LightDenseYOLO: A Fast and Accurate Marker Tracker for Autonomous UAV Landing by Visible Light Camera Sensor on Drone
Autonomous landing of an unmanned aerial vehicle or a drone is a challenging problem for the robotics research community. Previous researchers have attempted to solve this problem by combining multiple sensors such as global positioning system (GPS) receivers, inertial measurement unit, and multiple camera systems. Although these approaches successfully estimate an unmanned aerial vehicle location during landing, many calibration processes are required to achieve good detection accuracy. In addition, cases where drones operate in heterogeneous areas with no GPS signal should be considered. To overcome these problems, the authors determined how to safely land a drone in a GPS-denied environment using the authors' remote-marker-based tracking algorithm based on a single visible-light-camera sensor. Instead of using hand-crafted features, the authors' algorithm includes a convolutional neural network named lightDenseYOLO to extract trained features from an input image to predict a marker’s location by visible light camera sensor on drone. Experimental results show that the authors' method significantly outperforms state-of-the-art object trackers both using and not using convolutional neural network in terms of both accuracy and processing time.
- Record URL:
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/14248220
-
Supplemental Notes:
- © 2018 Boyuan Wang et al.
-
Authors:
- Nguyen, Phong
- Arsalan, Muhammad
- Koo, Ja
- Naqvi, Rizwan
- Truong, Noi Quang
- Park, Kang Ryoung
- Publication Date: 2018-6
Language
- English
Media Info
- Media Type: Web
- Features: Figures; References; Tables;
- Pagination: 30p
-
Serial:
- Sensors
- Volume: 18
- Issue Number: 6
- Publisher: MDPI AG
- ISSN: 1424-8220
- Serial URL: http://www.mdpi.com/journal/sensors
-
Publication flags:
Open Access (libre)
Subject/Index Terms
- TRT Terms: Cameras; Drones; Landing; Landing aids; Neural networks; Sensors
- Identifier Terms: LightDenseYOLO
- Subject Areas: Aviation; Data and Information Technology;
Filing Info
- Accession Number: 01676330
- Record Type: Publication
- Files: TRIS
- Created Date: Jul 26 2018 2:38PM