Hand tracking and gesture gecogniton by anisotropic kernel mean shift

Qi, Sumin; Huang, Xianwu

doi:10.1109/icnnsp.2008.4590417

Cited by 9 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tracker-1 uses the anisotropic mean shift in [21] and Tracker-2 uses combined mean shift and particle filter (MSPF) in [1] for tracking on the same videos. Section 6.1 describes seven case studies with some tracking results included.…”

Section: Resultsmentioning

confidence: 99%

“…Section 4.1 reviews the anisotropic mean shift (MS) in [21]. Section 4.2 briefly describes the basic formulae of particle filter that are used for visual tracking.…”

Section: Related Methods: Brief Reviewmentioning

confidence: 99%

“…It is performed in image coordinates by including the scale and orientation as additional dimensions and simultaneously estimating all unknowns. Sumin and Xianwu [21] proposes simultaneous tracking of position, scale and orientation by using anisotropic mean shift. It uses the bandwidth matrix to compute the scale and orientation.…”

Section: Related Workmentioning

confidence: 99%

“…6 for our tracking scheme is defined as the shape parameters of the bounding box containing a candidate image object, as follows s = y 1 y 2 W θ H T (21) where y = (y 1 , y 2 ) is the center coordinates of bounding box, θ the rotation angle, W and H the width and hight of the box, respectively. Under the Brownian motion model for the state dynamics, the state transition pdf is Gaussian distributed,…”

Section: Particle Filter Tracking With the Embedded Mean Shiftmentioning

confidence: 99%

See 3 more Smart Citations

A Robust Particle Filter-Based Method for Tracking Single Visual Object Through Complex Scenes Using Dynamical Object Shape and Appearance Similarity

Khan

Backhouse

2010

J Sign Process Syst

View full text Add to dashboard Cite

This paper addresses the issue of tracking a single visual object through crowded scenarios, where a target object may be intersected or partially occluded by other objects for a long duration, experience severe deformation and pose changes, and different motion speed in cluttered background. A robust visual object tracking scheme is proposed that exploits the dynamics of object shape and appearance similarity. The method uses a particle filter where a multi-mode anisotropic mean shift is embedded to improve the initial particles. Comparing with the conventional particle filter and mean shift-based tracking (Shan et al. 2004), our method offers the following novelties: We employ a fully tunable rectangular bounding box described by five parameters (2D central location, width, height, and orientation) and full functionaries in the joint tracking scheme; We derive the equations for the multi-mode version of the anisotropic mean shift where the rectangular bounding box is partitioned into concentric areas, allowing better tracking objects with multiple modes. The bounding box parameters are then computed by using eigen-decomposition of mean shift estimates and weighted averaging. This enables a more efficient redistributions of initial particles towards locations associated with large weights, hence an efficient particle filter tracking using a very small number of particles (N = 15 is used). Experiments have been conducted on video containing a range of complex scenarios, where tracking results are further evaluated by using two objective criteria and compared with two existing tracking methods. Our results have shown that the propose method is robust in terms of tracking drift, tightness and accuracy of tracked bounding boxes, especially in scenarios where the target object contains long-term partial occlusions, intersections, severe deformation, pose changes, or cluttered background with similar color distributions.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Section 4.1 reviews the anisotropic mean shift (MS) in [21]. Section 4.2 briefly describes the basic formulae of particle filter that are used for visual tracking.…”

Section: Related Methods: Brief Reviewmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Particle Filter Tracking With the Embedded Mean Shiftmentioning

confidence: 99%

See 2 more Smart Citations

A Robust Particle Filter-Based Method for Tracking Single Visual Object Through Complex Scenes Using Dynamical Object Shape and Appearance Similarity

Khan

Backhouse

2010

J Sign Process Syst

View full text Add to dashboard Cite

show abstract

“…Apart from dynamic point maintenance and the use of separate foreground and background areas, a reinitialization process is applied to tracker-A if the similarity between the tracked area and the reference object area becomes small, indicating a potential tracking drift ( e.g., due to few correspondence points) which could propagate through frames. For tracker-B, an enhanced anisotropic mean shift is achieved by choosing the center between the candidate region of tracker-A and the previous candidate region of mean shift [11], and by allowing a re-initialization process. The basic idea is to guide the MS to a correct target object location especially when confusing track situations occur (e.g.…”

Section: A Hybrid Tracking Scheme-1 Combining Adaptive Appearance Witmentioning

confidence: 99%

Adaptive appearance learning for visual object tracking

Khan

2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper addresses online learning of reference object distribution in the context of two hybrid tracking schemes that combine the mean shift with local point feature correspondences, and the mean shift under the Bayesian framework, respectively. The reference object distribution is built up by a kernel-weighted color histogram. The main contributions of the proposed schemes includes: (a) an adaptive learning strategy that seeks to update the reference object distribution when the changes are caused by the intrinsic object dynamic without partial occlusion/intersection; (b) novel dynamic maintenance of object feature points by exploring both foreground and background sets; (c) integration of adaptive appearance and local point features in joint object appearance similarity and local point features correspondences-based tracker to improve [7]; (d) integration of adaptive appearance in joint appearance similarity and particle filter tracker under the Bayesian framework to improve [10]. Experimental results on a range of videos captured by a dynamic/stationary camera demonstrate the effectiveness of the proposed schemes in terms of robustness to partial occlusions, tracking drifts and tightness and accuracy of tracked bounding box. Comparisons are also made with the two hybrid trackers together with 3 existing trackers.

show abstract

Robust Object Tracking Using Particle Filters and Multi-region Mean Shift

Backhouse

Khan

2009

Advances in Multimedia Information Processing - PCM 2009

View full text Add to dashboard Cite

Hand tracking and gesture gecogniton by anisotropic kernel mean shift

Cited by 9 publications

References 7 publications

A Robust Particle Filter-Based Method for Tracking Single Visual Object Through Complex Scenes Using Dynamical Object Shape and Appearance Similarity

A Robust Particle Filter-Based Method for Tracking Single Visual Object Through Complex Scenes Using Dynamical Object Shape and Appearance Similarity

Adaptive appearance learning for visual object tracking

Robust Object Tracking Using Particle Filters and Multi-region Mean Shift

Contact Info

Product

Resources

About