Intelligent household surveillance robot

Abstract

In many societies, the aged people are often living alone. For the aging population, surveillance in household environments has become more and more important. In this paper, we present a household surveillance robot that can detect abnormal events by utilizing video and audio information. In our approach, moving targets can be detected by the robot with a passive acoustic location device. Then the robot tracks the targets by employing a particle filter algorithm. In adapting to different lighting conditions, the target model is updated regularly based on an update mechanism. To achieve robust tracking, the robot detects abnormal human behaviors by tracking the upper body of a person. For audio surveillance, Mel frequency cepstral coefficients(MFCC) is used to extract features from audio information. Those features are input to a support vector machine classifier for analysis. When any abnormal audio information is detected, a camera on the robot will be triggered to further confirm the occurrence of the abnormal event. Experimental results show that the robot can detect abnormal behaviors such as “falling down” and “running”. Also, a 88.17% accuracy rate is achieved in the detection of abnormal audio information like “crying”, “groan”, and “gun shooting”.