Abstract
Very recent research efforts started investigating the possibilities of more ‘intelligent’ usage of Inductive Loop Detectors (ILD), to possibly derive ‘wide-area’/‘section-related’ measures from their outputs, as opposed to the limited conventional point measurements. This research attempts to improve the accuracy of vehicle re-identification at successive loop detector stations through improving the distance measures for pattern nearness in the pattern matching process. Vehicle inductance-signature data, collected by a California team of researchers, were further analysed at the University of Toronto. Several new techniques including neural networks, new distance measures and waveform warping-reduction processes were investigated to match the vehicle signature waveforms showing potential for significant accuracy improvement compared to features reported in the literature.