Flexible 3D Lane Detection by Hierarchical Shape MatchingFlexible 3D Lane Detection by Hierarchical Shape Matching

TL;DR

This paper introduces a hierarchical, end-to-end 3D lane detection method from point clouds that improves accuracy in complex scenes by combining global parametric curve regression with local shape detection.

Contribution

It proposes a novel hierarchical network architecture that predicts flexible lane shapes at multiple levels, integrating global and local information for enhanced 3D lane detection.

Findings

Outperforms current top methods on two datasets.

Achieves high precision in complex scenes.

Ablation studies confirm effectiveness of each component.

Abstract

As one of the basic while vital technologies for HD map construction, 3D lane detection is still an open problem due to varying visual conditions, complex typologies, and strict demands for precision. In this paper, an end-to-end flexible and hierarchical lane detector is proposed to precisely predict 3D lane lines from point clouds. Specifically, we design a hierarchical network predicting flexible representations of lane shapes at different levels, simultaneously collecting global instance semantics and avoiding local errors. In the global scope, we propose to regress parametric curves w.r.t adaptive axes that help to make more robust predictions towards complex scenes, while in the local vision the structure of lane segment is detected in each of the dynamic anchor cells sampled along the global predicted curves. Moreover, corresponding global and local shape matching losses and anchor cell generation strategies are designed. Experiments on two datasets show that we overwhelm current top methods under high precision standards, and full ablation studies also verify each part of our method. Our codes will be released at https://github.com/Doo-do/FHLD.