#### DMCA

## Real-Time Tracking of Non-Rigid Objects using Mean Shift (2000)

### Cached

### Download Links

Venue: | IEEE CVPR 2000 |

Citations: | 805 - 19 self |

### Citations

12164 | Elements of Information Theory - Cover, Thomas - 1991 |

3702 | Statistical Pattern Recognition (Second Edition - Fukunaga - 1990 |

1602 | Color Indexing
- Swain, Ballard
- 1991
(Show Context)
Citation Context ...tistical measure (18) is well suited for the task of target localization since: 1. It is nearly optimal, due to its link to the Bayes error. Note that the widely used histogram intersection technique =-=[26]-=- has no such theoretical foundation. 2. It imposes a metric structure (see Appendix). The Bhattacharyya distance [15, p.99] or Kullback divergence [8, p.18] are not metrics since they violate at least... |

1491 | Condensation: Conditional density propagation for visual tracking
- Isard, Blake
- 1998
(Show Context)
Citation Context ...that the same technique can be employed to derive the measurement vector for optimal prediction schemes such as the (Extended) Kalman filter [1, p.56, 106], or multiple hypothesis tracking approaches =-=[5, 9, 17, 18]-=-. In return, the prediction can determine the priors (defining the presence of the target in a given neighborhood) assumed equal in this paper. This connection is however beyond the scope of this pape... |

1458 | Pfinder: real-time tracking of the human body
- Wren, Azarbayejani, et al.
- 1997
(Show Context)
Citation Context ...of visual features in complex environments is a challenging task for the vision community. Real-time applications such as surveillance and monitoring [10], perceptual user interfaces [4], smart rooms =-=[16, 28]-=-, and video compression [12] all require the ability to track moving objects. The computational complexity of the tracker is critical for most applications, only a small percentage of a system resourc... |

997 | III. Alignment by maximization of mutual information - Viola, Wells - 1995 |

470 | Multivariate Density Estimation
- Scott
- 1996
(Show Context)
Citation Context ...of the Bhattacharyya coefficient from sample data involves the estimation of the densities p and q, for which we employ the histogram formulation. Although not the best nonparametric density estimate =-=[25]-=-, the histogram satisfies the low computational cost imposed by real-time processing. We estimate the discrete densitysq = fq u g u=1:::m (with P m u=1sq u = 1) from the m-bin histogram of the target ... |

342 | Tracking and Data - Bar-Shalom, Fortman - 1988 |

327 | Elliptical head tracking using intensity gradients and color histograms
- Birchfield
- 1998
(Show Context)
Citation Context ...l region in frame 30) has been compared with the target candidates obtained by sweeping the elliptical region in frame 105 inside the rectangle. While most of the tracking approaches based on regions =-=[3, 14, 21]-=- must perform an exhaustive search in the rectangle to find the maximum, our algorithm converged in four iterations as shown in Figure 3. Note that since the basin of attraction of the mode covers the... |

309 | Icondensation: Unifying low-level and high-level tracking in a stochastic framework
- Isard, Blake
- 1998
(Show Context)
Citation Context ...that the same technique can be employed to derive the measurement vector for optimal prediction schemes such as the (Extended) Kalman filter [1, p.56, 106], or multiple hypothesis tracking approaches =-=[5, 9, 17, 18]-=-. In return, the prediction can determine the priors (defining the presence of the target in a given neighborhood) assumed equal in this paper. This connection is however beyond the scope of this pape... |

280 | Moving target classification and tracking from realtime video
- Lipton, Fujiyoshi, et al.
- 1988
(Show Context)
Citation Context ... the same framework. 4 Tracking Algorithm We assume in the sequel the support of two modules which should provide (a) detection and localization in the initial frame of the objects to track (targets) =-=[21, 23]-=-, and (b) periodic analysis of each object to account for possible updates of the target models due to significant changes in color [22]. 4.1 Color Representation Target Model Let fx ? i g i=1:::n be ... |

275 |
The divergence and Bhattacharyya distance measures in signal selection
- Kailath
- 1967
(Show Context)
Citation Context ... be present at any location y in the neighborhood of the previously estimated location. An entity closely related to the Bayes error is the Bhattacharyya coefficient, whose general form is defined by =-=[19]-=- ae(y) j ae [p(y); q] = Z p p z (y)q z dz : (16) Properties of the Bhattacharyya coefficient such as its relation to the Fisher measure of information, quality of the sample estimate, and explicit for... |

