Results 1 - 10 of 4,587

Kernel-Based Object Tracking

by Dorin Comaniciu, Visvanathan Ramesh, Peter Meer , 2003
"... A new approach toward target representation and localization, the central component in visual tracking of non-rigid objects, is proposed. The feature histogram based target representations are regularized by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity fu ..."
Abstract - Cited by 900 (4 self) - Add to MetaCart
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

Real-Time Tracking of Non-Rigid Objects using Mean Shift

by Dorin Comaniciu, Visvanathan Ramesh, Peter Meer - IEEE CVPR 2000 , 2000
"... A new method for real-time tracking of non-rigid objects seen from a moving camera isproposed. The central computational module is based on the mean shift iterations and nds the most probable target position in the current frame. The dissimilarity between the target model (its color distribution) an ..."
Abstract - Cited by 815 (19 self) - Add to MetaCart
A new method for real-time tracking of non-rigid objects seen from a moving camera isproposed. The central computational module is based on the mean shift iterations and nds the most probable target position in the current frame. The dissimilarity between the target model (its color distribution

Mean-shift Blob Tracking through Scale Space

by Robert Collins Carnegie , 2003
"... The mean-shift algorithm is an efficient technique for tracking 2D blobs through an image. Although the scale of the mean-shift kernel is a crucial parameter, there is presently no clean mechanism for choosing or updating scale while tracking blobs that are changing in size. We adapt Lindeberg &apos ..."
Abstract - Add to MetaCart
's theory of feature scale selection based on local maxima of differential scale-space filters to the problem of selecting kernel scale for mean-shift blob tracking. We show that a difference of Gaussian (DOG) mean-shift kernel enables efficient tracking of blobs through scale space. Using

Mean shift blob tracking through scale space

by Robert T. Collins - in Proc. CVPR
"... The mean-shift algorithm is an efficient technique for track-ing 2D blobs through an image. Although the scale of the mean-shift kernel is a crucial parameter, there is presently no clean mechanism for choosing this scale or updating it while tracking blobs that are changing in size. In this pa-per, ..."
Abstract - Cited by 207 (3 self) - Add to MetaCart
-per, we adapt Lindeberg’s theory of feature scale selection based on local maxima of differential scale-space filters to the problem of selecting kernel scale for mean-shift blob tracking. We show that a difference of Gaussian (DOG) mean-shift kernel enables efficient tracking of blobs through scale space

Continuously Adaptive Mean-Shift (CamShift)

by Clark Van Dam, Gagan Mirch , 2013
"... Computer Vision and Image Processing. Abstract — The Continuously Adaptive Mean-Shift (CamShift) algorithm, incorporating scene depth information is combined with the l1-minimization sparse representation based method to form a hybrid kernel and state space-based tracking algorithm. We take advantag ..."
Abstract - Add to MetaCart
Computer Vision and Image Processing. Abstract — The Continuously Adaptive Mean-Shift (CamShift) algorithm, incorporating scene depth information is combined with the l1-minimization sparse representation based method to form a hybrid kernel and state space-based tracking algorithm. We take

Target Tracking Based on Mean-shift and Kalman Filter

by Songtao Jiang
"... Keywords:target tracking; the mean deviation; Kalman filter; Kernel function histogram. Abstract. Analysis of the scheme- shift is difficult to effectively track the main defect of gray level moving targets un-der complicated background, puts forward the combination of Mean shift and kalman filter m ..."
Abstract - Add to MetaCart
Keywords:target tracking; the mean deviation; Kalman filter; Kernel function histogram. Abstract. Analysis of the scheme- shift is difficult to effectively track the main defect of gray level moving targets un-der complicated background, puts forward the combination of Mean shift and kalman filter

Computer Vision Face Tracking For Use in a Perceptual User Interface

by Gary R. Bradski , 1998
"... As a first step towards a perceptual user interface, a computer vision color tracking algorithm is developed and applied towards tracking human faces. Computer vision algorithms that are intended to form part of a perceptual user interface must be fast and efficient. They must be able to track in re ..."
Abstract - Cited by 357 (4 self) - Add to MetaCart
the Continuously Adaptive Mean Shift (CAMSHIFT) algorithm. CAMSHIFT’s tracking accuracy is compared against a Polhemus tracker. Tolerance to noise, distractors and performance is studied. CAMSHIFT is then used as a computer interface for controlling commercial computer games and for exploring immersive 3D graphic

On-line selection of discriminative tracking features

by Robert T. Collins, Yanxi Liu, Marius Leordeanu , 2003
"... This paper presents an on-line 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 track-ing the ..."
Abstract - Cited by 356 (5 self) - Add to MetaCart
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 adap-tively selects the top-ranked discriminative features for tracking. Examples are presented that demonstrate how this method adapts

W.: Mean-shift blob tracking with adaptive feature selection and scale adaptation

by Dawei Liang, Qingming Huang, Shuqiang Jiang, Hongxun Yao, Wen Gao - In: International Conference Image Processing (2007
"... When the appearances of the tracked object and surrounding background change during tracking, fixed feature space tends to cause tracking failure. To address this problem, we propose a method to embed adaptive feature selection into mean shift tracking framework. From a feature set, the most discrim ..."
Abstract - Cited by 5 (1 self) - Add to MetaCart
When the appearances of the tracked object and surrounding background change during tracking, fixed feature space tends to cause tracking failure. To address this problem, we propose a method to embed adaptive feature selection into mean shift tracking framework. From a feature set, the most

Efficient mean-shift tracking via a new similarity measure

by Changjiang Yang, Ramani Duraiswami, Larry Davis - in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR ’05 , 2005
"... The mean shift algorithm has achieved considerable success in object tracking due to its simplicity and robustness. It finds local minima of a similarity measure between the color histograms or kernel density estimates of the model and target image. The most typically used similarity measures are th ..."
Abstract - Cited by 52 (4 self) - Add to MetaCart
The mean shift algorithm has achieved considerable success in object tracking due to its simplicity and robustness. It finds local minima of a similarity measure between the color histograms or kernel density estimates of the model and target image. The most typically used similarity measures
Results 1 - 10 of 4,587