TELECARE: A ROBUST MOTION DETECTION SYSTEM FOR REAL-TIME HUMAN MOVEMENT MONITORING

摘要

This paper presents an image understanding approach to monitor human movement and identify the abnormal circumstance by robust motion detection for the care of the elderly in a home-based environment. In contrast to the conventional approaches which apply either a fixed feature extraction scheme or a pre-defined object model for motion detection and tracking, we introduce a multiple feature extraction scheme for robust motion detection. The proposed algorithms include 1) multiple image feature extraction including the detection of interesting points and boundaries, 2) adaptive thresholding selection based on the compactness measures of fuzzy sets in image feature space, and 3) an optimized algorithm for object tracking and decision making. The feasibility and effectiveness of the proposed approach is demostrated throughout the experimental results of a telecare system by robust motion detection.