Research on target detection and tracking system of rescue robot

Abstract

This target detection and tracking system is the basis for rescue robots to achieve their independent search and rescue operations. In order to improve their mobile performance and sensing capability, the Kinect camera is employed by rescue robots to obtain environmental visual. The AKAZE(Accelerated-KAZE) feature matching algorithm is adopted to achieve target detection in video frames, combining with the RANSAC (random sample consensus) algorithm to remove the mismatch point to improve the detection accuracy. In addition, the TLD(tracking learning detection) tracking algorithm is used to track the detected targets, combining with the target depth information to calculate their world coordinates and drive robots to achieve the target tracking. This study builds a software system based on the Ubuntu system and the ROS (robot operating system) platform. Turtlebot robot is used as the experimental platform for tests. Experimental results show that the proposed system can quickly detect the target and track the target in a multi-barrier environment in real-time.