213 |
An efficient implementation of Reidâ€™s multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking
- Cox, Hingorani
- 1996
(Show Context)
Citation Context ...that the same technique can be employed to derive the measurement vector for optimal prediction schemes such as the (Extended) Kalman filter [1, p.56, 106], or multiple hypothesis tracking approaches =-=[5, 9, 17, 18]-=-. In return, the prediction can determine the priors (defining the presence of the target in a given neighborhood) assumed equal in this paper. This connection is however beyond the scope of this pape... |

208 | A multiple hypothesis approach to figure tracking
- Cham, Rehg
- 1999
(Show Context)
Citation Context |

197 | Mean shift analysis and applications
- Comaniciu, Meer
- 1999
(Show Context)
Citation Context ...patterns, being robust to partial occlusions, clutter, rotation in depth, and changes in camera position. It is a natural application to motion analysis of the mean shift procedure introduced earlier =-=[6, 7]-=-. The mean shift iterations are employed to find the target candidate that is the most similar to a given target model, with the similarity being expressed by a metric based on the Bhattacharyya coeff... |

101 | Real-time closed-world tracking
- Intille, Davis, et al.
- 1997
(Show Context)
Citation Context ...of visual features in complex environments is a challenging task for the vision community. Real-time applications such as surveillance and monitoring [10], perceptual user interfaces [4], smart rooms =-=[16, 28]-=-, and video compression [12] all require the ability to track moving objects. The computational complexity of the tracker is critical for most applications, only a small percentage of a system resourc... |

99 |
Tracking colour objects using adaptive mixture models
- McKenna, Raja, et al.
- 1999
(Show Context)
Citation Context ...tion in the initial frame of the objects to track (targets) [21, 23], and (b) periodic analysis of each object to account for possible updates of the target models due to significant changes in color =-=[22]-=-. 4.1 Color Representation Target Model Let fx ? i g i=1:::n be the pixel locations of the target model, centered at 0. We define a function b : R 2 ! f1 : : : mg which associates to the pixel at loca... |

92 | Color-based tracking of heads and other mobile objects at video frame rates
- Fieguth, Teropoulos
- 1997
(Show Context)
Citation Context ...l region in frame 30) has been compared with the target candidates obtained by sweeping the elliptical region in frame 105 inside the rectangle. While most of the tracking approaches based on regions =-=[3, 14, 21]-=- must perform an exhaustive search in the rectangle to find the maximum, our algorithm converged in four iterations as shown in Figure 3. Note that since the basin of attraction of the mode covers the... |

72 |
Computer Vision Face Tracking as a Component of a Perceptual User Interface
- Bradski
- 1998
(Show Context)
Citation Context ...ficient tracking of visual features in complex environments is a challenging task for the vision community. Real-time applications such as surveillance and monitoring [10], perceptual user interfaces =-=[4]-=-, smart rooms [16, 28], and video compression [12] all require the ability to track moving objects. The computational complexity of the tracker is critical for most applications, only a small percenta... |

72 | Distribution free decomposition of multivariate data
- Comaniciu, Meer
- 1998
(Show Context)
Citation Context ...patterns, being robust to partial occlusions, clutter, rotation in depth, and changes in camera position. It is a natural application to motion analysis of the mean shift procedure introduced earlier =-=[6, 7]-=-. The mean shift iterations are employed to find the target candidate that is the most similar to a given target model, with the similarity being expressed by a metric based on the Bhattacharyya coeff... |

72 | 3d trajectory recovery for tracking multiple objects and trajectory guided recognition of actions
- Rosales, Sclaroff
- 1999
(Show Context)
Citation Context ... percentage of a system resources being allocated for tracking, while the rest is assigned to preprocessing stages or to high-level tasks such as recognition, trajectory interpretation, and reasoning =-=[24]-=-. This paper presents a new approach to the real-time tracking of non-rigid objects based on visual features such as color and/or texture, whose statistical distributions characterize the object of in... |

