Human Activity Recognition in Images using SVMs and Geodesics on Smooth Manifolds
Article No.: 20, Pages 1 - 6
Abstract
This paper addresses the problem of human activity recognition in still images. We propose a novel method that focuses on human-object interaction for feature representation of activities on Riemannian manifolds, and exploits underlying Riemannian geometry for classification. The main contributions of the paper include: (a) represent human activity by appearance features from local patches centered at hands containing interacting objects, and by structural features formed from the detected human skeleton containing the head, torso axis and hands; (b) formulate SVM kernel function based on geodesics on Riemannian manifolds under the log-Euclidean metric; (c) apply multi-class SVM classifier on the manifold under the one-against-all strategy. Experiments were conducted on a dataset containing 17196 images in 12 classes of activities from 4 subjects. Test results, evaluations, and comparisons with state-of-the-art methods provide support to the effectiveness of the proposed scheme.
References
[1]
H. Aghajan, J.C. Augusto, R.L.C. Delgado, "Human-Centric Interfaces for Ambient Intelligence," Elsevier, 1st Edition, 2009.
[2]
K. Guo, P. Ishwar, J. Konrad, "Action recognition using sparse representation on covariance manifolds of optical flow," in Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 188--195, Boston, MA, USA, Aug. 29 - Sept. 1, 2010.
[3]
M.F. Abdelkader et al., "Silhouette-based gesture and action recognition via modeling trajectories on Riemannian shape manifolds," Computer Vision and Image Understanding (CVIU), vol. 115, no. 3, pp. 439--455, 2011.
[4]
Y. Wang et al., "Unsupervised discovery of action classes," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 1654--1661, New York, NY, USA, June 17--22, 2006.
[5]
N. Ikizler et al., "Recognizing actions from still images," in Proceedings of IAPR International Conference on Pattern Recognition (ICPR), pp. 1--4, Tampa, FL, USA, Dec. 8 -- 11, 2008.
[6]
B. Yao, F. Li, "Grouplet: A structured image representation for recognizing human and object interactions," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9--16, San Francisco, CA, USA, June 13 -- 18, 2010.
[7]
Y. Yun, I.Y.H. Gu, H. Aghajan, "Riemannian manifold-based support vector machine for human activity classification in images," in Proceedings of IEEE International Conference on Image Processing (ICIP), pp. 3466--3469, Melbourne, VIC, Australia, Sept. 15 -- 18, 2013.
[8]
J.M. Lee, "Introduction to Smooth Manifolds," Springer, 2006.
[9]
O. Tuzel, F. Porikli, P. Meer, "Region covariance: a fast descriptor for detection and classification," in Proceedings of European Conference on Computer Vision (ECCV), vol. 2, pp. 589--600, Graz, Austria, May 7 -- 13, 2006.
[10]
C. Cortes, V.N. Vapnik, "Support-vector networks," Machine Learning, vol. 20, no. 3, pp. 273--297, 1995.
[11]
X. Pennec, P. Fillard, N. Ayache, "A Riemannian framework for tensor computing," International Journal of Computer Vision (IJCV), vol. 66, no. 1, pp. 41--66, 2006.
[12]
V. Arsigny et al., "Geometric means in a novel vector space structure on symmetric-positive definite matrices," SIAM Journal on Matrix Analysis and Applications, vol. 66, no. 1, pp. 328--347, 2008.
[13]
R. Subbarao, P. Meer, "Nonlinear mean shift over Riemannian manifolds," International Journal on Computer Vision (IJCV), vol. 84, pp. 1--20, 2009.
[14]
O. Tuzel, F. Porikli, P. Meer, "Pedestrian detection via classification on Riemannian manifolds," IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 30, no. 10, pp. 1713--1727, 2008.
[15]
C.W. Hsu, C.J. Lin, "A comparison of methods for multi-class support vector machines," IEEE Transactions on Neural Networks, vol. 13, no. 2, pp. 415--425, 2002.
