Below Horizon Aircraft Detection Using Deep Learning for Vision-Based Sense and Avoid

Abstract

Commercial operation of unmanned aerial vehicles (UAVs) would benefit from an onboard ability to sense and avoid (SAA) potential mid-air collision threats. In this paper we present a new approach for detection of aircraft below the horizon. We address some of the challenges faced by existing vision-based SAA methods such as detecting stationary aircraft (that have no relative motion to the background), rejecting moving ground vehicles, and simultaneous detection of multiple aircraft. We propose a multi-stage, vision-based aircraft detection system which utilises deep learning to produce candidate aircraft that we track over time. We evaluate the performance of our proposed system on real flight data where we demonstrate detection ranges comparable to the state of the art with the additional capability of detecting stationary aircraft, rejecting moving ground vehicles, and tracking multiple aircraft.The authors are with the

Well-Known brands recognition by automated classifiers using local and global features

“…Some researchers [24] - [25] also reported that image classification-using bag of features and SVM as a classifier could significantly improve the accuracy of classification, as used in [26] to detect review spam on the labeled dataset of social media. Other recommend also categorizing the scenes like in Aircraft detection [27] - [28]. The texture characteristics and Gabor filtering method are used to reduce detection processing and computational complexity while refining detection effectiveness by 90%.…”

Automatic Detection of Wrecked Airplanes from UAV Images

“…Based on our knowledge, similar detection only for locating airplanes, not the wreckages. Detecting multiple airplanes has been proposed by the work [13], a deep learning algorithm has been proposed detecting airplanes below the horizon with the feature able to reject moving vehicles. Images below the horizon also can have a highly cluttered background that makes detection nontrivial.…”

Self-Checking Deep Neural Networks for Anomalies and Adversaries in Deployment

“…Deep Neural Networks (DNNs) have achieved high performance across many domains, such as speech processing [1], image classification [2], medical diagnostics [3], and social media [4]. DNNs have been deployed to support many mission-critical applications, including malware detection [5], aircraft detection systems [6] and autonomous vehicles [7]. There are increasing concerns about the generality of deep learning models, i.e., their limited performance on unseen samples beyond the training dataset.…”