Depth-Based Human Fall Detection via Shape Features and Improved Extreme Learning Machine

Abstract

Falls are one of the major causes leading to injury of elderly people. Using wearable devices for fall detection has a high cost and may cause inconvenience to the daily lives of the elderly. In this paper, we present an automated fall detection approach that requires only a low-cost depth camera. Our approach combines two computer vision techniques-shape-based fall characterization and a learning-based classifier to distinguish falls from other daily actions. Given a fall video clip, we extract curvature scale space (CSS) features of human silhouettes at each frame and represent the action by a bag of CSS words (BoCSS). Then, we utilize the extreme learning machine (ELM) classifier to identify the BoCSS representation of a fall from those of other actions. In order to eliminate the sensitivity of ELM to its hyperparameters, we present a variable-length particle swarm optimization algorithm to optimize the number of hidden neurons, corresponding input weights, and biases of ELM. Using a low-cost Kinect depth camera, we build an action dataset that consists of six types of actions (falling, bending, sitting, squatting, walking, and lying) from ten subjects. Experimenting with the dataset shows that our approach can achieve up to 91.15% sensitivity, 77.14% specificity, and 86.83% accuracy. On a public dataset, our approach performs comparably to state-of-the-art fall detection methods that need multiple cameras.

Proposing Enhanced Feature Engineering and a Selection Model for Machine Learning Processes

“…However, their work needs to be extended to more SL algorithms. Ma et al [16] utilized Particle Swarm Optimization (PSO) algorithm to develop their proposed approach for detection of falling elderly people. Their proposed research enhances the selection of variables (such as hidden neurons, input weights, etc.)…”

Three Ways to Improve the Performance of Real-Life Camera-Based Fall Detection Systems

“…The commercialization of the Microsoft Kinect also provides the possibility of directly extracting 3D images in an affordable way. This has led to the usage of this sensor to detect falls [34,35]. Another path that is sometimes used is thermal imagers [36].…”

P1‐429: Adding Intelligence to a Floor‐Based Array Personnel Detector

“…It correctly locates the source of falling sound in attempt to reduce false alarms, which also makes the system robust under noisy situations. In [10] Microsoft Kinect presents a depth-based human fall detection technique, utilizing both shape-based and learning-based classifiers. In [17] a fall detection system based on floor vibration using a piezoelectric sensor was designed.…”