List of Titles

On temporal order invariance for view-invariant action recognition

- Ul-Haq, Anwaar, Gondal, Iqbal, Murshed, Manzur

Authors: Ul-Haq, Anwaar , Gondal, Iqbal , Murshed, Manzur
Date: 2013
Type: Text , Journal article
Relation: IEEE Transactions on Circuits and Systems for Video Technology Vol. 23, no. 2 (2013), p. 203-211
Full Text: false
Reviewed:
Description: View-invariant action recognition is one of the most challenging problems in computer vision. Various representations are being devised for matching actions across different viewpoints to achieve view invariance. In this paper, we explore the invariance property of temporal order of action instances during action execution and utilize it for devising a new view-invariant action recognition approach. To ensure temporal order during matching, we utilize spatiotemporal features, feature fusion and temporal order consistency constraint. We start by extracting spatiotemporal cuboid features from video sequences and applying feature fusion to encapsulate within-class similarity for the same viewpoints. For each action class, we construct a feature fusion table to facilitate feature matching across different views. An action matching score is then calculated based on global temporal order constraint and number of matching features. Finally, the action label of the class with the maximum value of the matching score is assigned to the query action. Experimentation is performed on multiple view Inria Xmas motion acquisition sequences and West Virginia University action datasets, with encouraging results, that are comparable to the existing view-invariant action recognition techniques.

On dynamic scene geometry for view-invariant action matching

- Ul-Haq, Anwaar, Gondal, Iqbal, Murshed, Manzur

Authors: Ul-Haq, Anwaar , Gondal, Iqbal , Murshed, Manzur
Date: 2011
Type: Text , Conference paper
Relation: 24th IEEE Conference on Computer Vision and Pattern Recognition (CVPR) p. 3305-3312
Full Text: false
Reviewed:
Description: Variation in viewpoints poses significant challenges to action recognition. One popular way of encoding view-invariant action representation is based on the exploitation of epipolar geometry between different views of the same action. Majority of representative work considers detection of landmark points and their tracking by assuming that motion trajectories for all landmark points on human body are available throughout the course of an action. Unfortunately, due to occlusion and noise, detection and tracking of these landmarks is not always robust. To facilitate it, some of the work assumes that such trajectories are manually marked which is a clear drawback and lacks automation introduced by computer vision. In this paper, we address this problem by proposing view invariant action matching score based on epipolar geometry between actor silhouettes, without tracking and explicit point correspondences. In addition, we explore multi-body epipolar constraint which facilitates to work on original action volumes without any pre-processing. We show that multi-body fundamental matrix captures the geometry of dynamic action scenes and helps devising an action matching score across different views without any prior segmentation of actors. Extensive experimentation on challenging view invariant action datasets shows that our approach not only removes long standing assumptions but also achieves significant improvement in recognition accuracy and retrieval.

An enhancement to closed-form method for natural image matting

- Zhu, Jun, Zhang, Dengsheng, Lu, Guojun

Authors: Zhu, Jun , Zhang, Dengsheng , Lu, Guojun
Date: 2010
Type: Text , Conference paper
Relation: Proceedings of the 2010 Digital Image Computing: Techniques and Applications p. 629-634
Full Text: false
Reviewed:
Description: Natural image matting is a task to estimate fractional opacity of foreground layer from an image. Many matting methods have been proposed, and most of them are trimap-based. Among these methods, closed-form matting offers both trimap-based and scribble-based matting. However, the closed-form method causes significant errors at background-hole regions due to over-smoothing. In this paper, we identify the source of the problem and propose our solution to enhance the closed-form method. Experiments show that our enhanced method can improve the accuracy for trimap-based images and obtain similar result to the closed-form method for scribble-based matting.

Pattern based object segmentation using split and merge

- Karim, Ziaul, Paiker, Nafize, Ali, M. Ameer, Sorwar, Golam, Islam, M. M.

Authors: Karim, Ziaul , Paiker, Nafize , Ali, M. Ameer , Sorwar, Golam , Islam, M. M.
Date: 2009
Type: Text , Conference proceedings
Relation: 2009 IEEE International Conference on Fuzzy Systems; Jeju Island; South Korea; 20th- 24th August 2009 p. 2166-2169
Full Text: false
Reviewed:
Description: Split and Merge (SM) algorithm is a well recognized algorithm for segmenting homogeneous regions in an image. Though SM algorithm is simple and easy, this algorithm is unable to segment all type objects in an image successfully due to huge variations among the objects in size, shape, color and intensity. Moreover, the SM algorithm is also highly dependent on threshold values used for split and merge stages. Addressing these issues, a new algorithm namely pattern based object segmentation using split and merge (PSM) considering the basic SM algorithm, the region stability, and the patterns for object extraction. The experimental results prove the superior segmentation performance of the PSM algorithm in comparison with the basic SM algorithm, suppressed fuzzy c-means (SFCM), and object based image segmentation using fuzzy clustering (FISG). ©2009 IEEE.
Description: IEEE International Conference on Fuzzy Systems

Showing items 1 - 4 of 4