SwiftLane: Towards Fast and Efficient Lane Detection

TL;DR

SwiftLane introduces a lightweight, end-to-end deep learning framework for lane detection that achieves real-time performance with high accuracy, suitable for embedded systems like Nvidia Jetson AGX Xavier.

Contribution

The paper presents a novel, fast, and efficient lane detection method that outperforms existing approaches in speed while maintaining accuracy, optimized for resource-constrained devices.

Findings

Achieves 411 fps inference speed on standard hardware.

Maintains competitive accuracy on CULane benchmark.

Enables real-time detection at 56 fps on Nvidia Jetson AGX Xavier.

Abstract

Recent work done on lane detection has been able to detect lanes accurately in complex scenarios, yet many fail to deliver real-time performance specifically with limited computational resources. In this work, we propose SwiftLane: a simple and light-weight, end-to-end deep learning based framework, coupled with the row-wise classification formulation for fast and efficient lane detection. This framework is supplemented with a false positive suppression algorithm and a curve fitting technique to further increase the accuracy. Our method achieves an inference speed of 411 frames per second, surpassing state-of-the-art in terms of speed while achieving comparable results in terms of accuracy on the popular CULane benchmark dataset. In addition, our proposed framework together with TensorRT optimization facilitates real-time lane detection on a Nvidia Jetson AGX Xavier as an embedded system while achieving a high inference speed of 56 frames per second.