Title :
An Address-Event Fall Detector for Assisted Living Applications
Author :
Zhengming Fu ; Delbruck, T. ; Lichtsteiner, P. ; Culurciello, E.
Author_Institution :
Dept. of Electr. Eng., Yale Univ., New Haven, CT
fDate :
6/1/2008 12:00:00 AM
Abstract :
In this paper, we describe an address-event vision system designed to detect accidental falls in elderly home care applications. The system raises an alarm when a fall hazard is detected. We use an asynchronous temporal contrast vision sensor which features sub-millisecond temporal resolution. The sensor reports a fall at ten times higher temporal resolution than a frame-based camera and shows 84% higher bandwidth efficiency as it transmits fall events. A lightweight algorithm computes an instantaneous motion vector and reports fall events. We are able to distinguish fall events from normal human behavior, such as walking, crouching down, and sitting down. Our system is robust to the monitored person´s spatial position in a room and presence of pets.
Keywords :
CMOS image sensors; biomechanics; biomedical measurement; domestic safety; geriatrics; health care; health hazards; CMOS image sensor; address-event fall detector; address-event vision system; assisted living applications; asynchronous temporal contrast vision sensor; crouching down; elderly home care applications; instantaneous motion vector; lightweight algorithm; motion detection; sitting down; walking; Bandwidth; Biomedical monitoring; Cameras; Detectors; Hazards; Humans; Legged locomotion; Machine vision; Senior citizens; Sensor phenomena and characterization; AER; Address-event; CMOS image sensor; assisted living; elderly home care; fall detection; motion detection; temporal-difference; vision sensor;
Journal_Title :
Biomedical Circuits and Systems, IEEE Transactions on
DOI :
10.1109/TBCAS.2008.924448