Regions of Interest Segmentation from LiDAR Point Cloud for Multirotor Aerial Vehicles

TL;DR

This paper introduces a real-time LiDAR point cloud segmentation filter designed for multirotor drones, enabling efficient obstacle detection without prior mapping, suitable for agricultural low-altitude operations.

Contribution

A novel LiDAR segmentation filter that operates in real-time on sparse point clouds for obstacle avoidance in multirotor aerial vehicles, without requiring preliminary mapping.

Findings

Effective segmentation in simulated environments

Successful real-world drone implementation

Open-source code and datasets provided

Abstract

We propose a novel filter for segmenting the regions of interest from LiDAR 3D point cloud for multirotor aerial vehicles. It is specially targeted for real-time applications and works on sparse LiDAR point clouds without preliminary mapping. We use this filter as a crucial component of fast obstacle avoidance system for agriculture drone operating at low altitude. As the first step, each point cloud is transformed into a depth image and then identify places near to the vehicle (local maxima) by locating areas with high pixel densities. Afterwards, we merge the original depth image with identified locations after maximizing intensities of pixels in which local maxima were obtained. Next step is to calculate the range angle image that represents angles between two consecutive laser beams based on the improved depth image. Once the corresponding range angle image is constructed, smoothing is applied to reduce the noise. Finally, we find out connected components within the improved depth image while incorporating smoothed range angle image. This allows separating the regions of interest. The filter has been tested on various simulated environments as well as an actual drone and provides real-time performance. We make our source code, dataset available at https://github.com/GPrathap/hagen.git and real world experiment result can be found on the following link: https://www.youtube.com/watch?v=iHd_ZkhKPjc available online.