RCLane: Relay Chain Prediction for Lane Detection

TL;DR

This paper introduces RCLane, a novel lane detection method that predicts relay chains to effectively capture lane topologies, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper proposes a relay chain prediction approach that models lane topologies more effectively than existing dense prediction or detection methods.

Findings

Achieved new state-of-the-art on TuSimple, CULane, CurveLanes, LLAMAS benchmarks.

Effectively captures lane topologies like Y-shape and Fork-shape.

Demonstrated robustness across diverse lane detection scenarios.

Abstract

Lane detection is an important component of many real-world autonomous systems. Despite a wide variety of lane detection approaches have been proposed, reporting steady benchmark improvements over time, lane detection remains a largely unsolved problem. This is because most of the existing lane detection methods either treat the lane detection as a dense prediction or a detection task, few of them consider the unique topologies (Y-shape, Fork-shape, nearly horizontal lane) of the lane markers, which leads to sub-optimal solution. In this paper, we present a new method for lane detection based on relay chain prediction. Specifically, our model predicts a segmentation map to classify the foreground and background region. For each pixel point in the foreground region, we go through the forward branch and backward branch to recover the whole lane. Each branch decodes a transfer map and a distance map to produce the direction moving to the next point, and how many steps to progressively predict a relay station (next point). As such, our model is able to capture the keypoints along the lanes. Despite its simplicity, our strategy allows us to establish new state-of-the-art on four major benchmarks including TuSimple, CULane, CurveLanes and LLAMAS.