Human Activity Recognition in Images Using SVMs and Geodesics on Smooth Manifolds
Paper in proceedings, 2014

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.

symmetric positive definite (SPD) matrices

Human activity recognition

Riemannian manifold

support vector machines (SVMs)

covariance descriptor

Author

Yixiao Yun

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Signal Processing

Keren Fu

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Signal Processing

Irene Yu-Hua Gu

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Signal Processing

Hamid Aghajan

Stanford University

Ghent university

Jie Yang

Shanghai Jiao Tong University

8th ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2014; Venezia; Italy; 4 November 2014 through 7 November 2014

Art. no. a20-

Areas of Advance

Information and Communication Technology

Transport

Subject Categories

Geometry

Information Science

Signal Processing

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1145/2659021.2659063

ISBN

978-145032925-5

More information

Latest update

3/7/2018 7