[16]
M.A. Livingston et al. "Performance measurements for the Microsoft Kinect skeleton," in Proceedings of IEEE Virtual Reality Workshop (VRW), pp. 119--120, Costa Mesa, CA, USA, March 4 -- 8, 2012.
[17]
H. Karcher, "Riemannian center of mass and mollifier smoothing," Communications on Pure and Applied Mathematics, vol. 30, no. 5, pp. 509--541, 1977.
[18]
Cornell Activity Datasets: CAD-60 {Online}. Available: http://pr.cs.cornell.edu/humanactivities/data.php
[19]
J. Sung et al., "Unstructured human activity detection from RGBD images," in Proceedings of International Conference on Robotics and Automation (ICRA), pp. 842--849, Saint Paul, MN, USA, May 14 -- 18, 2012.
[20]
H. Koppula, R. Gupta, A. Saxena, "Learning human activities and object affordances from RGB-D videos," International Journal of Robotics Research (IJRR), vol. 32, no. 8, pp. 951--970, 2013.
[21]
C. Zhang, Y. Tian, "RGB-D camera-based daily living activity recognition," Journal of Computer Vision and Image Processing (JCVIP), vol. 2, no. 4, 2012.
[22]
B. Ni, P. Moulin, S. Yan, "Order-preserving sparse coding for sequence classification," in Proceedings of European Conference on Computer Vision (ECCV), vol. 2, pp. 173--187, Florence, Italy, Oct. 7 -- 13, 2012.
[23]
X. Yang, Y. Tian, "Effective 3D action recognition using EigenJoints," Journal of Visual Communication and Image Representation (JVCIR), vol. 25, no. 1, pp. 2--11, 2014.
[24]
L. Piyathilaka, S. Kodagoda, "Gaussian mixture based HMM for human daily activity recognition using 3D skeleton features," in Proceedings of IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 567--572, Melbourne, VIC, Australia, June 19 -- 21, 2013.
[25]
B. Ni et al., "Multilevel depth and image fusion for human activity detection," IEEE Transactions on Cybernetics, vol. 43, no. 5, pp. 1383--1394, 2013.
[26]
R. Gupta, A. Chia, D. Rajan, "Human activities recognition using depth images," in Proceedings of ACM International Conference on Multimedia, pp. 283--292, 2013.
[27]
J. Wang et al., "Learning actionlet ensemble for 3D human action recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), in press, 2013.
[28]
T.K. Moon, W.C. Stirling, "Mathematical Methods and Algorithms for Signal Processing," Prentice Hall, 1999.
Index Terms
- Human Activity Recognition in Images using SVMs and Geodesics on Smooth Manifolds
Recommendations
Manifold Learning and Recognition of Human Activity Using Body-Area Sensors
ICMLA '11: Proceedings of the 2011 10th International Conference on Machine Learning and Applications and Workshops - Volume 02Manifold learning is an important technique for effective nonlinear dimensionality reduction in machine learning. In this paper, we present a manifold-based framework for human activity recognition using wearable motion sensors. In our framework, we use ...
Random Projections of Smooth Manifolds
We propose a new approach for nonadaptive dimensionality reduction of manifold-modeled data, demonstrating that a small number of random linear projections can preserve key information about a manifold-modeled signal. We center our analysis on the ...
Manifolds: a global setting for geometry and analysis, with or without coordinates
Manifolds are curved spaces that admit local coordinate systems which look like Euclidean space. Much of the classical geometry of Euclidean space extends and generalizes to manifolds. A generalization of Euclidean geometry is Riemannian geometry, where ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
November 2014
286 pages
Copyright © 2014 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 04 November 2014
Check for updates
Author Tags
Qualifiers
- Tutorial
- Research
- Refereed limited
Conference
ICDSC '14
Sponsor:
ICDSC '14: International Conference on Distributed Smart Cameras
November 4 - 7, 2014
Venezia Mestre, Italy
Acceptance Rates
ICDSC '14 Paper Acceptance Rate 49 of 69 submissions, 71%;
Overall Acceptance Rate 92 of 117 submissions, 79%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 117Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in