An Infrared Array Sensor-Based Approach for Activity Detection, Combining Low-Cost Technology with Advanced Deep Learning Techniques

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 10; p. 3898
• Main Authors: Muthukumar, Krishnan Arumugasamy, Bouazizi, Mondher, Ohtsuki, Tomoaki
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 20.05.2022; MDPI
• Subjects: Accuracy; activity detection; Analysis; Classification; computer vision; Deep Learning; healthcare; Image Processing, Computer-Assisted - methods; infrared array sensor; low-resolution; Methods; Neural networks; Neural Networks, Computer; Noise; Older people; Population; Sensors; Technology; Wearable computers; Japan; activity detection; denoising; deep learning; infrared array sensor; super-resolution; computer vision; low-resolution; CGAN; healthcare
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22103898

In this paper, we propose an activity detection system using a 24 × 32 resolution infrared array sensor placed on the ceiling. We first collect the data at different resolutions (i.e., 24 × 32, 12 × 16, and 6 × 8) and apply the advanced deep learning (DL) techniques of Super-Resolution (SR) and denoising to enhance the quality of the images. We then classify the images/sequences of images depending on the activities the subject is performing using a hybrid deep learning model combining a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM). We use data augmentation to improve the training of the neural networks by incorporating a wider variety of samples. The process of data augmentation is performed by a Conditional Generative Adversarial Network (CGAN). By enhancing the images using SR, removing the noise, and adding more training samples via data augmentation, our target is to improve the classification accuracy of the neural network. Through experiments, we show that employing these deep learning techniques to low-resolution noisy infrared images leads to a noticeable improvement in performance. The classification accuracy improved from 78.32% to 84.43% (for images with 6 × 8 resolution), and from 90.11% to 94.54% (for images with 12 × 16 resolution) when we used the CNN and CNN + LSTM networks, respectively.