Machine Vision and Pattern Recognition Laboratory (MVPR) at Lappeenranta
University of Technology (LUT) is focused on intelligent computing, especially
on digital image processing and analysis applications. This presentation focuses
on machine vision applications for automatic traffic sign inventory and
simultaneous condition analysis. These applications can be used to improve road
maintenance processes, to decrease maintenance costs, and to meet the
requirements of future intelligent driving systems. Machine vision based
inventory of traffic signs consists of detection, classification, localization,
and condition analysis. The goal of this research is to combine automatic
traffic sign detection and classification with traffic sign inventory and
condition analysis. This study proposes a machine vision system for traffic sign
inventory. The performance of the system is evaluated with three datasets: the
Swedish summer dataset and two datasets specifically collected for this
research. Experimental results showed that the system was able to detect, to
locate, and to classify almost all the traffic signs and to analyze their
condition robustly.