Driver recognition using gaussian mixture models and decision fusion techniques
MetadataShow full item record
CitationBenli, K. S., Düzağaç, R. & Eskil, M. T. (2008). Driver recognition using gaussian mixture models and decision fusion techniques. Lecture Notes in Computer Science, 5370, 803-811. doi:10.1007/978-3-540-92137-0_88
In this paper we present our research in driver recognition. The goal of this study is to investigate the performance of different classifier fusion techniques in a driver recognition scenario. We are using solely driving behavior signals such as break and accelerator pedal pressure, engine RPM, vehicle speed; steering wheel angle for identifying the driver identities. We modeled each driver using Gaussian Mixture Models, obtained posterior probabilities of identities and combined these scores using different fixed mid trainable (adaptive) fusion methods. We observed error rates is low as 0.35% in recognition of 100 drivers using trainable combiners. We conclude that the fusion of multi-modal classifier results is very successful in biometric recognition of a person in a car setting.
SourceLecture Notes in Computer Science
Showing items related by title, author, creator and subject.
Gaussian mixture models are an important tool in Bayesian decision theory. In this study, we focus on building such models over statistical database protected under differential privacy. Our approach involves querying ...
Bu bildiride, bilgisayarlı görü ve örüntü tanıma alanlarında çok önemli bir yeri olan plaka tanıma sistemlerinin performansını artırmak amacıyla algoritmik kaynaşım yöntemini önermekteyiz. Plaka tanıma sistemleri genellikle ...
Li, Ke; Kong, Fanzhen; Özaydın, Fatih; Yang, Qing; Cao, Zhuoliang; Yang, Ming (Springer New York LLC, 2016-05-06)An interesting aspect of multipartite entanglement is that for perfect teleportation and superdense coding, not the maximally entangled W states but a special class of non-maximally entangled W-like states are required. ...