Title :
Neural Networks for Improved Tracking
Author :
Perlovsky, Leonid I. ; Deming, Ross W.
Author_Institution :
Harvard Univ., Cambridge
Abstract :
In this letter, we have developed a neural network (NN) based upon modeling fields for improved object tracking. Models for ground moving target indicator (GMTI) tracks have been developed as well as neural architecture incorporating these models. The neural tracker overcomes combinatorial complexity of tracking in highly cluttered scenarios and results in about 20-dB (two orders of magnitude) improvement in signal-to-clutter ratio.
Keywords :
computer vision; image motion analysis; neural nets; object detection; radar detection; radar tracking; target tracking; combinatorial complexity; ground moving target indicator; multitarget tracking; neural architecture; neural networks; object tracking; radar tracking; signal-to-clutter ratio; Combinatorial complexity; ground moving target indicator (GMTI) radar; multitarget tracking; neural networks (NNs);
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2007.903143
