Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints

TL;DR

This paper introduces TSRJI, a novel skeleton image representation combining reference joints and tree structure to improve 3D action recognition accuracy using CNNs, achieving state-of-the-art results on NTU RGB+D 120.

Contribution

The paper proposes TSRJI, a new skeleton image representation that enhances spatial relation encoding for CNN-based 3D action recognition.

Findings

Achieves state-of-the-art accuracy on NTU RGB+D 120 dataset.

Effectively encodes spatial relations using reference joints and tree structure.

Demonstrates superior performance over existing skeleton image methods.

Abstract

In the last years, the computer vision research community has studied on how to model temporal dynamics in videos to employ 3D human action recognition. To that end, two main baseline approaches have been researched: (i) Recurrent Neural Networks (RNNs) with Long-Short Term Memory (LSTM); and (ii) skeleton image representations used as input to a Convolutional Neural Network (CNN). Although RNN approaches present excellent results, such methods lack the ability to efficiently learn the spatial relations between the skeleton joints. On the other hand, the representations used to feed CNN approaches present the advantage of having the natural ability of learning structural information from 2D arrays (i.e., they learn spatial relations from the skeleton joints). To further improve such representations, we introduce the Tree Structure Reference Joints Image (TSRJI), a novel skeleton image representation to be used as input to CNNs. The proposed representation has the advantage of combining the use of reference joints and a tree structure skeleton. While the former incorporates different spatial relationships between the joints, the latter preserves important spatial relations by traversing a skeleton tree with a depth-first order algorithm. Experimental results demonstrate the effectiveness of the proposed representation for 3D action recognition on two datasets achieving state-of-the-art results on the recent NTU RGB+D~120 dataset.