#### DMCA

## Kernel-Based Object Tracking (2003)

### Cached

### Download Links

- [www.caip.rutgers.edu]
- [www.wisdom.weizmann.ac.il]
- [www.comaniciu.net]
- [www.soe.ucsc.edu]
- [www.cim.mcgill.ca]
- [www.cim.mcgill.ca]
- [www.wisdom.weizmann.ac.il]
- [classes.soe.ucsc.edu]
- [comaniciu.net]
- [www.xmt.be]
- [www.cs.drexel.edu]
- [www.cs.drexel.edu]
- [web.eecs.umich.edu]
- [www.caip.rutgers.edu]
- [coewww.rutgers.edu]
- [www.caip.rutgers.edu]
- [www.ee.duke.edu]
- [www.cs.ucf.edu]
- [www.cs.ucf.edu]
- DBLP

### Other Repositories/Bibliography

Citations: | 885 - 4 self |

### Citations

12158 | Elements of information theory - Cover, Thomas - 1991 |

5734 | A tutorial on hidden Markov models and selected applications in speech recognition
- Rabiner
- 1989
(Show Context)
Citation Context ...cretely sampled points to parameterize the mean and covariance of the posterior density. When the state space is discrete and consists of a finite number of states, Hidden Markov Models (HMM) filters =-=[60]-=- can be applied for tracking. The most general class of filters is represented by particle filters [45], also called bootstrap filters [31], which are based on Monte Carlo integration methods. The cur... |

3702 | Introduction to Statistical Pattern Recognition, 2nd ed - Fukunaga - 1990 |

2355 | P.: Mean shift: A robust approach toward feature space analysis
- Comaniciu, Meer
- 2002
(Show Context)
Citation Context ... kðxÞ at y in the current frame, with the data being weighted by wi (10). The mode of this density in the local neighborhood is the sought maximum that can be found employing the mean shift procedur=-=e [17-=-]. In this procedure, the kernel is recursively moved from the current location ^y 0 to the new location ^y 1 according to the relation ^y 1 P nh i1 xiwig P nh i1 wig ^y 0 xi h ^y 0 xi h 2 2 ; ð11Þ ... |

1958 | A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking
- Arulampalam, Maskell, et al.
- 2002
(Show Context)
Citation Context ...o integration methods. The current density of the state is represented by a set of random samples with associated weights and the new density is computed based on these samples and weights (see [23], =-=[3]-=- for reviews). The UKF can be employed to generate proposal distributions for particle filters, in which case the filter is called Unscented Particle Filter (UPF) [54]. When the tracking is performed ... |

1694 |
Novel approach to nonlinear/non-Gaussian Bayesian state estimation
- Gordon, Salmond, et al.
- 1993
(Show Context)
Citation Context ... finite number of states, Hidden Markov Models (HMM) filters [60] can be applied for tracking. The most general class of filters is represented by particle filters [45], also called bootstrap filters =-=[31]-=-, which are based on Monte Carlo integration methods. The current density of the state is represented by a set of random samples with associated 2 weights and the new density is computed based on thes... |

1602 | Color Indexing
- Swain, Ballard
- 1991
(Show Context)
Citation Context .... Therefore, Ch can be precalculated for a given kernel and different values of h. The 2. It has a clear geometric interpretation. Note that the Lp histogram metrics (including histogram intersection =-=-=-[71]) do not enforce the conditions Pm u1 ^qu 1 and Pm u1 ^pu 3. 4. 1. It uses discrete densities and, therefore, it is invariant to the scale of the target (up to quantization effects). It is valid f... |

1491 | Condensation: Conditional density propagation for visual tracking
- Isard, Blake
- 1998
(Show Context)
Citation Context ...laroff [65] used the Extended Kalman Filter to estimate a 3D object trajectory from 2D image motion. Particle filtering was first introduced in vision as the Condensation algorithm by Isard and Blake =-=[40]-=-. Probabilistic exclusion for tracking multiple objects was discussed in [51]. Wu and Huang developed an algorithm to integrate multiple target clues [76]. Li and Chellappa [48] proposed simultaneous ... |

1458 | Pfinder: real-time tracking of the human body
- Wren, Azarbayejani, et al.
- 1997
(Show Context)
Citation Context ...N REAL-TIME object tracking is the critical task in many computer vision applications such as surveillance [44], [16], [32], perceptual user interfaces [10], augmented reality [26], smart rooms [39], =-=[75]-=-, [47], object-based video compression [11], and driver assistance [34], [4]. Two major components can be distinguished in a typical visual tracker. Target Representation and Localization is mostly a ... |

1021 | On sequential Monte Carlo sampling methods for Bayesian filtering
- Doucet, Godsill, et al.
(Show Context)
Citation Context ...e Carlo integration methods. The current density of the state is represented by a set of random samples with associated weights and the new density is computed based on these samples and weights (see =-=[23]-=-, [3] for reviews). The UKF can be employed to generate proposal distributions for particle filters, in which case the filter is called Unscented Particle Filter (UPF) [54]. When the tracking is perfo... |

