Remote Marker-Based Tracking for UAV Landing Using Visible-Light Camera Sensor

Abstract

Unmanned aerial vehicles (UAVs), which are commonly known as drones, have proved to be useful not only on the battlefields where manned flight is considered too risky or difficult, but also in everyday life purposes such as surveillance, monitoring, rescue, unmanned cargo, aerial video, and photography. More advanced drones make use of global positioning system (GPS) receivers during the navigation and control loop which allows for smart GPS features of drone navigation. However, there are problems if the drones operate in heterogeneous areas with no GPS signal, so it is important to perform research into the development of UAVs with autonomous navigation and landing guidance using computer vision. In this research, we determined how to safely land a drone in the absence of GPS signals using our remote maker-based tracking algorithm based on the visible light camera sensor. The proposed method uses a unique marker designed as a tracking target during landing procedures. Experimental results show that our method significantly outperforms state-of-the-art object trackers in terms of both accuracy and processing time, and we perform test on an embedded system in various environments.

LightDenseYOLO: A Fast and Accurate Marker Tracker for Autonomous UAV Landing by Visible Light Camera Sensor on Drone

“…The size of our marker is 1 m ×1 m [ 3 ]. In this study, we solve the problem of autonomous drone landing by proposing a long-distance marker-based tracking algorithm using the same marker.…”

“…Our previous work attempted to solve the problem of autonomous drone landing by using hand-crafted features extracted by a remote-marker-based tracking algorithm using a single visible light camera, and we successfully tracked a marker at a height of 10 m [ 3 ]. However, it is difficult to be apply when a drone is higher than 10 m because of the low resolution of the marker in the drone camera image which is often the case with drone landing.…”

UAV Landing Using Computer Vision Techniques for Human Detection

“…Nguyen et al based their work on the poor experiences with the Amazon delivery service [33], proposing a new approach using markers to detect the landing site, without needing location systems. The onboard computer detects in real time the presence of a marker in different day times: morning, afternoon, evening, and night.…”

Augmenting GPS with Geolocated Fiducials to Improve Accuracy for Mobile Robot Applications

“…Fiducials have previously been used in GPS-denied environments to augment odometry and inertial navigation systems (INS) to facilitate more accurate navigation through association with a ground-truth [17][18][19]. In contrast, we propose to use fiducials regions in non-GPS denied environments to improve GPS accuracy by reducing errors associated with time-variant variables for a short period of time.…”