Real-Time Structural Detection for Indoor Navigation from 3D LiDAR Using Bird's-Eye-View Images

TL;DR

This paper introduces a lightweight, real-time structural detection framework using Bird's-Eye-View images from 3D LiDAR data, suitable for resource-constrained robots, with a focus on efficiency and robustness.

Contribution

The work presents a novel BEV-based perception pipeline that balances robustness and computational efficiency for real-time structural detection on low-power robotic platforms.

Findings

YOLO-OBB achieves real-time detection at 10 Hz on low-power hardware.

Classical methods are fast but sensitive to noise; RANSAC is robust but not real-time.

The proposed pipeline effectively filters cluttered observations without GPU acceleration.

Abstract

Efficient structural perception is essential for mapping and autonomous navigation on resource-constrained robots. Existing 3D methods are computationally prohibitive, while traditional 2D geometric approaches lack robustness. This paper presents a lightweight, real-time framework that projects 3D LiDAR data into 2D Bird's-Eye-View (BEV) images to enable efficient detection of structural elements relevant to mapping and navigation. Within this representation, we systematically evaluate several feature extraction strategies, including classical geometric techniques (Hough Transform, RANSAC, and LSD) and a deep learning detector based on YOLO-OBB. The resulting detections are integrated through a spatiotemporal fusion module that improves stability and robustness across consecutive frames. Experiments conducted on a standard mobile robotic platform highlight clear performance trade-offs. Classical methods such as Hough and LSD provide fast responses but exhibit strong sensitivity to noise, with LSD producing excessive segment fragmentation that leads to system congestion. RANSAC offers improved robustness but fails to meet real-time constraints. In contrast, the YOLO-OBB-based approach achieves the best balance between robustness and computational efficiency, maintaining an end-to-end latency (satisfying 10 Hz operation) while effectively filtering cluttered observations in a low-power single-board computer (SBC) without using GPU acceleration. The main contribution of this work is a computationally efficient BEV-based perception pipeline enabling reliable real-time structural detection from 3D LiDAR on resource-constrained robotic platforms that cannot rely on GPU-intensive processing. The source code and pre-trained models are publicly available.