An efficient method for extracting road lane mark by fusing vehicle-based stereo image and laser range data

Nowadays, an integration of real-time sensing and map reference from vehicles would be very effective to achieve a complete Cruise-Assist system such as what can make a driver avoid a traffic accident. However, existing digital road maps such as network data or simple 3D data for vehicle navigation cannot support Cruise-Assist well, in particular, in an urban area. In fact, various road features such as zebra, road lane mark, and boundary are required for accurate map reference, and more, those features should have higher precision and more detail information. But, so far it is labor-intensive and costly for acquiring this kind of road spatial data, therefore, an efficient method, which can acquire that kind of spatial data automatically and robustly, is required. This research focuses on efficient acquisition of road lane mark and carries out a method for extracting them by fusing vehicle-based stereo image and laser range data. A lot of experiments were performed to certify and check the efficiency of our fusion-based automatic road lane mark extraction method. From achieved results of these experiments, our fusion-based automatic extraction of road lane mark can get high success ratio (more than 90%).