Decentralized Training of 3D Lane Detection with Automatic Labeling Using HD Maps,
Paper in proceeding, 2023

To have competent 3D lane detection for real-world driving, a massive amount of data from all over the world is needed, but data collection and manual annotation are costly and time-consuming. The diversity of data collected by developmental cars might still be limited compared to the data collected by a large fleet of customer cars. Federated learning enables training models on edge without transferring data out of devices. However, training supervised learning tasks at the edge is directly tied to having access to high-quality labels, which is limited at the edge. In this paper, we propose a fully automatic method to generate 3D lane labels at the edge using a pre-recorded HD map to enable the federated training of the 3D lane detection model. As a reference, a semi-automatic method is applied for creating a 3D-lane dataset used as ground truth. Our experimental results show that the model can achieve comparable performance when training on the same dataset in both a centralized and a decentralized manner. And the models trained on semi-automatic labeled datasets slightly outperform those trained on fully-automatically labeled datasets. This study shows that a well-performing 3D lane detection model can be trained in a supervised and fully decentralized manner, and most importantly, data privacy at the edge is guaranteed.

Federated Learning


3D Lane Detection


Yadong Mao

Chalmers University of Technology

Zhuqi Xiao

Chalmers University of Technology

Che-Tsung Lin

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Pedro Porto Buarque de Gusmão

University of Cambridge

Nicholas Lane

University of Cambridge

Christopher Zach

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Mina Alibeigi

Zenseact AB

IEEE Vehicular Technology Conference

15502252 (ISSN)

Florence, Italy,

Subject Categories


Transport Systems and Logistics

Communication Systems

Electrical Engineering, Electronic Engineering, Information Engineering

More information