Histogram of oriented displacements (HOD): describing trajectories of human joints for action recognition

Authors:
Mohammad A. Gowayyed;Marwan Torki;Mohamed E. Hussein;Motaz El-Saban
Affiliations:
Department of Computer and Systems Engineering, Alexandria University, Alexandria, Egypt;Department of Computer and Systems Engineering, Alexandria University, Alexandria, Egypt;Department of Computer and Systems Engineering, Alexandria University, Alexandria, Egypt;Microsoft Research Advanced Technology Lab Cairo, Cairo, Egypt
Venue:
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Year:
2013

Citing 5
Cited 0

Discriminative human action recognition in the learned hierarchical manifold space

Image and Vision Computing
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Real-time human pose recognition in parts from single depth images

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Action recognition by dense trajectories

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Mining actionlet ensemble for action recognition with depth cameras

CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Creating descriptors for trajectories has many applications in robotics/human motion analysis and video copy detection. Here, we propose a novel descriptor for 2D trajectories: Histogram of Oriented Displacements (HOD). Each displacement in the trajectory votes with its length in a histogram of orientation angles. 3D trajectories are described by the HOD of their three projections. We use HOD to describe the 3D trajectories of body joints to recognize human actions, which is a challenging machine vision task, with applications in human-robot/machine interaction, interactive entertainment, multimedia information retrieval, and surveillance. The descriptor is fixed-length, scale-invariant and speed-invariant. Experiments on MSR-Action3D and HDM05 datasets show that the descriptor outperforms the state-of-the-art when using off-the-shelf classification tools.