997 | III. Alignment by maximization of mutual information
- Viola, Wells
- 1995
(Show Context)
Citation Context ...lization. While the filtering and data association have their roots in control theory, algorithms for target representation and localization are specific to images and related to registration methods =-=[72]-=-, [64], [56]. Both target localization and registration maximizes a likelihood type function. The difference is that in tracking, as opposed to registration, only small changes are assumed in the loca... |

921 |
Tracking and Data Association
- Bar-Shalom, Fortmann
- 1988
(Show Context)
Citation Context ... complexity of a tracker as low as possible. The most abstract formulation of the filtering and data association process is through the state space approach for modeling discrete-time dynamic systems =-=[5]-=-. The information characterizing the target is defined by the state sequencefxkg k0;1;... , whose evolution in time is specified by the dynamic equation xk f kðxk 1; vkÞ. The available . D. Comanici... |

805 | Real-time tracking of non-rigid objects using mean shift
- Comaniciu, Ramesh, et al.
- 2000
(Show Context)
Citation Context ...e can introduce a large bias in the estimated location of the target, and the resulting measure is scale variant (see [37, p. 262] for a discussion). We mention that since its original publication in =-=[18]-=-, the idea of kernel-based tracking has been exploited and developed forward by various researchers. Chen and Liu [14] experimented with the same kernel-weighted histograms, but employed the Kullback-... |

744 | A new extension of the kalman filter to nonlinear systems
- Julier, Uhlman
- 1997
(Show Context)
Citation Context ... by linearization the Extended Kalman Filter (EKF) [5, p. 106] is obtained, the posterior density being still modeled as Gaussian. A recent alternative to the EKF is the Unscented Kalman Filter (UKF) =-=[42]-=- which uses a set of discretely sampled points to parameterize the mean and covariance of the posterior density. When the state space is discrete and consists of a finite number of states, Hidden Mark... |

728 | The Visual Analysis of Human Movement: A Survey
- Gavrila
- 1999
(Show Context)
Citation Context ...ted an affine tracker based on planar regions and anchor points. Tracking people, which raises many challenges due to the presence of large 3D, nonrigid motion, was extensively analyzed in [36], [1], =-=[30]-=-, [73]. Explicit tracking approaches of people [69] are timeconsuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the paper is to ... |

650 | Divergence measures based on the Shannon entropy
- Lin
- 1991
(Show Context)
Citation Context ...ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi ^puðyÞ^qu ; ð7Þ u1 the sample estimate of the Bhattacharyya coefficient between p and q [43]. The Bhattacharyya coefficient is a divergence-type measu=-=re -=-[49] which has a straightforward geometric interpretawhere is the Kronecker delta function. The normalization constant C is derived by imposing the condition Pm u1 ^qu 1, from where 1 C Pn i1 k kx? ik... |

581 | An algorithm for tracking multiple targets
- Reid
- 1979
(Show Context)
Citation Context ... p. 222], on the other hand, calculates the measurement-to-target association probabilities jointly across all the targets. A different strategy is represented by the Multiple Hypothesis Filter (MHF) =-=[63]-=-, [20], [5, p. 106] which evaluates the probability that a given target gave rise to a certain measurement sequence. The MHF formulation can be adapted to track the modes of the state density [13]. Th... |

536 | Non-parametric model for background subtraction
- Elgammal, Harwood, et al.
- 2000
(Show Context)
Citation Context ... of attraction of the mode covers the entire rectangular window. In controlled environments with fixed camera, additional geometric constraints (such as the expected scale) and background subtraction =-=[24]-=- can be exploited to improve the tracking process. The Subway-1 sequence (Fig. 4) is suitable for such an approach, however, the results presented here has been processed with the algorithm unchanged.... |

484 |
Condensation—conditional density propagation for visual tracking
- Isard, Blake
- 1998
(Show Context)
Citation Context ...roff [65] used the Extended Kalman Filter to estimate a 3D object trajectory from 2D image motion. Particle filtering was first introduced, in vision, as the Condensation algorithm by Isard and Blake =-=[40]-=-. Probabilistic exclusion for tracking multiple objects was discussed in [51]. Wu and Huang developed an algorithm to integrate multiple target clues [76]. Li and Chellappa [48] proposed simultaneous ... |

470 | Multivariate Density Estimation
- Scott
- 1996
(Show Context)
Citation Context ...ams should be used. Thus, we have target model : ^q fg ^qu u1...m target candidate : ^pðyÞf^puðyÞgu1...m X m u1 Xm u1 ^qu 1 ^pu 1: The histogram is not the best nonparametric density estimate [68]=-=, but it-=- suffices for our purposes. Other discrete density estimates can be also employed. We will denote by ^ðyÞ ^pðyÞ; ^qŠ ð1Þ a similarity function between ^p and ^q. The function ^ðyÞ plays the r... |

405 | Human motion analysis: A review
- Aggarwal, Cai
- 1997
(Show Context)
Citation Context ...[26] presented an affine tracker based on planar regions and anchor points. Tracking people, which rises many challenges due to the presence of large 3D, non-rigid motion, was extensively analyzed in =-=[36, 1, 30, 73]-=-. Explicit tracking approaches of people [69] are time-consuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the paper is to intro... |

