Qi, Weiqing (The Hong Kong University of Science and Technology (GuangZhou)), ZHAO, Guoyang (HKUST(GZ)), Ma, Fulong (Hong Kong University of Science and Technology), Zheng, Linwei (The Hong Kong University of Science and Technology, HKUST), Ma, Jun (The Hong Kong University of Science and Technology (Guangzhou)), Liu, Ming (HKUST (Guangzhou))

CLRKDNet: Speeding up Lane Detection with Knowledge Distillation

Scheduled for presentation during the Poster Session "Detection, estimatation and prediction for intelligent transportation systems" (WeAT17), Wednesday, September 25, 2024, 10:30−12:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 14, 2024

Abstract

Road lanes are integral components of the visual perception systems in intelligent vehicles, playing a pivotal role in safe navigation. In lane detection tasks, balancing accuracy with real-time performance is essential, yet existing methods often sacrifice one for the other. To address this trade-off, we introduce CLRKDNet, a streamlined model that balances detection accuracy with real-time performance. The state-of-the-art model CLRNet has demonstrated exceptional performance across various datasets, yet its computational overhead is substantial due to its Feature Pyramid Network (FPN) and muti-layer detection head architecture. Our method simplifies both the FPN structure and detection heads, redesigning them to incorporate a novel teacher-student distillation process alongside a newly introduced series of distillation losses. This combination improves inference speed by up to 60% while maintaining detection accuracy comparable to CLRNet. This strategic balance of accuracy and speed makes CLRKDNet a viable solution for real-time lane detection tasks in autonomous driving applications.