Detection of fall for the elderly in an indoor environment using a tri-axial accelerometer and Kinect depth data
- PDF / 1,104,852 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 56 Downloads / 218 Views
Detection of fall for the elderly in an indoor environment using a tri-axial accelerometer and Kinect depth data R. Jansi1
· R. Amutha1
Received: 11 March 2019 / Revised: 30 October 2019 / Accepted: 24 January 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Monitoring elderly people who are living alone is a crucial task as they are at great risk of fall occurrence. In this paper, we present a robust framework for fall detection that makes use of two different signals namely tri-axial data from an accelerometer and depth maps from a Kinect sensor. Our approach functions at two stages. At the first stage, the accelerometer data is continuously being monitored and is used to indicate fall whenever the sum vector magnitude of the tri-axial data crosses a specific threshold. This fall indication denotes a high probability of fall occurrence. To confirm this and to avoid false alarms, the depth maps of a predefined window length captured prior to the instant of fall indication are obtained and processed. We propose a new descriptor, Entropy of Depth Difference Gradient Map that acts as a discriminative descriptor in differentiating fall from other daily activities. Finally, fall confirmation is done by employing a sparse representation-based classifier using the extracted descriptors. To ascertain the proposed model, we have performed experimental analysis using a publicly available UR Fall Detection dataset and also using a Synthetic dataset. The experimental results clearly depict the superior performance of our model. Keywords Accelerometer · Classification · Fall detection · Kinect · Sparse representation
1 Introduction and related works Fall detection is a pivotal task in the aspect of the independent living of the elderly. There are several approaches being proposed in the literature for identifying the falls from the daily activities. These include the usage of infrared sensor arrays (Liu et al. 2012), RFID modules (Chen and Lin 2010), floor vibrations (Zigel et al. 2009), floor sensors (Rimminen et al. 2010), vision-based cameras (Alhimale et al. 2014; De Miguel et al. 2017), wearable sensors (Li et al. 2009; Wu et al. 2015) etc. The most commonly used technique for fall detection involves the usage of wearable sensors. A quaternion algorithm has been proposed (Wu et al. 2015) for the detection of fall
B 1
R. Jansi [email protected] Department of Electronics and Communication Engineering, SSN College of Engineering, Chennai, India
123
Multidimensional Systems and Signal Processing
from daily activities using a single accelerometer. In this work, falls were detected based on a threshold that was calculated using accelerometer measurements along the three axes and rotation angle of the accelerometer readings. Detection of human fall is also possible using a bi-axial gyroscope sensor (Bourke and Lyons 2008). In this work, in order to distinguish falls from daily activities, a threshold-based algorithm was used wherein parameters like angular velocity, angular acceleratio
Data Loading...