352 | Color-based probabilistic tracking
- Pérez, Hue, et al.
(Show Context)
Citation Context ... texture analysis. The benefits of guiding random particles by gradient optimization are discussed in [70] and a particle filter for color histogram tracking based on the metric (6) is implemented in =-=[57]-=-. Finally, we would like to add a word of caution. The tracking solution presented in this paper has several desirable properties: it is efficient, modular, has straightforwardsCOMANICIU ET AL.: KERNE... |

342 | Robust online appearance models for visual tracking
- Jepson, Fleet, et al.
(Show Context)
Citation Context ...ed by Sclaroff and Isidoro [67] using robust M-estimators. Learning of appearance models by employing a mixture of stable image structure, motion information, and an outlier process, was discussed in =-=[41]-=-. In a different approach, Ferrari et al. [26] presented an affine tracker based on planar regions and anchor points. Tracking people, which raises many challenges due to the presence of large 3D, non... |

327 | Elliptical head tracking using intensity gradients and color histograms
- Birchfield
- 1998
(Show Context)
Citation Context ...f iterations is 4:19 per frame. region inside the rectangle. The surface is asymmetric due to neighboring colors that are similar to the target. While most of the tracking approaches based on regions =-=[7]-=-, [27], [50] must perform an exhaustive search in the rectangle to find the maximum, our algorithm converged in four iterations as shown in Fig. 3. Note that the operational basin of attraction of the... |

280 | Moving target classification and tracking from realtime video
- Lipton, Fujiyoshi, et al.
- 1988
(Show Context)
Citation Context ...edges, or any combination of them. In the sequel, it is assumed that the following information is available: 1) detection and localization in the initial frame of the objects to track (target models) =-=[50]-=-, [8] and 2) periodic analysis of each object to account for possible updates of the target models due to significant changes in color [53]. 4.1 Distance Minimization Minimizing the distance (6) is eq... |

275 |
The divergence and Bhattacharyya distance measures in signal selection
- Kailath
- 1967
(Show Context)
Citation Context ...ffiffi p 1 ^pðyÞ; ^qŠ; ð6Þ where we chose ^ðyÞ ^pðyÞ; ^qŠ Xm pffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi ^puðyÞ^qu ; ð7Þ u1 the sample estimate of the Bhattacharyya coefficient betwee=-=n p and q [43]-=-. The Bhattacharyya coefficient is a divergence-type measure [49] which has a straightforward geometric interpretawhere is the Kronecker delta function. The normalization constant C is derived by impo... |

258 | A probabilistic exclusion principle for tracking multiple objects
- MacCormick, Blake
- 1999
(Show Context)
Citation Context ...from 2D image motion. Particle filtering was first introduced, in vision, as the Condensation algorithm by Isard and Blake [40]. Probabilistic exclusion for tracking multiple objects was discussed in =-=[51]-=-. Wu and Huang developed an algorithm to integrate multiple target clues [76]. Li and Chellappa [48] proposed simultaneous tracking and verification based on particle filters applied to vehicles and f... |

241 | Support vector tracking
- Avidan
- 2004
(Show Context)
Citation Context ...ications such as surveillance [44], [16], [32], perceptual user interfaces [10], augmented reality [26], smart rooms [39], [75], [47], object-based video compression [11], and driver assistance [34], =-=[4]-=-. Two major components can be distinguished in a typical visual tracker. Target Representation and Localization is mostly a bottom-up process which has also to cope with the changes in the appearance ... |

240 | Empirical evaluation of dissimilarity measures for color and texture
- Rubner, Puzicha, et al.
- 2001
(Show Context)
Citation Context ...ces an interpolation process between the locations on the image lattice. The employed target representations do not restrict the way similarity is measured and various functions can be used for . See =-=[59]-=- for an experimental evaluation of different histogram similarity measures. 3 METRIC BASED oN BHATTACHARYYA COEFFICIENT The similarity function defines a distance among target model and candidates. To... |

231 | Multi-camera multi-person tracking for easyliving
- Krumm, Harris, et al.
- 2000
(Show Context)
Citation Context ...-TIME object tracking is the critical task in many computer vision applications such as surveillance [44], [16], [32], perceptual user interfaces [10], augmented reality [26], smart rooms [39], [75], =-=[47]-=-, object-based video compression [11], and driver assistance [34], [4]. Two major components can be distinguished in a typical visual tracker. Target Representation and Localization is mostly a bottom... |

213 |
An efficient implementation of Reid’s multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking
- Cox, Hingorani
- 1996
(Show Context)
Citation Context ...2], on the other hand, calculates the measurement-to-target association probabilities jointly across all the targets. A different strategy is represented by the Multiple Hypothesis Filter (MHF) [63], =-=[20]-=-, [5, p. 106] which evaluates the probability that a given target gave rise to a certain measurement sequence. The MHF formulation can be adapted to track the modes of the state density [13]. The data... |

212 | Algorithms for cooperative multisensor surveillance
- Collins, Lipton, et al.
- 2001
(Show Context)
Citation Context ...lly-smooth similarity function, Bhattacharyya coefficient, face tracking. 1 INTRODUCTION REAL-TIME object tracking is the critical task in many computer vision applications such as surveillance [44], =-=[16]-=-, [32], perceptual user interfaces [10], augmented reality [26], smart rooms [39], [75], [47], object-based video compression [11], and driver assistance [34], [4]. Two major components can be disting... |

