Title: Research on Tire Pattern Image Classification
Affiliation: | Xidian University, Xi’an, China | |
Date and Time of Talk: | 14th DECEMBER 2022 | 12:20 PM – 13:00 PM |
Abstract:
Tire pattern recognition is an important means to provide clues for traffic accident processing. With the rapid increase in the number of vehicles, it is in urgent need to develop efficient and automatic tire pattern image classification and recognition system, so as to further improve the work efficiency of law enforcement departments.
This talk will share with the audience what we can done in tire pattern pattern classification, including three parts. (1) Self-built dataset, the largest tire pattern image dataset available for research use. (2) Tire pattern feature extraction, to obtain robust low-level tire pattern features. (3) Deep-learning based tire pattern image classification, for effective tire patter recognition
Biography:
Address: The Institute of Antennas and EM scattering of XidianUniversity PO.Box 377, No.2 Southern TaiBai Road, 710071
Xidian University, Xi’an Shaanxi, P. R. CHINA