In this study, reducing motion blur in images taken by our unmanned aerial vehicle is investigated. Since shakes of unmanned aerial vehicle cause motion blur in taken images, autonomous performance of our unmanned aerial vehicle is maximized to prevent it from shakes. In order to maximize autonomous performance of unmanned aerial vehicle (i.e. to reduce motion blur), initially, camera mounted unmanned aerial vehicle dynamics are obtained. Then, optimum location of unmanned aerial vehicle camera is estimated by considering unmanned aerial vehicle dynamics and autopilot parameters. After improving unmanned aerial vehicle by optimum camera location, dynamics and controller parameters, it is called as improved autonomous controlled unmanned aerial vehicle. Also, unmanned aerial vehicle with camera fixed at the closest point to center of gravity is called as standard autonomous controlled unmanned aerial vehicle. Both improved autonomous controlled and standard autonomous controlled unmanned aerial vehicles are performed in real time flights, and approximately same trajectories are tracked. In order to compare performance of improved autonomous controlled and standard autonomous controlled unmanned aerial vehicles in reducing motion blur, a motion blur kernel model which is derived using recorded roll, pitch and yaw angles of unmanned aerial vehicle is improved. Finally, taken images are simulated to examine effect of unmanned aerial vehicle shakes. In comparison with standard autonomous controlled flight, important improvements on reducing motion blur are demonstrated by improved autonomous controlled unmanned aerial vehicle.
Purpose The aim of this paper is to redesign of morphing unmanned aerial vehicle (UAV) using neural network for simultaneous improvement of roll stability coefficient and maximum lift/drag ratio. Design/methodology/approach Redesign of a morphing our UAV manufactured in Faculty of Aeronautics and Astronautics, Erciyes University is performed with using artificial intelligence techniques. For this purpose, an objective function based on artificial neural network (ANN) is obtained to get optimum values of roll stability coefficient (Clβ) and maximum lift/drag ratio (Emax). The aim here is to save time and obtain satisfactory errors in the optimization process in which the ANN trained with the selected data is used as the objective function. First, dihedral angle (φ) and taper ratio (λ) are selected as input parameters, C*lβ and Emax are selected as output parameters for ANN. Then, ANN is trained with selected input and output data sets. Training of the ANN is possible by adjusting ANN weights. Here, ANN weights are adjusted with artificial bee colony (ABC) algorithm. After adjusting process, the objective function based on ANN is optimized with ABC algorithm to get better Clβ and Emax, i.e. the ABC algorithm is used for two different purposes. Findings By using artificial intelligence methods for redesigning of morphing UAV, the objective function consisting of C*lβ and Emax is maximized. Research limitations/implications It takes quite a long time for Emax data to be obtained realistically by using the computational fluid dynamics approach. Practical implications Neural network incorporation with the optimization method idea is beneficial for improving Clβ and Emax. By using this approach, low cost, time saving and practicality in applications are achieved. Social implications This method based on artificial intelligence methods can be useful for better aircraft design and production. Originality/value It is creating a novel method in order to redesign of morphing UAV and improving UAV performance.
In this paper, a hybrid method which combines homothetic multi-hypothesis tracker (HPMHT) and artificial neural networks (ANNs) is presented to solve multiple target tracking problem. The performances of the proposed neural network aided homothetic multi-hypothesis tracker (NNAHPMHT) and the HPMHT are compared for two different test scenarios. It was observed that the estimation performances obtained from the NNAHPMHT are better than those obtained from only the HPMHT. The NNAHPMHT method doesn't require additional complex modeling for tracking multiple targets. The additional implementation time originated from NNAHPMHT is only recall time of the ANN. For this reason, the proposed method is very suitable for realtime implementation.
Purpose The purpose of this paper is to examine the success of constrained control on reducing motion blur which occurs as a result of helicopter vibration. Design/methodology/approach Constrained controllers are designed to reduce the motion blur on images taken by helicopter. Helicopter vibrations under tight and soft constrained controllers are modeled and added to images to show the performance of controllers on reducing blur. Findings The blur caused by vibration can be reduced via constrained control of helicopter. Research limitations/implications The motion of camera is modeled and assumed same as the motion of helicopter. In model of exposing image, image noise is neglected, and blur is considered as the only distorting effect on image. Practical implications Tighter constrained controllers can be implemented to take higher quality images by helicopters. Social implications Recently, aerial vehicles are widely used for aerial photography. Images taken by helicopters mostly suffer from motion blur. Reducing motion blur can provide users to take higher quality images by helicopters. Originality/value Helicopter control is performed to reduce motion blur on image for the first time. A control-oriented and physic-based model of helicopter is benefited. Helicopter vibration which causes motion blur is modeled as blur kernel to see the effect of helicopter vibration on taken images. Tight and soft constrained controllers are designed and compared to denote their performance in reducing motion blur. It is proved that images taken by helicopter can be prevented from motion blur by controlling helicopter tightly.
Özetçe-Bu çalışmada, çocuklarda el bileği radyografik görüntülerinden kemik yaşını tayin etmek için yeni bir yaklaşım ve yapay sinir ağları (YSA) kullanılarak otomatik bir sistem geliştirilmiştir. Kemik yaşı tayini için el bileği kemiklerinden sadece dirsek ve ön kol kemiği ile bunların epifizleri kullanılmıştır. Bu yöntem ve YSA ile geliştirilen sistem sayesinde bir uzmana, kullanılan görüntülerin kaliteli olmasına, belirli bir standart açı ve uzaklıktan çekilmesine ihtiyaç duyulmadığından yaş tayini, doğru ve hızlı bir şekilde yapılabilmektedir. Tasarlanan sistem farklı yaşlarda olan ve daha önce iki uzman tarafından kemik yaşı tayin edilmiş 32 el bileği görüntüsü üzerinde denenmiş ve kemik yaşını 0.52 yıl ortalama hata ile tahmin etmiştir. Anahtar Kelimeler -kemik yaşı tayini; dirsek ve ön kol kemiği epifizi; yapay sinir ağları.Abstract-In this study, an automated system using a novel method and artificial neural networks (ANN) to assess bone age of children from hand radiographs is proposed. Bone age is estimated accurately by utilizing distal radius, ulna and their epiphysis for skeletal maturity assessment. With the system designed using the method and ANN, bone age assessment become possible without any guidance of radiologists and applicable in a very short time. Not only sharp and high quality radiographs but also degraded ones can be used for skeletal maturation assessment in this system. Moreover, the system is not required the radiographs exposed in any exact standard, angle or distance. The proposed system is tested with 32 hand radiographs of various ages which are assessed by two radiologists. As a result, bone ages are assessed mean error of 0.52 year by the system. Keywords -bone age assessment; epiphysis of radius and ulna; artificial neural networks.
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.