A Real-Time and Multi-Sensor-Based Landing Area Recognition System for UAVs

This paper presents a real-time and multi-sensor-based landing area recognition system for UAVs, which aims to enable UAVs to land safely on open and flat terrain and is suitable for comprehensive unmanned autonomous operation. The landing area recognition system for UAVs is built on the combination...

Full description

Saved in:
Bibliographic Details
Published inDrones (Basel) Vol. 6; no. 5; p. 118
Main Authors Liu, Fei, Shan, Jiayao, Xiong, Binyu, Fang, Zheng
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 07.05.2022
Subjects
3DLiDAR
Algorithms
autonomous landing
Cameras
Contact angle
deep learning
Landing
Lidar
Localization
Methods
multi-sensor fusion
Object recognition
object tracking
Real time
Researchers
semantic segmentation
Semantics
Sensors
Three dimensional models
Unmanned aerial vehicles
Vision systems
Online AccessGet full text

Cover

More Information
Summary:This paper presents a real-time and multi-sensor-based landing area recognition system for UAVs, which aims to enable UAVs to land safely on open and flat terrain and is suitable for comprehensive unmanned autonomous operation. The landing area recognition system for UAVs is built on the combination of a camera and a 3D LiDAR. The problem is how to fuse the image and point cloud information and realize the landing area recognition to guide the UAV landing autonomously and safely. To solve this problem, firstly, we use a deep learning method to realize the landing area recognition and tracking from images. After that, we project 3D LiDAR point cloud data into camera coordinates to obtain the semantic label of each point. Finally, we use the 3D LiDAR point cloud data with the semantic label to build the 3D environment map and calculate the most suitable area for UAV landing. Experiments show that the proposed method can achieve accurate and robust recognition of landing area for UAVs.
ISSN:2504-446X
2504-446X
DOI:10.3390/drones6050118