Improved Track Continuity in Multi Target Tracking by Fusing Multiple Input Sources
Jeffrey Dyke Millard, Randy Beard · 2018
Reliable track continuity is an important characteristic of multiple target tracking (MTT) algorithms. In the specific case of tracking multiple ground targets from an aerial platform, challenges arise due to realistic operating environments such as imperfections in the measurement source. Some popular visual detection techniques include Kanade-Lucas-Tomasi (KLT)-based motion detection, difference imaging, and object feature matching. Each of these algorithmic detectors has fundamental limitations in regard to providing consistent measurements. In this paper we present a scalable detection framework that leverages multiple measurement sources. We also present the recursive random sample consensus (R-RANSAC) algorithm in a data fusion architecture that can simultaneously accommodate multiple measurement sources. We demonstrate robust track continuity using post-processed flight data and show real-time computational performance.