Target Detection and Tracking Using Intelligent Wheelchair

Hammad Khan (CESAT, Pakistan); Saima Rehman (NUST, Pakistan); Tabinda Ashraf (Munster Technological University, Ireland); Muhammad Umair, Usama Zubair and Yasir Ayaz (NUST, Pakistan)

Human-robot interaction is one of the most basic requirements for service robots. In order to provide the desired service, these robots are required to detect and track people in human cluttered environment. Once the target to be followed has been recognized by robot, next step is navigation while taking care of obstacles. This paper presents a novel approach for the target detection to make the robot able of target tracking in a cluttered environment. Using data from Hough transform our system classifies the target person from other human beings in the environment. Our system tracks human being by gathering details of his position and velocity, and then converting this data into corresponding linear and angular velocity of robot. System used in the project is an intelligent wheelchair with partial AI and partial human command based working architecture with LRF and stereo camera mounted on it.

Journal: International journal of simulation: systems, science & technology V18

Published: Mar 31, 2017

DOI: 10.5013/IJSSST.a.18.01.04