Correction: Aircraft Detection using Deep Convolutional Neural Network in Small Unmanned Aircraft Systems

2018 ◽  
Author(s):  
Sunyou Hwang ◽  
Jaehyun Lee ◽  
Heemin Shin ◽  
Sungwook Cho ◽  
David Hyunchul Shim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Unmanned Aircraft ◽  
Deep Convolutional Neural Network ◽  
Unmanned Aircraft Systems ◽  
Aircraft Systems ◽  
Aircraft Detection

scholarly journals Construction of an advanced method for recognizing monitored objects by a convolutional neural network using a discrete wavelet transform

2021 ◽  
Vol 4 (9(112)) ◽  
pp. 65-77
Author(s):  
Vadym Slyusar ◽  
Mykhailo Protsenko ◽  
Anton Chernukha ◽  
Stella Gornostal ◽  
Sergey Rudakov ◽  
...  
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Convolutional Neural Network ◽  
Discrete Wavelet Transform ◽  
Unmanned Aircraft ◽  
Unmanned Aircraft Systems ◽  
Discrete Wavelet ◽  
Surveillance Systems ◽  
Improved Method ◽  
Aircraft Systems

The tasks that unmanned aircraft systems solve include the detection of objects and determining their state. This paper reports an analysis of image recognition methods in order to automate the specified process. Based on the analysis, an improved method for recognizing images of monitored objects by a convolutional neural network using a discrete wavelet transform has been devised. Underlying the method is the task of automating image processing in unmanned aircraft systems. The operability of the proposed method was tested using an example of processing an image (aircraft, tanks, helicopters) acquired by the optical system of an unmanned aerial vehicle. A discrete wavelet transform has been used to build a database of objects' wavelet images and train a convolutional neural network based on them. That has made it possible to improve the efficiency of recognition of monitored objects and automate a given process. The effectiveness of the improved method is achieved by preliminary decomposition and approximation of the digital image of the monitored object by a discrete wavelet transform. The stages of a given method include the construction of a database of the wavelet images of images and training a convolutional neural network. The effectiveness of recognizing the monitored objects' images by the improved method was tested on a convolutional neural network, which was trained with images of 300 monitored objects. In this case, the time to make a decision, based on the proposed method, decreased on average from 0.7 to 0.84 s compared with the artificial neural networks ResNet and ConvNets. The method could be used in the information processing systems in unmanned aerial vehicles that monitor objects; in robotic complexes for various purposes; in the video surveillance systems of important objects

scholarly journals Use of Unmanned Aircraft Systems for Bridge Inspection: A Review

DYNA ◽  
2021 ◽  
Vol 88 (217) ◽  
pp. 32-41
Author(s):  
Didier Aldana Rodriguez ◽  
Diego Leonardo Ávila Granados ◽  
Jorge Armando Villalba-Vidales
Keyword(s):  
Neural Network ◽  
Health Monitoring ◽  
Structure From Motion ◽  
Unmanned Aircraft ◽  
Unmanned Aircraft Systems ◽  
Bridge Inspection ◽  
Aircraft Systems ◽  
Future Challenges ◽  
Levels Of Automation ◽  
Different Levels

This review describes the use of Unmanned Aircraft Systems (UAS) for bridge inspection, with an emphasis on Multi-rotor UAS. It depicts the different levels of automation and autonomy during UAS operation and what levels are achieved during inspections. A description of the payload of UAS consisting of the equipment required to acquire data and images is included. It also contains a compendium of the techniques used to create models from images in order to detect failures and perform Structural Health Monitoring (SHM) through techniques, such as: 3D reconstruction, infrared thermography, Structure From Motion (SFM), Convolutional Neural Network (CNN) and others. The software required to apply the mentioned techniques is also mentioned. It subsequently explains the generation of mathematical models to characterize the multirotor and generate efficient trajectories. Finally, the review concludes by describing the operational limitations of UAS and future challenges.

Sign in / Sign up

Export Citation Format

Share Document