End-to-End Lane Marker Detection via Row-wise Classification

TL;DR

This paper introduces an end-to-end lane marker detection method that transforms the problem into a row-wise classification task, eliminating the need for post-processing and achieving competitive results on standard benchmarks.

Contribution

The paper proposes a novel row-wise classification approach for lane detection, enabling direct vertex prediction without post-processing, which is a significant departure from traditional dense prediction methods.

Findings

Outperforms state-of-the-art on TuSimple and CULane benchmarks

Eliminates post-processing in lane detection pipeline

Achieves comparable or better accuracy with end-to-end approach

Abstract

In autonomous driving, detecting reliable and accurate lane marker positions is a crucial yet challenging task. The conventional approaches for the lane marker detection problem perform a pixel-level dense prediction task followed by sophisticated post-processing that is inevitable since lane markers are typically represented by a collection of line segments without thickness. In this paper, we propose a method performing direct lane marker vertex prediction in an end-to-end manner, i.e., without any post-processing step that is required in the pixel-level dense prediction task. Specifically, we translate the lane marker detection problem into a row-wise classification task, which takes advantage of the innate shape of lane markers but, surprisingly, has not been explored well. In order to compactly extract sufficient information about lane markers which spread from the left to the right in an image, we devise a novel layer, which is utilized to successively compress horizontal components so enables an end-to-end lane marker detection system where the final lane marker positions are simply obtained via argmax operations in testing time. Experimental results demonstrate the effectiveness of the proposed method, which is on par or outperforms the state-of-the-art methods on two popular lane marker detection benchmarks, i.e., TuSimple and CULane.