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.
Highlights
The global market for unmanned aerial vehicles (UAVs) has grown dramatically in recent years along with rapid development of new applications [1]
From the 2nd input image, we do not perform template matching for the whole image but in a small region of interest (ROI), The size of the ROI is (w + m) × (h + m) where m is a margin that we empirically considered and we created a new template with the same size (w × h) as the original template
From the 2nd input image,2017, we 17, do1987 not perform template matching for the whole image but in a small region of interest Sensors (ROI), The size of the ROI is (w + m) × (h + m) where m is a margin that we empirically considered large enough to ensure that the marker appears inside the selected ROI
Summary
The global market for unmanned aerial vehicles (UAVs) has grown dramatically in recent years along with rapid development of new applications [1]. Typical UAVs are controlled by humans, and experience is required as the UAV still haves low control accuracy. The mission path of autonomous UAVs requires them to fly at low speed while following a path or to track an object of interest, and to perform a series of actions. In order to address a broader range of applications, one has to migrate to integrated processing add-ons that would carry out on demand, on-board, collaborative or autonomous functions, with the aim of realizing an intelligent UAV functionality. With the increase in the computational potential of UAVs, previous studies do address computationally demanding tasks, but have adopted the UAVs into autonomous system that can take control of its own flight and perform optimized missions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
