Camera-Only Bird's Eye View Perception: A Neural Approach to LiDAR-Free Environmental Mapping for Autonomous Vehicles

TL;DR

This paper introduces a novel camera-only perception system for autonomous vehicles that generates Bird's Eye View maps by integrating object detection and monocular depth estimation, eliminating the need for expensive LiDAR sensors.

Contribution

It extends the Lift-Splat-Shoot architecture to combine YOLOv11 and DepthAnythingV2 for comprehensive scene understanding using only cameras.

Findings

Achieves up to 85% road segmentation accuracy

Detects vehicles with 85-90% accuracy

Maintains average positional errors around 1.2 meters

Abstract

Autonomous vehicle perception systems have traditionally relied on costly LiDAR sensors to generate precise environmental representations. In this paper, we propose a camera-only perception framework that produces Bird's Eye View (BEV) maps by extending the Lift-Splat-Shoot architecture. Our method combines YOLOv11-based object detection with DepthAnythingV2 monocular depth estimation across multi-camera inputs to achieve comprehensive 360-degree scene understanding. We evaluate our approach on the OpenLane-V2 and NuScenes datasets, achieving up to 85% road segmentation accuracy and 85-90% vehicle detection rates when compared against LiDAR ground truth, with average positional errors limited to 1.2 meters. These results highlight the potential of deep learning to extract rich spatial information using only camera inputs, enabling cost-efficient autonomous navigation without sacrificing accuracy.