Inertial Sensor Data to Image Encoding for Human Action Recognition

Convolutional Neural Networks (CNNs) are successful deep learning models in the field of computer vision. To get the maximum advantage of CNN model for Human Action Recognition (HAR) using inertial sensor data, in this paper, we use four types of spatial domain methods for transforming inertial sensor data to activity images, which are then utilized in a novel fusion framework. These four types of activity images are Signal Images (SI), Gramian Angular Field (GAF) Images, Markov Transition Field (MTF) Images and Recurrence Plot (RP) Images. Furthermore, for creating a multimodal fusion framework and to exploit activity images, we made each type of activity images multimodal by convolving with two spatial domain filters: Prewitt filter and High-boost filter. ResNet-18, a CNN model, is used to learn deep features from multi-modalities. Learned features are extracted from the last pooling layer of each ResNet and then fused by canonical correlation based fusion (CCF) for improving the accuracy of human action recognition. These highly informative features are served as input to a multi-class Support Vector Machine (SVM). Experimental results on three publicly available inertial datasets show the superiority of the proposed method over the current state-of-the-art.

Automated summary

Convolutional Neural Networks (CNNs) are used to recognize human actions using inertial sensor data in this study, where four spatial domain methods are employed to transform the sensor data into activity images. The multimodal fusion framework improves the accuracy by convolving each activity image with two spatial filters and fusing the deep features learned by CNN model ResNet-18. The proposed method demonstrates superiority over the current state-of-the-art in human action recognition on inertial datasets.