Human Action Recognition Using Deep Multilevel Multimodal (M2) Fusion of Depth and Inertial Sensors

TL;DR

This paper introduces three innovative deep multilevel multimodal fusion frameworks for human action recognition, combining depth and inertial sensor data at various stages to improve classification accuracy using CNNs and SVMs.

Contribution

It proposes novel multilevel fusion strategies at different stages, transforming raw sensor data into images, and leveraging CNNs for rich feature extraction before classification.

Findings

Proposed frameworks outperform existing methods on multiple datasets.

Multilevel fusion captures complementary features more effectively.

Fusion at various stages enhances classification accuracy.

Abstract

Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level), missing the opportunity to fuse rich mid-level features necessary for better classification. To address this shortcoming, in this paper, we propose three novel deep multilevel multimodal fusion frameworks to capitalize on different fusion strategies at various stages and to leverage the superiority of multilevel fusion. At input, we transform the depth data into depth images called sequential front view images (SFIs) and inertial sensor data into signal images. Each input modality, depth and inertial, is further made multimodal by taking convolution with the Prewitt filter. Creating "modality within modality" enables further complementary and discriminative feature extraction through Convolutional Neural Networks (CNNs). CNNs are trained on input images of each modality to learn low-level, high-level and complex features. Learned features are extracted and fused at different stages of the proposed frameworks to combine discriminative and complementary information. These highly informative features are served as input to a multi-class Support Vector Machine (SVM). We evaluate the proposed frameworks on three publicly available multimodal HAR datasets, namely, UTD Multimodal Human Action Dataset (MHAD), Berkeley MHAD, and UTD-MHAD Kinect V2. Experimental results show the supremacy of the proposed fusion frameworks over existing methods.