Surveillance Patrol Robot for People Tracking in Indoor Environments

Neerparaj Rai; Shakti Dhar; Rupam Kakati

Abstract

There is a great challenge that a mobile robot reliably and continuously tracks a specific person in indoor environments. In this paper, a novel method is presented, which can effectively recognize and reliably track a target person based on mobile robot vision. Such a robot is equipped with a camera which senses a moving object and starts tracking the object. The on-board camera develops a computer vision system for detection of the object/target to control and guide the movement of mobile robot. In order to effectively track the specific person, upper body color clothes region is proposed for extracting the pattern features. The system applies center-of-mass based computation, filtering and color segmentation algorithm to locate the target and the position of the robot. Artificial neural network (ANN) is introduced for controlling the robot to follow the person with voice-aided instructions from the robot. Experimental results validate the robustness and the reliability of this approach.Keywords: Mobile robot, people tracking, color segmentation, filtering