Automated remote fall detection using impact features from video and audio |
| |
| Affiliation: | 1. Stichting Epilepsie Instellingen Nederland (SEIN), the Netherlands;2. Image Sciences Institute, University Medical Center Utrecht, Utrecht, the Netherlands;3. Utrecht University, Utrecht, the Netherlands;1. AGH University of Science and Technology, 30 Mickiewicza Av., 30-059 Krakow, Poland;2. University of Rzeszow, Pigonia 1, 35-310 Rzeszow, Poland;1. Computer Languages and Systems Department, University of Seville, 41012 Seville, Spain;2. Applied Economics I Department, University of Seville, 41012 Seville, Spain;1. AGH University of Science and Technology, 30 Mickiewicza Av., 30-059 Kraków, Poland;2. University of Rzeszow, 16c Rejtana Av., 35-959 Rzeszów, Poland;1. Faculty of Medicine, Université de Montréal, C.P. 6128 Centre-ville, Montréal, Québec, H3C 3J7, Canada;2. Research Center, Institut universitaire de gériatrie de Montréal (Pavillon André-Roch Lecours), 4565 chemin Queen-Mary, Montréal, Québec, H3W 1W5, Canada;3. Department of Occupational Therapy, Faculty of Rehabilitation Medicine, University of Alberta. 2-64 Corbett Hall, Edmonton, AB, T6G 2G4, Canada;4. School of Medicine and Health Sciences, Universidad del Rosario. Calle 63D # 24-31, 7 de Agosto, Bogotá D.C, Colombia, Colombia;5. Faculty of Medicine, Université de Montréal, School of Rehabilitation, Site Pavillon Parc, C.P. 6128 Centre-ville, Montréal, Québec, H3C 3J7, Canada |
| |
| Abstract: | Elderly people and people with epilepsy may need assistance after falling, but may be unable to summon help due to injuries or impairment of consciousness. Several wearable fall detection devices have been developed, but these are not used by all people at risk. We present an automated analysis algorithm for remote detection of high impact falls, based on a physical model of a fall, aiming at universality and robustness. Candidate events are automatically detected and event features are used as classifier input. The algorithm uses vertical velocity and acceleration features from optical flow outputs, corrected for distance from the camera using moving object size estimation. A sound amplitude feature is used to increase detector specificity. We tested the performance and robustness of our trained algorithm using acted data from a public database and real life data with falls resulting from epilepsy and with daily life activities. Applying the trained algorithm to the acted dataset resulted in 90% sensitivity for detection of falls, with 92% specificity. In the real life data, six/nine falls were detected with a specificity of 99.7%; there is a plausible explanation for not detecting each of the falls missed. These results reflect the algorithm’s robustness and confirms the feasibility of detecting falls using this algorithm. |
| |
| Keywords: | Fall detection Remote sensing Pattern recognition Video analysis |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
