HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition

TL;DR

This paper introduces HOPC, a robust 3D action recognition method using a novel descriptor and keypoint detection that outperforms existing techniques, especially under viewpoint changes.

Contribution

The paper presents a new descriptor and keypoint detection algorithm for 3D pointcloud-based action recognition, improving robustness to viewpoint, noise, and action speed variations.

Findings

Outperforms state-of-the-art algorithms on benchmark datasets.

Demonstrates robustness to viewpoint variations.

Introduces a new multiview human activity dataset.

Abstract

Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint. In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations. Our technique consists of a novel descriptor and keypoint detection algorithm. The proposed descriptor is extracted at a point by encoding the Histogram of Oriented Principal Components (HOPC) within an adaptive spatio-temporal support volume around that point. Based on this descriptor, we present a novel method to detect Spatio-Temporal Key-Points (STKPs) in 3D pointcloud sequences. Experimental results show that the proposed descriptor and STKP detector outperform state-of-the-art algorithms on three benchmark human activity datasets. We also introduce a new multiview public dataset and show the robustness of our proposed method to viewpoint variations.