Congratulations to Han Jiang
Congratulations to Han Jiang who successfully defended his MSc thesis, entitled “Semi-automated Generation of Road Transition Lines Using Mobile Laser Scanning Data” on July 31, 2017. The committee members included Prof. Jonathan Li (supervisor, Chair of the defense), Prof. Mike Chapman (Ryerson University, Department of Civil Engineering), Prof. Richard Kelly (University of Waterloo, Department of Geography and Environmental Management) and Prof. Alex Wong (University of Waterloo, Department of Systems Design Engineering).
Thesis abstract:
Recent advances in autonomous vehicles (AVs) are exponential. Prominent car manufacturers, academic institutions, and corresponding governmental departments around the world are taking active roles in the AV industry. Although the attempts to integrate AV technology into smart roads and smart cities have been in the works for more than half a century, the High Definition Road Maps (HDRMs) that assists full self-driving autonomous vehicles did not yet exist. Mobile Laser Scanning (MLS) has enormous potential in the construction of HDRMs due to its flexibility in collecting wide coverage of street scenes and 3D information on scanned targets. However, without proper and efficient execution, it is difficult to generate HDRMs from MLS point clouds.
This study recognises the research gap and difficulties in constructing HDRMs and proposes a robust semi-automated method for transition line (the path that passes through a road intersection) generation in road intersections from MLS point clouds. The proposed method contains three modules: road surface detection by the curb-based region growing algorithm, road marking extraction using the multi-thresholding algorithm, and transition line generation through a combination of the lane marking node structure generation algorithm and the cubic Catmull-Rom spline algorithm. According to the comparative study, the proposed method outperforms other latest methods in road marking extraction.
The experimental results demonstrate that transition lines can be successfully generated for both T-shaped and normal road intersections (four-way road intersections) with promising accuracy. In the validation of lane marking extraction using the manually interpreted lane marking points, the method can achieve 90.68% completeness, 89.42% correctness, and 90.05% F-measure. The success rate of transition line generation is 96.5%. Additionally, the Buffer-overlay-statistics (BOS) method validates that the proposed method can generate lane centerlines and transition lines within a 30-cm range of the reference paths on Unmanned Aerial Vehicle (UAV) images. The completeness of the results in Test Datasets 3 and 4 is 94.8% and 89.7%, respectively, and the miscoding is 4.4% and 8.8%, respectively. In conclusion, this study makes a considerable contribution to the research on generating transition lines for HDRMs, which further contributes to the research of AVs.