Abstract
The automation of the Wilderness Search and Rescue (WiSAR) task aims for high levels of understanding of various scenery. In addition, working in unfriendly and complex environments may cause a time delay in the operation and consequently put human lives at stake. In order to address this problem, Unmanned Aerial Vehicles (UAVs), which provide potential support to the conventional methods, are used. These vehicles are provided with reliable human detection and tracking algorithms; in order to be able to find and track the bodies of the victims in complex environments, and a robust control system to maintain safe distances from the detected bodies. In this paper, a human detection based on the color and depth data captured from onboard sensors is proposed. Moreover, the proposal of computing data association from the skeleton pose and a visual appearance measurement allows the tracking of multiple people with invariance to the scale, translation and rotation of the point of view with respect to the target objects. The system has been validated with real and simulation experiments, and the obtained results show the ability to track multiple individuals even after long-term disappearances. Furthermore, the simulations present the robustness of the implemented reactive control system as a promising tool for assisting the pilot to perform approaching maneuvers in a safe and smooth manner.
Highlights
Wilderness Search and Rescue (WiSAR) missions place special requirements on small aerial robotic systems since it is the process of finding and assisting individuals who are lost in remote wilderness areas
The advantage in modifying the reference for the position controller is that the feedback loop of the PID controller is exploited to make the Unmanned Aerial Vehicles (UAVs) converge towards the desired stopping distance, where the repulsive velocity computed by the algorithm equals the approach velocity of the UAV
To validate the control presented in this paper, simulation experiments have been carried out, as shown in Figure 11, the proposed control algorithm has been compared with two known strategies; Dynamic Parametric Field (DPF) and Time to Impact (TTI)
Summary
The recent and continuously increasing research in the field of Unmanned Aerial Vehicles (UAVs) has boosted them as suitable platforms for carrying sensors and computer systems in order to perform advanced tasks, such as terrain thematic and topographic mapping [1,2,3]; exploration of unreachable areas like islands [4], rivers [5], forests [6] or oceans [7]; for surveillance purposes [8,9]; for traffic monitoring [10], including the estimation of the traffic flow behavior [11], and traffic speed [12]; and search and rescue operations after disasters [13,14,15]. We propose a detection and multi-object tracking algorithm based on color and depth data streams provided by a low-weight and low-cost sensor, unlike another branch of methods based on thermal technologies [21,22]. The advantage of using local data is that it allows the UAV to adapt to the changing in the environment in a reactive manner in real-time This type of control, that describes the cooperation of autonomous and manual control, is known as Semi-Automatic control. This paper presents a detection and tracking algorithm for rescuing victims in disaster environments using aerial images, aided by a semi-autonomous reactive control, whose main contributions are summarized as follows:.
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
