Home // ICAS 2024, The Twentieth International Conference on Autonomic and Autonomous Systems // View article

ELaneNet: Using Lane Parameters for Better Detection of Lanes in Autonomous Driving Systems

Authors:
Elikem Buertey
Kshirasagar Naik
Nitin Naik
Sriram Sivaraman

Keywords: Convolutional Neural Network; Enhanced LaneNet; lane detection; ELaneNet; semantic segmentation; autonomous driving; knowledge guided machine learning

Abstract:
Lane detection is crucial for an Autonomous Driving System (ADS). 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 eLaneNet, 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 eLaneNet over LaneNet in detecting lanes. Using the TuSimple dataset, we show that eLaneNet performs bette than 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 an ADS.

Pages: 7 to 17

Copyright: Copyright (c) IARIA, 2024

Publication date: March 10, 2024

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-68558-140-4

Location: Athens, Greece

Dates: from March 10, 2024 to March 14, 2024