Histogram of Oriented Displacements (HOD): Describing Trajectories of Human Joints for Action Recognition
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.
Cite
Text
Gowayyed et al. "Histogram of Oriented Displacements (HOD): Describing Trajectories of Human Joints for Action Recognition." International Joint Conference on Artificial Intelligence, 2013.Markdown
[Gowayyed et al. "Histogram of Oriented Displacements (HOD): Describing Trajectories of Human Joints for Action Recognition." International Joint Conference on Artificial Intelligence, 2013.](https://mlanthology.org/ijcai/2013/gowayyed2013ijcai-histogram/)BibTeX
@inproceedings{gowayyed2013ijcai-histogram,
title = {{Histogram of Oriented Displacements (HOD): Describing Trajectories of Human Joints for Action Recognition}},
author = {Gowayyed, Mohammad Abdelaziz and Torki, Marwan and Hussein, Mohamed Elsayed and El-Saban, Motaz},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2013},
pages = {1351-1357},
url = {https://mlanthology.org/ijcai/2013/gowayyed2013ijcai-histogram/}
}