210 |
Non-Gaussian state-space modeling of nonstationary time series
- Kitagawa
- 1987
(Show Context)
Citation Context ... space is discrete and consists of a finite number of states, Hidden Markov Models (HMM) filters [60] can be applied for tracking. The most general class of filters is represented by particle filters =-=[45]-=-, also called bootstrap filters [31], which are based on Monte Carlo integration methods. The current density of the state is represented by a set of random samples with associated weights and the new... |

208 | A multiple hypothesis approach to figure tracking
- Cham, Rehg
- 1999
(Show Context)
Citation Context ...HF) [63], [20], [5, p. 106] which evaluates the probability that a given target gave rise to a certain measurement sequence. The MHF formulation can be adapted to track the modes of the state density =-=[13]-=-. The data association problem for multiple target particle filtering is presented in [62], [38]. The filtering and association techniques discussed above were applied in computer vision for various t... |

188 | W4: Who? when? where? what? a real time system for detecting and tracking people
- Haritaoglu, Harwood, et al.
- 1998
(Show Context)
Citation Context ...[26] presented an affine tracker based on planar regions and anchor points. Tracking people, which rises many challenges due to the presence of large 3D, non-rigid motion, was extensively analyzed in =-=[36, 1, 30, 73]-=-. Explicit tracking approaches of people [69] are time-consuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the paper is to intro... |

166 | View-invariant representation and recognition of actions
- Rao, Yilmaz, et al.
(Show Context)
Citation Context ...(FLIR) imagery. Xu and Fujimura [77] used night vision for pedestrian detection and tracking, where the detection is performed by a support vector machine and the tracking is kernel-based. Rao et al. =-=[61]-=- employed kernel tracking in their system for action recognition, while Caenen et al. [12] followed the same principle for texture analysis. The benefits of guiding random particles by gradient optimi... |

152 | Covariance scaled sampling for monocular 3D body tracking
- Sminchisescu, Triggs
- 2001
(Show Context)
Citation Context ...nchor points. Tracking people, which raises many challenges due to the presence of large 3D, nonrigid motion, was extensively analyzed in [36], [1], [30], [73]. Explicit tracking approaches of people =-=[69]-=- are timeconsuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the paper is to introduce a new framework for efficient tracking of... |

151 | Probabilistic data association methods for tracking complex visual objects
- Rasmussen, Hager
- 2001
(Show Context)
Citation Context ...to a certain measurement sequence. The MHF formulation can be adapted to track the modes of the state density [13]. The data association problem for multiple target particle filtering is presented in =-=[62]-=-, [38]. The filtering and association techniques discussed above were applied in computer vision for various tracking scenarios. Boykov and Huttenlocher [9] employed the Kalman filter to track vehicle... |

137 |
Bayesian multi-camera surveillance
- Kettnaker, Zabih
- 1999
(Show Context)
Citation Context ...spatially-smooth similarity function, Bhattacharyya coefficient, face tracking. 1 INTRODUCTION REAL-TIME object tracking is the critical task in many computer vision applications such as surveillance =-=[44]-=-, [16], [32], perceptual user interfaces [10], augmented reality [26], smart rooms [39], [75], [47], object-based video compression [11], and driver assistance [34], [4]. Two major components can be d... |

134 | Optical flow constraints on deformable models with applications to face tracking
- Decarlo, Metaxas
- 2000
(Show Context)
Citation Context ...ication dependent and plays a decisive role in the robustness and efficiency of the tracker. For example, face tracking in a crowded scene relies more on target representation than on target dynamics =-=[21]-=-, while in aerial video surveillance, e.g., [74], the target motion and the ego-motion of the camera are the more important components. In real-time applications, only a small percentage of the system... |

130 |
Tracking persons in monocular image sequences. Computer Vision and Image Understanding (CVIU
- Wachter, Nagel
- 1999
(Show Context)
Citation Context ... affine tracker based on planar regions and anchor points. Tracking people, which raises many challenges due to the presence of large 3D, nonrigid motion, was extensively analyzed in [36], [1], [30], =-=[73]-=-. Explicit tracking approaches of people [69] are timeconsuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the paper is to introd... |

118 | Real-time tracking of image regions with changes in geometry and illumination
- Hager, Belhumeur
- 1996
(Show Context)
Citation Context ...erty can be exploited to develop efficient, gradient-based localization schemes using the normalized correlation criterion [6]. Since the correlation is sensitive to illumination, Hager and Belhumeur =-=[33]-=- explicitly modeled the geometry and illumination changes. The method was improved by Sclaroff and Isidoro [67] using robust M-estimators. Learning of appearance models by employing a mixture of stabl... |

101 | Real-time closed-world tracking
- Intille, Davis, et al.
- 1997
(Show Context)
Citation Context ...DUCTION REAL-TIME object tracking is the critical task in many computer vision applications such as surveillance [44], [16], [32], perceptual user interfaces [10], augmented reality [26], smart rooms =-=[39]-=-, [75], [47], object-based video compression [11], and driver assistance [34], [4]. Two major components can be distinguished in a typical visual tracker. Target Representation and Localization is mos... |

