Development of an Automatic Road Sign Extraction Method by Fusion of Stereo Images and Laser Data

Abstract

In this research, an advanced data fusion technology was developed for the purpose of precise/automatic road sign extraction, by fusing collected initial navigation data, stereo images and laser range data. The major contributions of this research are fusion of stereo images and laser range data for high accurate road sign candidate extraction and reducing the misrecognition of road signs by using 3D information and multi-stereo-images.
A lot of experiments were performed to certify and check the accuracy and efficiency of our fusion-based precise/automatic road sign extraction technology. From achieved results of these experiments, our developed system is efficient system for generating high-accuracy road sign database.