Spatio-temporal inductance-pattern recognition for vehicle re-identification

详细信息    查看全文

• 作者：Abdulhai ; Baher ; Tabib ; Seyed M.
• 关键词：ITS ; Loop detector ; Freeway management systems ; Vehicle re-identification ; Vehicle signature ; Spatio-temporal pattern recognition ; Neural networks
• 刊名：Transportation Research Part C: Emerging Technologies
• 出版年：2003
• 出版时间：June - August, 2003
• 年：2003
• 卷：11
• 期：3-4
• 页码：223-239
• 全文大小：282 K

文摘

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.