70 | Geodesic Active Regions for Motion Estimation and Tracking
- Paragios, Deriche
- 1999
(Show Context)
Citation Context ... the same framework. 4 Tracking Algorithm We assume in the sequel the support of two modules which should provide (a) detection and localization in the initial frame of the objects to track (targets) =-=[21, 23]-=-, and (b) periodic analysis of each object to account for possible updates of the target models due to significant changes in color [22]. 4.1 Color Representation Target Model Let fx ? i g i=1:::n be ... |

58 |
Finding Waldo, or focus of attention using local color information
- Ennesser, Medioni
- 1995
(Show Context)
Citation Context ...action of the mode covers the entire window, the correct location of the target would have been reached also from farther initial points. An optimized computation of the exhaustive search of the mode =-=[13]-=- has a much larger arithmetic complexity, depending on the chosen search area. The new method has been applied to track people on subway platforms. The camera being fixed, additional geometric constra... |

58 | Fundamental Bounds on Edge Detection: An Information Theoretic Evaluation of Different Edge Cues
- Konishi, Yuille, et al.
- 1999
(Show Context)
Citation Context ...esults only for distributions that are separated by the mean-difference [15, p.132]. Similar measures were already used in computer vision. The Chernoff and Bhattacharyya bounds have been employed in =-=[20]-=- to determine the effectiveness of edge detectors. The Kullback divergence has been used in [27] for finding the pose of an object in an image. The next section shows how to minimize (18) as a functio... |

56 | shift analysis and applications - Comaniciu, Meer, et al. - 1999 |

54 | Region tracking through image sequences
- Bascle, Deriche
- 1995
(Show Context)
Citation Context ...odel histogram onto the new frame can introduce a large bias in the estimated location of the target, and the resulting measure is scale variant. Gradient based region tracking has been formulated in =-=[2]-=- by minimizing the energy of the deformable region, but no real-time claims were made. APPENDIX Proof of Theorem 1 Since n is finite the sequencesfK is bounded, therefore, it is sufficient to show tha... |

52 |
Automatic Face Location Detection and Tracking for Model-Assisted Coding of Video Teleconference
- Eleftheriadis, Jacquin
- 1995
(Show Context)
Citation Context ...vironments is a challenging task for the vision community. Real-time applications such as surveillance and monitoring [10], perceptual user interfaces [4], smart rooms [16, 28], and video compression =-=[12]-=- all require the ability to track moving objects. The computational complexity of the tracker is critical for most applications, only a small percentage of a system resources being allocated for track... |

24 | Indoor monitoring via the collaboration between a peripheral sensor and a foveal sensor
- Cui, Samasekera, et al.
- 1998
(Show Context)
Citation Context ... sequences. 1 Introduction The efficient tracking of visual features in complex environments is a challenging task for the vision community. Real-time applications such as surveillance and monitoring =-=[10]-=-, perceptual user interfaces [4], smart rooms [16, 28], and video compression [12] all require the ability to track moving objects. The computational complexity of the tracker is critical for most app... |

12 |
The Quality of TrainingSample Estimates of the Bhattacharyya Coefficient
- Djouadi, Snorrason, et al.
- 1990
(Show Context)
Citation Context ...: (16) 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 =-=[11, 19]-=-. Our interest in expression (16) is, however, motivated by its near optimality given by the relationship to the Bayes error. Indeed, let us denote by ff and fi two sets of parameters for the distribu... |

12 |
III. "Alignment by maximization of mutual information
- Viola, Wells
- 1995
(Show Context)
Citation Context ...sures were already used in computer vision. The Chernoff and Bhattacharyya bounds have been employed in [20] to determine the effectiveness of edge detectors. The Kullback divergence has been used in =-=[27]-=- for finding the pose of an object in an image. The next section shows how to minimize (18) as a function of y in the neighborhood of a given location, by exploiting the mean shift iterations. Only th... |

10 | Moving target classi cation and tracking from real-time video - Lipton, Fujiyoshi, et al. - 1998 |

3 | Elliptical Head Tracking using intensity Gradients and Color Histograms - eld - 1998 |

2 | M Grei enhagen, \Indoor Monitoring Via the Collaboration Between a Peripheral Senson and a Foveal Sensor - Cui, Samarasekera, et al. - 1998 |

2 | The Quality ofTraining-Sample Estimates of the Bhattacharyya Coe cient - Djouadi, Snorrason, et al. - 1990 |