Abstract—A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed. The feature histogram-based target representations are regularized by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples, the new method successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data association techniques is also discussed. We describe only a few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking. Index Terms—Nonrigid object tracking, target localization and representation, spatially-smooth similarity function, Bhattacharyya coefficient, face tracking. 1
|
4364
|
Elements of Information Theory
– Cover, Thomas
- 1991
|
|
2103
|
A tutorial in hidden Markov models and selected applications in speech recognition
– Rabiner
- 1989
|
|
1663
|
Introduction to Statistical Pattern Recognition
– Fukunaga
- 1990
|
|
925
|
Color indexing
– Swain, Ballard
- 1991
|
|
720
|
Pfinder: Realtime tracking of the human body
– Wren, Azarbayejani, et al.
- 1997
|
|
634
|
Condensation – conditional density propagation for visual tracking
– Isard, Blake
- 1998
|
|
537
|
Novel approach to nonlinear/non-Gaussian Bayesian state estimation
– Gordon, Salmond, et al.
- 1993
|
|
459
|
Tracking and data association
– Bar-Shalom, Fortmann
- 1987
|
|
433
|
Alignment by maximization of mutual information
– Viola
- 1995
|
|
398
|
Mean Shift: A Robust Approach Toward Feature Space Analysis
– Comaniciu, Meer
|
|
360
|
A tutorial on particle filters for online nonlinear, non-Gaussian Bayesian tracking
– Arulampalam, Maskell, et al.
- 2002
|
|
311
|
Visual analysis of human movement: A survey
– Gavrila
- 1999
|
|
276
|
Real-time tracking of non-rigid objects using mean shift
– Comaniciu, Ramesh, et al.
- 2000
|
|
272
|
On sequential Monte Carlo sampling methods for Bayesian filtering
– Doucet, Godsill, et al.
|
|
225
|
Multivariate Density Estimation
– Scott
- 1992
|
|
193
|
An algorithm for tracking multiple targets
– Reid
- 1979
|
|
178
|
Divergence Measures Based on the Shannon Entropy
– Lin
- 1991
|
|
160
|
Condensation—conditional density propagation for visual tracking
– Isard, Blake
- 1998
|
|
159
|
Elliptical Head Tracking Using Intensity Gradients and Color Histograms
– Birchfield
- 1998
|
|
158
|
Non-parametric model for background subtraction
– Elgammal, Harwood, et al.
- 2000
|
|
157
|
Human motion analysis: a review
– Aggarwal, Cai
- 1997
|
|
152
|
A new extension of the Kalman filter to nonlinear systems
– Julier, Uhlmann
- 1997
|
|
142
|
A probabilistic exclusion principle for tracking multiple objects
– MacCormick, Blake
- 2000
|
|
127
|
A multiple hypothesis approach to figure tracking
– Cham, Rehg
- 1999
|
|
108
|
W4: Who, when, where, what: A real time system for detecting and tracking people
– Haritaoglu, Harwood, et al.
- 1998
|
|
104
|
T.F.: Robust online appearance models for visual tracking
– Jepson, Fleet, et al.
|
|
101
|
Moving target classification and tracking from real-time video
– Lipton, Fujiyoshi, et al.
- 1998
|
|
93
|
An Efficient Implementation of Reid’s Multiple Hypothesis Tracking Algorithm and Its Evaluation for the Purpose of Visual Tracking
– Cox, Hingorani
- 1996
|
|
92
|
Color-Based Probabilistic Tracking
– Pèrez, Hue, et al.
- 2002
|
|
90
|
Empirical Evaluation of Dissimilarity Measures for Color and Texture
– Puzicha, Rubner, et al.
- 1999
|
|
89
|
Real-Time Tracking of Image Regions with Changes
– Hager, Belhumeur
- 1996
|
|
86
|
Multi-camera multi-person tracking for EasyLiving
– Krumm, Harris, et al.
- 2000
|
|
81
|
Tracking of persons in monocular image sequences
– Wachter, Nagel
- 1997
|
|
77
|
Non-Gaussian state-space modeling of nonstationary time series
– Kitagawa
- 1987
|
|
76
|
Active blobs
– Sclaroff, Isidoro
- 1998
|
|
73
|
The Divergence and Bhattacharyya Distance Measures in Signal Selection
– Kailath
- 1967
|
|
73
|
Covariance scaled sampling for monocular 3d body tracking
– Sminchisescu, Triggs
- 2001
|
|
65
|
Algorithms for cooperative multisensor surveillance
– Collins, Lipton, et al.
- 2001
|
|
61
|
Tracking colour objects using adaptive mixture models
– Raja, Mckenna, et al.
- 1999
|
|
55
|
Real-time closed-world tracking
– INTILLE, DAVIS, et al.
- 1997
|
|
52
|
Probabilistic data association methods for tracking complex visual objects
– Rasmussen, Hager
|
|
50
|
Optical flow constraints on deformable models with applications to face tracking
– Carlo, Metaxas
- 2000
|
|
49
|
D.: Color-based tracking of heads and other mobile objects at video frame rates
– Fieguth, Terzopoulos
- 1997
|
|
49
|
Unifying Maximum Likelihood Approaches in Medical Image Registration
– Roche, Malandain, et al.
- 2000
|
|
48
|
Finding waldo, or focus of attention using local color information
– Ennesser, Medioni
- 1995
|
|
44
|
Spatial color indexing and applications
– Huang, Kumar, et al.
- 1998
|
|
44
|
Bayesian multi-camera surveillance
– Kettnaker, Zabih
- 1999
|
|
42
|
Support vector tracking
– Avidan
|
|
42
|
View-invariant representation and recognition of actions
– Rao, Yilmaz, et al.
|
|
41
|
Region tracking through image sequences
– Bascle, Deriche
- 1995
|
