Practical Fall Detection System using Vision and Wearable sensors

Fall detection is an important and challenging research problem in healthcare domain. The fall detection system required to operate and give true alert in real time. Many of the existing approaches generates false fall alert which again causes inconvenience for the end users. Hence, there is a need to have robust and accurate fall detection approach with low latency in decision making. In this work, we have proposed and evaluated three different approaches of fall detection system based on a wireless accelerometer based embedded system, RGB Image processing based Software modelling approach and Kinect based depth processing approach. These proposed approaches try to improve on the mentioned drawbacks until we obtain a robust, running in real-time system with high accuracy and low processing time. In all of the demonstrated methods, we do not require any knowledge of the scene and computationally intensive classifiers. The accelerometer based embedded system consists of economic components and is easy to setup. RGB Image processing based Software modelling is simulated on MATLAB have been extensively researched and implemented in real-time. Kinect based depth based techniques are the most recent advancement on the issue and have resolved many discrepancies of the previous methods. The performance of each method is compared against each other. It is shown that our Kinect based depth processing provides promising accuracy of 94% which is better than the other approaches while simultaneously working in real time of 30 frames/second.