Abstract
In this paper, a study and evaluation of the combination of GPS/GNSS techniques and advanced image processing algorithms for distressed human detection, positioning and tracking, from a fully autonomous Unmanned Aerial Vehicle (UAV)-based rescue support system, are presented. In particular, the issue of human detection both on terrestrial and marine environment under several illumination and background conditions, as the human silhouette in water differs significantly from a terrestrial one, is addressed. A robust approach, including an adaptive distressed human detection algorithm running every N input image frames combined with a much faster tracking algorithm, is proposed. Real time or near-real-time distressed human detection rates achieved, using a single, low cost day/night NIR camera mounted onboard a fully autonomous UAV for Search and Rescue (SAR) operations. Moreover, the generation of our own dataset, for the image processing algorithms training is also presented. Details about both hardware and software configuration as well as the assessment of the proposed approach performance are fully discussed. Last, a comparison of the proposed approach to other human detection methods used in the literature is presented.
Highlights
Aerial image-based object detection is a very active research topic within the field of computer vision owed to the florescence of Unmanned Aerial Vehicle (UAV) technology
Recent research emphasize on the suitability of deep learning techniques adoption for assisting Search and Rescue (SAR) missions supported by UAVs [21] [22]
The combination of UAVs technologies, GPS/GNSS techniques and advanced image processing algorithms based on Convolutional Neural Networks (CNNs) for the instantaneous provision of life-saving services to distressed humans has been integrated and evaluated
Summary
In order to avoid the bright object’s saturation in the captured image, the artificial lighting power has to be adaptively adjusted in case the object is closer than 20 m This is automatically done in most commercially available cameras. Recent research emphasize on the suitability of deep learning techniques adoption for assisting SAR missions supported by UAVs [21] [22] Such approaches involve autonomous navigation of aerial vehicles [23], exploration of various unknown cluttered environments [24] or rescue missions conduction in indoor environments for human presence recognition [25]. The novelty of this research banks on the implementation and the evaluation of GPS/GNSS techniques combined with advanced image processing algorithms for the enhancement of SAR missions’ efficacy in both coastal and marine environments under several illumination conditions using a day/night low cost vision/IR.
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
