Continuous Human Action Detection Based on Wearable Inertial Data

TL;DR

This paper explores continuous human action detection using wearable inertial sensors, comparing various feature formats and neural network models, and finds that image-based inertial features with CNNs yield the best results.

Contribution

It introduces a method for continuous action detection using inertial sensors and compares different feature formats and neural network architectures for improved accuracy.

Findings

Image-based inertial features with CNN achieved 51.1% F1 score.

Comparison of feature formats and neural networks for inertial data.

Demonstrates feasibility of inertial sensors for continuous action detection.

Abstract

Human action detection is a hot topic, which is widely used in video surveillance, human machine interface, healthcare monitoring, gaming, dancing training and musical instrument teaching. As inertial sensors are low cost, portable, and having no operating space, it is suitable to detect human action. In real-world applications, actions that are of interest appear among actions of non interest without pauses in between. Recognizing and detecting actions of interests from continuous action streams is more challenging and useful for real applications. Based on inertial sensor and C-MHAD smart TV gesture recognition dataset, this paper utilized different inertial sensor feature formats, then compared the performance with different deep neural network structures according to these feature formats. Experiment results show the best performance was achieved by image based inertial feature with convolution neural network, which got 51.1% F1 score.