switching for Face Tracking in Multi-Colored Lighting Environments,” <i>IEEE Int'l Conf. Automatic Face and Gesture Recognition,</i> pp. 249-254, May 2002.]]

Digital Library

[28]

G. Toussaint, “Note on Optimal Selection of Independent Binary-Valued Features for Pattern Recognition,” <i>IEEE Trans. Information Theory,</i> vol. 17, no. 5, pp. 618-618, 1971.]]

Digital Library

[29]

K. Toyama and Y. Wu, “Bootstrap Initialization of Nonparameteric Texture Models for Tracking,” <i>Proc. European Conf. Computer Vision,</i> vol. 2, pp. 119-133, 2000.]]

Digital Library

[30]

B. Zarit B. Super and F. Quek, “Comparison of Five Color Models in Skin Pixel Classification,” <i>Proc. Int'l Workshop Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems,</i> pp. 58-63, Sept. 1999.]]

Digital Library

[31]

J. Zhang and Y. Liu, “Cervical Cancer Detection Using SVM-Based Feature Screening,” <i>Proc. Seventh Int'l Conf. Medical Image Computing and Computer Aided Intervention,</i> pp. 873-880, Oct. 2004.]]

[32]

X. Zhou R. Collins T. Kanade and P. Metes, “A Master-Slave System to Acquire Biometric Imagery of Humans at a Distance,” <i>Proc. ACM SIGGM Int'l Workshop Video Surveillance,</i> pp. 113-120, Nov. 2003.]]

Digital Library

[33]

Z. Zivkovic and B. Krose, “An EM-Like Algorithm for Color Histogram Based Object Tracking,” <i>Proc. IEEE Conf. Computer Vision and Pattern Recognition,</i> pp. 798-803, June 2004.]]

Cited By

Hao ZLiu GZhang HWang F(2024)Robust cascaded-parallel visual tracking using collaborative color and correlation filter modelsMultimedia Tools and Applications10.1007/s11042-023-15614-483:1(33-59)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1007/s11042-023-15614-4
Osojnik APanov PDžeroski S(2023)iSOUP-SymRF: Symbolic Feature Ranking with Random Forests in Online Multi-target RegressionDiscovery Science10.1007/978-3-031-45275-8_4(48-63)Online publication date: 9-Oct-2023
https://dl.acm.org/doi/10.1007/978-3-031-45275-8_4
Nai KLi ZWang H(2022)Learning Channel-Aware Correlation Filters for Robust Object TrackingIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2022.318627632:11(7843-7857)Online publication date: 1-Nov-2022
https://dl.acm.org/doi/10.1109/TCSVT.2022.3186276
Show More Cited By

Recommendations

On-Line Selection of Discriminative Tracking Features
ICCV '03: Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2

This paper presents a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. Our hypothesisis that the features that best discriminate between object and background are also ...
Read More
Color invariant SURF in discriminative object tracking
ECCV'10: Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II

Tracking can be seen as an online learning problem, where the focus is on discriminating object from background. From this point of view, features play a key role as the tracking accuracy depends on how well the feature distinguishes object and ...
Read More
Persistent tracking of static scene features using geometry

Despite many alternatives to feature tracking problem, iterative least squares solution solving the optical flow constraint has been the most popular approach used by many in the field. This paper attempts to leverage the former efforts to enhance ...
Read More

Comments

Information & Contributors

Information

Published In

cover image IEEE Transactions on Pattern Analysis and Machine Intelligence

IEEE Transactions on Pattern Analysis and Machine Intelligence Volume 27, Issue 10

October 2005

175 pages

ISSN:0162-8828

Issue’s Table of Contents

Copyright © 2005.

Publisher

IEEE Computer Society

United States

Publication History

Published: 01 October 2005

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

262
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Other Metrics

View Author Metrics

Citations

Cited By

Hao ZLiu GZhang HWang F(2024)Robust cascaded-parallel visual tracking using collaborative color and correlation filter modelsMultimedia Tools and Applications10.1007/s11042-023-15614-483:1(33-59)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1007/s11042-023-15614-4
Osojnik APanov PDžeroski S(2023)iSOUP-SymRF: Symbolic Feature Ranking with Random Forests in Online Multi-target RegressionDiscovery Science10.1007/978-3-031-45275-8_4(48-63)Online publication date: 9-Oct-2023
https://dl.acm.org/doi/10.1007/978-3-031-45275-8_4
Nai KLi ZWang H(2022)Learning Channel-Aware Correlation Filters for Robust Object TrackingIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2022.318627632:11(7843-7857)Online publication date: 1-Nov-2022
https://dl.acm.org/doi/10.1109/TCSVT.2022.3186276
Zhang HZhang ZZhang JZhao YGao M(2022)Online bionic visual siamese tracking based on mixed time-event triggering mechanismMultimedia Tools and Applications10.1007/s11042-022-13930-982:10(15199-15222)Online publication date: 29-Sep-2022
https://dl.acm.org/doi/10.1007/s11042-022-13930-9
Gao BSpratling M(2022)Explaining away results in more robust visual trackingThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-022-02466-639:5(2081-2095)Online publication date: 5-Apr-2022
https://dl.acm.org/doi/10.1007/s00371-022-02466-6
Chabane MKhelifa BTariq B(2021)Adaptive fast scale estimation, with accurate online model update based on kernelized correlation filterMachine Vision and Applications10.1007/s00138-021-01216-332:4Online publication date: 1-Jul-2021
https://dl.acm.org/doi/10.1007/s00138-021-01216-3
Guo CZhang ZLi JJiang XZhang JZhang L(2020)Robust Visual Tracking Using Kernel Sparse Coding on Multiple Covariance DescriptorsACM Transactions on Multimedia Computing, Communications, and Applications10.1145/336030816:1s(1-22)Online publication date: 17-Apr-2020
https://dl.acm.org/doi/10.1145/3360308
Jeon BShim DJin Kim H(2020)Detection-Aware Trajectory Generation for a Drone Cinematographer2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)10.1109/IROS45743.2020.9341368(1450-1457)Online publication date: 24-Oct-2020
https://dl.acm.org/doi/10.1109/IROS45743.2020.9341368
Zhang SHuang JLim JGong YWang JAhuja NYang M(2020)Tracking Persons-of-Interest via Unsupervised Representation AdaptationInternational Journal of Computer Vision10.1007/s11263-019-01212-1128:1(96-120)Online publication date: 1-Jan-2020
https://dl.acm.org/doi/10.1007/s11263-019-01212-1
Lee SQian GBeach A(2020)Real-Time Person Tracking and Association on Doorbell CamerasAdvances in Visual Computing10.1007/978-3-030-64559-5_36(458-469)Online publication date: 5-Oct-2020
https://dl.acm.org/doi/10.1007/978-3-030-64559-5_36
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents