Abstract-Aircraft tracking plays a key and important role in the Sense-and-Avoid system of Unmanned Aerial Vehicles (UAVs). This paper presents a novel robust visual tracking algorithm for UAVs in the midair to track an arbitrary aircraft at real-time frame rates, together with a unique evaluation system. This visual algorithm mainly consists of adaptive discriminative visual tracking method, Multiple-Instance (MI) learning approach, Multiple-Classifier (MC) voting mechanism and Multiple-Resolution (MR) representation strategy, that is called Adaptive M 3 tracker, i.e. AM 3 . In this tracker, the importance of test sample has been integrated to improve the tracking stability, accuracy and real-time performances. The experimental results show that this algorithm is more robust, efficient and accurate against the existing state-of-art trackers, overcoming the problems generated by the challenging situations such as obvious appearance change, variant surrounding illumination, partial aircraft occlusion, blur motion, rapid pose variation and onboard mechanical vibration, low computation capacity and delayed information communication between UAVs and Ground Station (GS). To our best knowledge, this is the first work to present this tracker for solving online learning and tracking freewill aircraft/intruder in the UAVs.
In this paper, we developed a novel Cross-Entropy Optimization (CEO)-based Fuzzy Logic Controller (FLC) for Fail-Safe UAV to expand its collision avoidance capabilities in the GPS-denied environments using Monocular Visual-Inertial SLAM-based strategy. The function of this FLC aims to control the heading of Fail-Safe UAV to avoid the obstacle, e.g. wall, bridge, tree line et al, using its real-time and accurate localization information. In the Matlab Simulink-based training framework, the Scaling Factor (SF) is adjusted according to the collision avoidance task firstly, and then the Membership Function (MF) is tuned based on the optimized Scaling Factor to further improve the control performances. After obtained the optimal SF and MF, 64 % of rules has been reduced (from 125 rules to 45 rules), and a large number of real see-and-avoid tests with a quadcopter have done. The simulation and experiment results show that this new proposed FLC can precisely navigates the Fail-Safe UAV to avoid the obstacle, obtaining better performances compared to only SF optimization-based FLC. To our best knowledge, this is the first work to present the optimized FLC using Cross-Entropy method in both SF and MF optimization, and apply it in the UAV.
This paper presents a novel robust visual tracking framework, based on discriminative method, for Unmanned Aerial Vehicles (UAVs) to track an arbitrary 2D/3D target at real-time frame rates, that is called the Adaptive Multi-Classifier Multi-Resolution (AMCMR) framework. In this framework, adaptive Multiple Classifiers (MC) are updated in the (k-1)th frame-based Multiple Resolutions (MR) structure with compressed positive and negative samples, and then applied them in the kth frame-based Multiple Resolutions (MR) structure to detect the current target. The sample importance has been integrated into this framework to improve the tracking stability and accuracy. The performance of this framework was evaluated with the Ground Truth (GT) in different types of public image databases and real flightbased aerial image datasets firstly, then the framework has been applied in the UAV to inspect the Offshore Floating Platform (OFP). The evaluation and application results show that this framework is more robust, efficient and accurate against the existing state-of-art trackers, overcoming the problems generated by the challenging situations such as obvious appearance change, variant illumination, partial/full target occlusion, blur motion, rapid pose variation and onboard mechanical vibration, among others. To our best knowledge, this is the first work to present this framework for solving the online learning and tracking freewill 2D/3D target problems, and applied it in the UAVs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.