Author, Institution: Juozas Balamutas, Kaunas University of Technology
Science area, field of science: Technological Sciences, Electrical and Electronics Engineering, T001
Research Supervisor: Prof. Dr. Dangirutis Navikas (Kaunas University of Technology, Electrical and Electronics Engineering, T001)
Dissertation Defence Board of Electrical and Electronic Engineering Science Field:
Prof. Dr. Elena Jasiūnienė (Kaunas University of Technology, Technological Sciences, Electrical and Electronics Engineering, T001) – chairperson
Assoc. Prof. Dr. Hab. Adam Idzkowski (Bialystok University of Technology, Poland, Technological Sciences, Electrical and Electronics Engineering, T001)
Prof. Dr. Darius Plonis (Vilnius Gediminas Technical University, Technological Sciences, Electrical and Electronics Engineering, T001)
Assoc. Prof. Dr. Reimondas Šliteris (Kaunas University of Technology, Technological Sciences, Electrical and Electronics Engineering, T001)
Prof. Dr. Darius Viržonis (Kaunas University of Technology, Technological Sciences, Electrical and Electronics Engineering, T001)
Dissertation defence meeting will be at Rectorate Hall of Kaunas University of Technology (K. Donelaičio 73-402, Kaunas)
The doctoral dissertation is available at the library of Kaunas University of Technology (Gedimino 50, Kaunas) and on the internet: J. Balamutas el.dissertation (PDF)
Annotation: In Intelligent Transportation Systems, unique vehicle identification plays a crucial role in improving traffic management, security, and road safety. Traditional re-identification methods primarily rely on video-based systems, which are sensitive to environmental conditions, suffer from visual obstructions, and face challenges related to data privacy. To address these limitations, this research explores an alternative approach using magnetic sensors embedded in the road. In this research a custom magnetic signature collection system is designed and implemented to capture Earth’s magnetic field distortions caused by passing vehicles. Innovative algorithms for temperature, auxiliary offset and wheel influence elimination are developed. Methods for depersonalized unique vehicle re-identification using captured magnetic signatures are designed and assessed. Various feature extraction algorithms and distance metrics are analyzed to evaluate their effectiveness in identifying similar magnetic signatures. Initial processing is applied on registered magnetic signatures, useful features extracted for decision making, different similarity assessment algorithms applied and prediction accuracy checked on real traffic data.
April 16 d. 10:00
Rectorate Hall at Kaunas University of Technology (K. Donelaičio 73-402, Kaunas)
Įtraukti į iCal
