Candidate: Elikem Buertey
Date: December 12, 2023
Time: 11:00 AM - 12:00 PM
Location: EIT 3141
Supervisor(s): Kshirasagar Naik, Hamed Majedi and Sherman Shen
Abstract:
Lane detection is crucial for autonomous vehicles and advanced driver assistance systems (ADAS). While traditional lane detection methods have limitations, machine learning has shown promise, though many deep learning networks struggle with variable lane detection. High Definition (HD) maps provide comprehensive road information but are expensive and inflexible. This research proposes Improved LaneNet (ILaneNet), a flexible, cost-effective, and robust lane detection system that adapts to diverse driving scenarios. By incorporating the number of lanes into the network, we demonstrate improved adaptability and potential advancements in autonomous driving technologies. We also introduce new evaluation metrics, namely, capacity, lost capacity and unsafe driving measure to assess lane detection techniques more comprehensively. We also propose evaluation of lane detection techniques by using a lane abstraction approach instead of the traditional line abstraction method. Through extensive evaluation and comparisons, we showcase the superiority of Improved LaneNet over LaneNet in detecting lanes. This research contributes to bridging the gap between ML techniques and HD maps, offering a viable solution for effective and efficient lane detection in autonomous vehicles and ADAS.