99 |
Tracking colour objects using adaptive mixture models
- McKenna, Raja, et al.
- 1999
(Show Context)
Citation Context ... 3D, nonrigid motion, was extensively analyzed in [36], [1], [30], [73]. Explicit tracking approaches of people [69] are timeconsuming and often the simpler blob model [75] or adaptive mixture models =-=[53]-=- are also employed. The main contribution of the paper is to introduce a new framework for efficient tracking of nonrigid objects. We show that by spatially masking the target with an isotropic kernel... |

98 | Active blobs
- Sclaroff, Isidoro
- 1998
(Show Context)
Citation Context ...n criterion [6]. Since the correlation is sensitive to illumination, Hager and Belhumeur [33] explicitly modeled the geometry and illumination changes. The method was improved by Sclaroff and Isidoro =-=[67]-=- using robust M-estimators. Learning of appearance models by employing a mixture of stable image structure, motion information, and an outlier process, was discussed in [41]. In a different approach, ... |

96 | Better proposal distributions: Object tracking using unscented particle filter
- Rui, Chen
- 2001
(Show Context)
Citation Context ...es. Chen et al. [15] used the Hidden Markov Model formulation for tracking combined with JPDAF data association. Rui and Chen proposed to track the face contour based on the unscented particle filter =-=[66]-=-. Cham and Rehg [13] applied a variant of MHF for figure tracking. The emphasis in this paper is on the other component of tracking: target representation and localization. While the filtering and dat... |

93 | Spatial color indexing and applications - Huang, Kumar, et al. - 1998 |

93 |
Pedestrian detection and tracking with night vision
- Xu, Liu, et al.
- 2005
(Show Context)
Citation Context ...ith a kernel tracker for monitoring shopping groups in stores. Yilmaz et al. [78] combined kernel tracking with global motion compensation for forward-looking infrared (FLIR) imagery. Xu and Fujimura =-=[77]-=- used night vision for pedestrian detection and tracking, where the detection is performed by a support vector machine and the tracking is kernel-based. Rao et al. [61] employed kernel tracking in the... |

92 | Color-based tracking of heads and other mobile objects at video frame rates
- Fieguth, Teropoulos
- 1997
(Show Context)
Citation Context ...rations is 4:19 per frame. region inside the rectangle. The surface is asymmetric due to neighboring colors that are similar to the target. While most of the tracking approaches based on regions [7], =-=[27]-=-, [50] must perform an exhaustive search in the rectangle to find the maximum, our algorithm converged in four iterations as shown in Fig. 3. Note that the operational basin of attraction of the mode ... |

87 | Unifying maximum likelihood approaches in medical image registration
- Roche, Malandain, et al.
- 2000
(Show Context)
Citation Context ...on. While the filtering and data association have their roots in control theory, algorithms for target representation and localization are specific to images and related to registration methods [72], =-=[64]-=-, [56]. Both target localization and registration maximizes a likelihood type function. The difference is that in tracking, as opposed to registration, only small changes are assumed in the location a... |

75 |
ªNonrigid Motion Analysis
- Aggarwal, Cai, et al.
- 1998
(Show Context)
Citation Context ...resented an affine tracker based on planar regions and anchor points. Tracking people, which raises many challenges due to the presence of large 3D, nonrigid motion, was extensively analyzed in [36], =-=[1]-=-, [30], [73]. Explicit tracking approaches of people [69] are timeconsuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the paper ... |

75 | The Bhattacharyya metric as an absolute similarity measure for frequency coded data
- Aherne, Thacker, et al.
- 1997
(Show Context)
Citation Context ...2 Þ.sCOMANICIU ET AL.: KERNEL-BASED OBJECT TRACKING 567 5. It approximates the chi-squared statistic, while avoiding the singularity problem of the chi-square test when comparing empty histogram bins=-= [2]-=-. Divergence-based measures were already used in computer vision. The Chernoff and Bhattacharyya bounds have been employed in [46] to determine the effectiveness of edge detectors. The Kullback diverg... |

72 |
Computer Vision Face Tracking as a Component of a Perceptual User Interface
- Bradski
- 1998
(Show Context)
Citation Context ...haryya coefficient, face tracking. 1 INTRODUCTION REAL-TIME object tracking is the critical task in many computer vision applications such as surveillance [44], [16], [32], perceptual user interfaces =-=[10]-=-, augmented reality [26], smart rooms [39], [75], [47], object-based video compression [11], and driver assistance [34], [4]. Two major components can be distinguished in a typical visual tracker. Tar... |

72 | 3d trajectory recovery for tracking multiple objects and trajectory guided recognition of actions
- Rosales, Sclaroff
- 1999
(Show Context)
Citation Context ...discussed above were applied in computer vision for various tracking scenarios. Boykov and Huttenlocher [9] employed the Kalman filter to track vehicles in an adaptive framework. Rosales and Sclaroff =-=[65]-=- used the Extended Kalman Filter to estimate a 3D object trajectory from 2D image motion. Particle filtering was first introduced, in vision, as the Condensation algorithm by Isard and Blake [40]. Pro... |

