Title :
Modelling temporal variations by polynomial regression for classification of radar tracks
Author :
Jochumsen, Lars W. ; Ostergaard, Jacob ; Jensen, Soren Holdt ; Pedersen, Morten O.
Author_Institution :
Terma A/S, Lystrup, Denmark
Abstract :
The sampling rate of a radar is often too low to reliably capture the acceleration of moving targets such as birds. Moreover, the sampling rate depends upon the target´s acceleration and heading and will therefore generally be time varying. When classifying radar tracks using temporal features, too low or highly varying sampling rates deteriorates the classifier´s performance. In this work, we propose to model the temporal variations of the target´s speed by low-order polynomial regression. Using the polynomial we obtain the conditional statistics of the targets speed at some future time given its speed at the current time. When used in a classifier based on Gaussian mixture models and with real radar data, it is shown that the inclusions of conditional statistics describing the targets temporal variations, leads to a substantial improvement in the overall classification performance.
Keywords :
Gaussian processes; mixture models; polynomials; radar tracking; regression analysis; signal classification; target tracking; Gaussian mixture model; conditional statistics; moving target acceleration; polynomial regression; radar track classification; sampling rate; target heading; temporal variation modelling; Acceleration; Birds; Marine vehicles; Radar cross-sections; Radar tracking; Target tracking; Automatic target classification; Machine learning; Radar; Surveillance;
Conference_Titel :
Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European
Conference_Location :
Lisbon