# Deep Multi-Sensor Lane Detection

## TL;DR

This paper introduces a deep neural network that fuses LiDAR and camera data to directly estimate accurate 3D lane boundaries, improving autonomous driving in complex scenarios.

## Contribution

It presents a novel multi-sensor deep learning approach that directly predicts 3D lane boundaries, addressing limitations of image-based methods.

## Key findings

- High accuracy in 3D lane boundary estimation demonstrated
- Effective in complex scenarios like occlusion, forks, and intersections
- Outperforms traditional image-based lane detection methods

## Abstract

Reliable and accurate lane detection has been a long-standing problem in the field of autonomous driving. In recent years, many approaches have been developed that use images (or videos) as input and reason in image space. In this paper we argue that accurate image estimates do not translate to precise 3D lane boundaries, which are the input required by modern motion planning algorithms. To address this issue, we propose a novel deep neural network that takes advantage of both LiDAR and camera sensors and produces very accurate estimates directly in 3D space. We demonstrate the performance of our approach on both highways and in cities, and show very accurate estimates in complex scenarios such as heavy traffic (which produces occlusion), fork, merges and intersections.