66 | Probabilisic detection and tracking of motion boundaries
- Black, Fleet
- 2000
(Show Context)
Citation Context ... or any combination of them. In the sequel, it is assumed that the following information is available: 1) detection and localization in the initial frame of the objects to track (target models) [50], =-=[8]-=- and 2) periodic analysis of each object to account for possible updates of the target models due to significant changes in color [53]. 4.1 Distance Minimization Minimizing the distance (6) is equival... |

58 |
Finding Waldo, or focus of attention using local color information
- Ennesser, Medioni
- 1995
(Show Context)
Citation Context ... the number of target pixels nh are in the same range. It is of interest to compare the complexity of the new algorithm with that of target localization without gradient optimization, as discussed in =-=[25]-=-. The search area is assumed to be equal to the operational basin of attraction, i.e., a region covering the target model pixels. The first step is to compute nh histograms. Assume that each histogram... |

58 | Fundamental Bounds on Edge Detection: An Information Theoretic Evaluation of Different Edge Cues
- Konishi, Yuille, et al.
- 1999
(Show Context)
Citation Context ...ity problem of the chi-square test when comparing empty histogram bins [2]. Divergence-based measures were already used in computer vision. The Chernoff and Bhattacharyya bounds have been employed in =-=[46]-=- to determine the effectiveness of edge detectors. The Kullback divergence between joint distribution and product of marginals (e.g., the mutual information) has been used in [72] for registration. In... |

57 |
The unscented particle filter
- Merwe, Doucet, et al.
- 2000
(Show Context)
Citation Context ...se samples and weights (see [23], [3] for reviews). The UKF can be employed to generate proposal distributions for particle filters, in which case the filter is called Unscented Particle Filter (UPF) =-=[54].-=- When the tracking is performed in a cluttered environment where multiple targets can be present [52], problems 0162-8828/03/$10.00 ß 2003 IEEE Published by the IEEE Computer SocietysCOMANICIU ET AL.... |

54 | Region tracking through image sequences
- Bascle, Deriche
- 1995
(Show Context)
Citation Context ...he location and appearance of the target in two consecutive frames. This property can be exploited to develop efficient, gradient-based localization schemes using the normalized correlation criterion =-=[6]-=-. Since the correlation is sensitive to illumination, Hager and Belhumeur [33] explicitly modeled the geometry and illumination changes. The method was improved by Sclaroff and Isidoro [67] using robu... |

45 | Gool, Real-time Affine Region Tracking and Coplanar Grouping
- Ferrari, Tuytelaars, et al.
- 2001
(Show Context)
Citation Context ... tracking. 1 INTRODUCTION REAL-TIME object tracking is the critical task in many computer vision applications such as surveillance [44], [16], [32], perceptual user interfaces [10], augmented reality =-=[26]-=-, smart rooms [39], [75], [47], object-based video compression [11], and driver assistance [34], [4]. Two major components can be distinguished in a typical visual tracker. Target Representation and L... |

43 | Color Indexing," Int'l - Swain, Ballard - 1991 |

38 |
Object Tracking: A
- YILMAZ, JAVED, et al.
(Show Context)
Citation Context ...ed on color and edge density in Fig. 13. Face sequence: The frames 39, 150, 163, 498, 576, and 619 are shown. conjunction with a kernel tracker for monitoring shopping groups in stores. Yilmaz et al. =-=[78]-=- combined kernel tracking with global motion compensation for forward-looking infrared (FLIR) imagery. Xu and Fujimura [77] used night vision for pedestrian detection and tracking, where the detection... |

37 | Aerial video surveillance and exploitation
- Kumar, Sawhney, et al.
(Show Context)
Citation Context ... robustness and efficiency of the tracker. For example, face tracking in 1 a crowded scene relies more on target representation than on target dynamics [21], while in aerial video surveillance, e.g., =-=[74]-=-, the target motion and the ego-motion of the camera are the more important components. In real-time applications only a small percentage of the system resources can be allocated for tracking, the res... |

36 |
Guiding random particles by deterministic search
- Sullivan, Rittscher
- 2001
(Show Context)
Citation Context ...g in their system for action recognition, while Caenen et al. [12] followed the same principle for texture analysis. The benefits of guiding random particles by gradient optimization are discussed in =-=[70]-=- and a particle filter for color histogram tracking based on the metric (6) is implemented in [57]. Finally, we would like to add a word of caution. The tracking solution presented in this paper has s... |

30 | Estimating uncertainty in SSD-based feature tracking
- Nickels, Hutchinson
(Show Context)
Citation Context ...tal and vertical movement. A constant-velocity dynamic model with acceleration affected by white noise [5, p. 82] has been assumed. The uncertainty of the measurements has been estimated according to =-=[55]-=-. The idea is to normalize the similarity surface and represent it as a probability density function. Since the similarity surface is smooth, for each filter only three measurements are taken into acc... |

