Histogram of Oriented Depth Gradients for Action Recognition

TL;DR

This paper introduces a computationally efficient method for action recognition in RGBD videos by combining local depth motion measures with appearance descriptors, evaluated on kitchen environment datasets.

Contribution

It proposes a novel approach that integrates depth motion features with RGB descriptors using Fisher vectors and linear SVMs for improved action recognition.

Findings

Depth motion measures enhance recognition accuracy.

The method outperforms previous state-of-the-art techniques.

Efficient computation suitable for real-time applications.

Abstract

In this paper, we report on experiments with the use of local measures for depth motion for visual action recognition from MPEG encoded RGBD video sequences. We show that such measures can be combined with local space-time video descriptors for appearance to provide a computationally efficient method for recognition of actions. Fisher vectors are used for encoding and concatenating a depth descriptor with existing RGB local descriptors. We then employ a linear SVM for recognizing manipulation actions using such vectors. We evaluate the effectiveness of such measures by comparison to the state-of-the-art using two recent datasets for action recognition in kitchen environments.