Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences

TL;DR

This paper introduces a multi-scale feature map framework using Laplacian pyramid depth motion images for improved human action recognition from depth videos, outperforming existing methods.

Contribution

It presents a novel multi-scale motion representation (LP-DMI) and a multi-granularity descriptor (LP-DMI-HOG) for enhanced action recognition accuracy.

Findings

Achieved over 93% accuracy on MSRAction3D dataset

Outperformed state-of-the-art benchmarks

Demonstrated effectiveness of multi-scale features in depth video analysis

Abstract

Human action recognition is an active research area in computer vision. Although great process has been made, previous methods mostly recognize actions based on depth data at only one scale, and thus they often neglect multi-scale features that provide additional information action recognition in practical application scenarios. In this paper, we present a novel framework focusing on multi-scale motion information to recognize human actions from depth video sequences. We propose a multi-scale feature map called Laplacian pyramid depth motion images(LP-DMI). We employ depth motion images (DMI) as the templates to generate the multi-scale static representation of actions. Then, we caculate LP-DMI to enhance multi-scale dynamic information of motions and reduces redundant static information in human bodies. We further extract the multi-granularity descriptor called LP-DMI-HOG to provide more discriminative features. Finally, we utilize extreme learning machine (ELM) for action classification. The proposed method yeilds the recognition accuracy of 93.41%, 85.12%, 91.94% on public MSRAction3D dataset, UTD-MHAD and DHA dataset. Through extensive experiments, we prove that our method outperforms state-of-the-art benchmarks.