30 |
Detection and tracking of shopping groups in stores
- Haritaoglu, Flickner
- 2001
(Show Context)
Citation Context ...rimented with the same kernel-weighted histograms, but employed the Kullback-Leibler distance as dissimilarity while performing the optimization based on trust-region methods. Haritaoglu and Flickner =-=[35]-=- used an appearance model based on color and edge density in conjunction with a kernel tracker for monitoring shopping groups in stores. Yilmaz et al. [78] combined kernel tracking with global motion ... |

24 | Trust-region methods for real-time tracking
- Chen, Liu
- 2001
(Show Context)
Citation Context ...[37, p. 262] for a discussion). We mention that since its original publication in [18], the idea of kernel-based tracking has been exploited and developed forward by various researchers. Chen and Liu =-=[14]-=- experimented with the same kernel-weighted histograms, but employed the Kullback-Leibler distance as dissimilarity while performing the optimization based on trust-region methods. Haritaoglu and Flic... |

23 | Adaptive Bayesian recognition in tracking rigid objects
- Boykov, Huttenlocher
(Show Context)
Citation Context ... target particle filtering is presented in [62], [38]. The filtering and association techniques discussed above were applied in computer vision for various tracking scenarios. Boykov and Huttenlocher =-=[9]-=- employed the Kalman filter to track vehicles in an adaptive framework. Rosales and Sclaroff [65] used the Extended Kalman Filter to estimate a 3D object trajectory from 2D image motion. Particle filt... |

21 |
Simultaneous tracking and verification via sequential posterior estimation
- Li, Chellappa
(Show Context)
Citation Context ...thm by Isard and Blake [40]. Probabilistic exclusion for tracking multiple objects was discussed in [51]. Wu and Huang developed an algorithm to integrate multiple target clues [76]. Li and Chellappa =-=[48]-=- proposed simultaneous tracking and verification based on particle filters applied to vehicles and faces. Chen et al. [15] used the Hidden Markov Model formulation for tracking combined with JPDAF dat... |

15 |
Analysis and Engineering of Video Monitoring Systems:An Approach and a Case Study
- Greiffenhagen, Comaniciu, et al.
(Show Context)
Citation Context ...ooth similarity function, Bhattacharyya coefficient, face tracking. 1 INTRODUCTION REAL-TIME object tracking is the critical task in many computer vision applications such as surveillance [44], [16], =-=[32]-=-, perceptual user interfaces [10], augmented reality [26], smart rooms [39], [75], [47], object-based video compression [11], and driver assistance [34], [4]. Two major components can be distinguished... |

15 | Target-tracking in FLIR imagery using mean-shift and global motion compensation
- Yilmaz, Shafique, et al.
- 2001
(Show Context)
Citation Context ...rust-region methods. Haritaoglu and Flickner [35] used an appearance model based on color and edge density in conjunction with a kernel tracker for monitoring shopping groups in stores. Yilmaz et al. =-=[78]-=- combined kernel tracking with global motion compensation for forward-looking infrared (FLIR) imagery. Xu and Fujimura [77] used night vision for pedestrian detection and tracking, where the detection... |

12 | Smart Cameras with RealTime Video Object Generation
- Bue, Comaniciu, et al.
- 2002
(Show Context)
Citation Context ... task in many computer vision applications such as surveillance [44], [16], [32], perceptual user interfaces [10], augmented reality [26], smart rooms [39], [75], [47], object-based video compression =-=[11]-=-, and driver assistance [34], [4]. Two major components can be distinguished in a typical visual tracker. Target Representation and Localization is mostly a bottom-up process which has also to cope wi... |

12 |
The Quality of TrainingSample Estimates of the Bhattacharyya Coefficient
- Djouadi, Snorrason, et al.
- 1990
(Show Context)
Citation Context ....; ^qm Properties of the Bhattacharyya coefficient such as its relation to the Fisher measure of information, quality of the sample estimate, and explicit forms for various distributions are given in =-=[22]-=-, [43]. The statistical measure (6) has several desirable properties: 1. It imposes a metric structure (see Appendix). The Bhattacharyya distance [28, p. 99] or Kullback divergence [19, p. 18] are not... |

12 |
III. "Alignment by maximization of mutual information
- Viola, Wells
- 1995
(Show Context)
Citation Context ...zation. While the filtering and data association have their roots in control theory, algorithms 3 for target representation and localization are specific to images and related to registration methods =-=[72, 64, 56]-=-. Both target localization and registration maximizes a likelihood type function. The difference is that in tracking, as opposed to registration, only small changes are assumed in the location and app... |

11 |
Novel Approach to Nonlinear
- Gordon, Salmond, et al.
- 1993
(Show Context)
Citation Context ... finite number of states, Hidden Markov Models (HMM) filters [60] can be applied for tracking. The most general class of filters is represented by particle filters [45], also called bootstrap filters =-=[31]-=-, which are based on Monte Carlo integration methods. The current density of the state is represented by a set of random samples with associated weights and the new density is computed based on these ... |

