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

• Published in: IEEE journal of biomedical and health informatics Vol. 18; no. 6; pp. 1915 - 1922
• Main Authors: Ma, Xin, Wang, Haibo, Xue, Bingxia, Zhou, Mingang, Ji, Bing, Li, Yibin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2014
• Subjects: Accidental Falls; Accuracy; Algorithm design and analysis; Algorithms; Artificial Intelligence; Cameras; Computer vision; Curvature scale space (CSS); extreme learning machine (ELM); fall detection; Feature extraction; Female; Humans; Image Processing, Computer-Assisted - methods; Male; Models, Statistical; Monitoring, Ambulatory - methods; Particle swarm optimization; Posture - physiology; Sensitivity and Specificity; shape contour; Walking - physiology

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. O...