DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection

TL;DR

This paper introduces a depth-aware BEV feature transformation method for 3D lane detection that effectively integrates monocular depth estimation to improve accuracy over traditional flat-ground assumptions.

Contribution

It proposes a novel feature extraction and fusion framework that incorporates depth information to enhance BEV feature construction for 3D lane detection.

Findings

Performs comparably with state-of-the-art on Apollo and OpenLane datasets.

Effectively integrates depth estimation to improve 3D perception.

Simplifies view transformation by combining FV and depth features.

Abstract

3D Lane detection plays an important role in autonomous driving. Recent advances primarily build Birds-Eye-View (BEV) feature from front-view (FV) images to perceive 3D information of Lane more effectively. However, constructing accurate BEV information from FV image is limited due to the lacking of depth information, causing previous works often rely heavily on the assumption of a flat ground plane. Leveraging monocular depth estimation to assist in constructing BEV features is less constrained, but existing methods struggle to effectively integrate the two tasks. To address the above issue, in this paper, an accurate 3D lane detection method based on depth-aware BEV feature transtormation is proposed. In detail, an effective feature extraction module is designed, in which a Depth Net is integrated to obtain the vital depth information for 3D perception, thereby simplifying the complexity of view transformation. Subquently a feature reduce module is proposed to reduce height dimension of FV features and depth features, thereby enables effective fusion of crucial FV features and depth features. Then a fusion module is designed to build BEV feature from prime FV feature and depth information. The proposed method performs comparably with state-of-the-art methods on both synthetic Apollo, realistic OpenLane datasets.