9 |
Engineering statistics for multi-object tracking
- Mahler
- 2001
(Show Context)
Citation Context ...ibutions for particle filters, in which case the filter is called Unscented Particle Filter (UPF) [54]. When the tracking is performed in a cluttered environment where multiple targets can be present =-=[52],-=- problems 0162-8828/03/$10.00 ß 2003 IEEE Published by the IEEE Computer SocietysCOMANICIU ET AL.: KERNEL-BASED OBJECT TRACKING 565 related to the validation and association of the measurements arise... |

6 | Analysing the Layout of Composite Textures
- Caenen, Ferrari, et al.
(Show Context)
Citation Context ...ng, where the detection is performed by a support vector machine and the tracking is kernel-based. Rao et al. [61] employed kernel tracking in their system for action recognition, while Caenen et al. =-=[12]-=- followed the same principle for texture analysis. The benefits of guiding random particles by gradient optimization are discussed in [70] and a particle filter for color histogram tracking based on t... |

6 | Seelen, “Computer vision for driver assistance systems
- Handmann, Kalinke, et al.
- 1998
(Show Context)
Citation Context ...n applications such as surveillance [44], [16], [32], perceptual user interfaces [10], augmented reality [26], smart rooms [39], [75], [47], object-based video compression [11], and driver assistance =-=[34]-=-, [4]. Two major components can be distinguished in a typical visual tracker. Target Representation and Localization is mostly a bottom-up process which has also to cope with the changes in the appear... |

6 |
Detection and Tracking of Shopping Groups
- Haritaoglu, Flickner
- 2001
(Show Context)
Citation Context ...rimented with the same kernel-weighted histograms, but employed the Kullback-Leibler distance as dissimilarity while performing the optimization based on trust-region methods. Haritaoglu and Flickner =-=[35]-=- used an appearance model based on color and edge density in Fig. 13. Face sequence: The frames 39, 150, 163, 498, 576, and 619 are shown. conjunction with a kernel tracker for monitoring shopping gro... |

6 |
Image Registration by Aligning Entropies
- Olson
- 2001
(Show Context)
Citation Context ...ile the filtering and data association have their roots in control theory, algorithms for target representation and localization are specific to images and related to registration methods [72], [64], =-=[56]-=-. Both target localization and registration maximizes a likelihood type function. The difference is that in tracking, as opposed to registration, only small changes are assumed in the location and app... |

5 |
JPDAF-Based HMM for RealTime Contour Tracking
- Chen, Rui, et al.
- 2001
(Show Context)
Citation Context ...eloped an algorithm to integrate multiple target clues [76]. Li and Chellappa [48] proposed simultaneous tracking and verification based on particle filters applied to vehicles and faces. Chen et al. =-=[15]-=- used the Hidden Markov Model formulation for tracking combined with JPDAF data association. Rui and Chen proposed to track the face contour based on the unscented particle filter [66]. Cham and Rehg ... |

4 |
Information Theoretic Measure for Visual Target Distinctness
- Garcia, Fdez-Valdivia, et al.
- 2001
(Show Context)
Citation Context ...nce between joint distribution and product of marginals (e.g., the mutual information) has been used in [72] for registration. Information theoretic measures for target distinctness were discussed in =-=[29]. -=-computed with kernel profile kðxÞ at y in the current frame, with the data being weighted by wi (10). The mode of this density in the local neighborhood is the sought maximum that can be found emplo... |

3 |
A Co-Inference Approach to Robust Tracking
- Wu, Huang
- 2001
(Show Context)
Citation Context ...the Condensation algorithm by Isard and Blake [40]. Probabilistic exclusion for tracking multiple objects was discussed in [51]. Wu and Huang developed an algorithm to integrate multiple target clues =-=[76]-=-. Li and Chellappa [48] proposed simultaneous tracking and verification based on particle filters applied to vehicles and faces. Chen et al. [15] used the Hidden Markov Model formulation for tracking ... |

2 |
W4: Who? When? Where? What?—A Real Time System for Detecting and Tracking
- Haritaoglu, Harwood, et al.
- 1998
(Show Context)
Citation Context ...[26] presented an affine tracker based on planar regions and anchor points. Tracking people, which raises many challenges due to the presence of large 3D, nonrigid motion, was extensively analyzed in =-=[36]-=-, [1], [30], [73]. Explicit tracking approaches of people [69] are timeconsuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the p... |

2 |
Seelen, "Computer vision for driver assistance systems
- Handmann, Kalinke, et al.
- 1998
(Show Context)
Citation Context ...er vision applications such as surveillance [44, 16, 32], perceptual user interfaces [10], augmented reality [26], smart rooms [39, 75, 47], object-based video compression [11], and driver assistance =-=[34, 4]-=-. Two major components can be distinguished in a typical visual tracker. Target Representation and Localization is mostly a bottom-up process which has also to cope with the changes in the appearance ... |

1 |
Sequential Monte Carlo Filtering for Multiple Target Tracking and Data Fusion
- Hue, Cadre, et al.
- 2002
(Show Context)
Citation Context ...ertain measurement sequence. The MHF formulation can be adapted to track the modes of the state density [13]. The data association problem for multiple target particle filtering is presented in [62], =-=[38]-=-. The filtering and association techniques discussed above were applied in computer vision for various tracking scenarios. Boykov and Huttenlocher [9] employed the Kalman filter to track vehicles in a... |