Fusion of Video and Inertial Sensing for Deep Learning-Based Human Action Recognition.

Haoran Wei,Roozbeh Jafari,Nasser Kehtarnavaz

doi:10.3390/s19173680

Abstract

This paper presents the simultaneous utilization of video images and inertial signals that are captured at the same time via a video camera and a wearable inertial sensor within a fusion framework in order to achieve a more robust human action recognition compared to the situations when each sensing modality is used individually. The data captured by these sensors are turned into 3D video images and 2D inertial images that are then fed as inputs into a 3D convolutional neural network and a 2D convolutional neural network, respectively, for recognizing actions. Two types of fusion are considered—Decision-level fusion and feature-level fusion. Experiments are conducted using the publicly available dataset UTD-MHAD in which simultaneous video images and inertial signals are captured for a total of 27 actions. The results obtained indicate that both the decision-level and feature-level fusion approaches generate higher recognition accuracies compared to the approaches when each sensing modality is used individually. The highest accuracy of 95.6% is obtained for the decision-level fusion approach.

Highlights

Human action recognition has been extensively studied in the literature and has already been incorporated into commercial products
The use of deep learning models or deep neural networks have proven to be more effective than conventional approaches for human action recognition
Paper, the simultaneous utilization video and inertial sensing were considered within a fusion to achievetohuman recognition based onbased deep modalities were considered withinframework a fusion framework achieveaction human action recognition learning models

Summary

Introduction

Human action recognition has been extensively studied in the literature and has already been incorporated into commercial products. The use of deep learning models or deep neural networks have proven to be more effective than conventional approaches for human action recognition. In [15], it was shown that deep learning networks utilizing video images performed better than the previous conventional approaches. Depth cameras have been utilized for human action recognition, e.g., [2,11]. The use of these cameras has been limited to indoor environments as they rely on infrared light for obtaining depth images

Results

Discussion

Conclusion