Fuzzy Clustering Means algorithm for track fusion in U.S. Coast Guard Vessel Traffic Service systems

摘要

This thesis presents a fuzzy association based data fusion algorithm for U.S. Coast Guard Vessel Traffic Service (VTS) systems to reduce the number of redundant target tracks displayed to vessel traffic operators. The proposed algorithm uses the Fuzzy Clustering Means (FCM) algorithm to reduce the number of target tracks and associate duplicate tracks by determining the degree of membership for each target track. The algorithm uses current sensor data and the known sensor resolutions for measurement-to-measurement association and the selection of the most accurate sensor for tracking fused targets. Actual vessel traffic data collected from U.S. Coast Guard VTS systems are used for simulation and analysis of the algorithm. The results exhibit successful fusion of correlated tracks and selection of the most accurate sensor resulting in a reduced number of tracks displayed to the VTS operator.