Neural network learning to identify airport runway taxiway numbers

Zhi Ha Chen, Jyh Ching Juang

研究成果: Conference contribution

摘要

In order to reduce the number of 'Runway Incursion' crashes, the process and method of the study is to simulate human visual neuron recognition pictures and train a machine learning model. The results are modeled as follows:1. The neural network outputs the feature vectors model after the Convolution operation. 2. Filter is used to detect the pixels of the background image of the airport environment. The feature map is output with Activated feature map. The same weight of the same feature object is added with Max pooling layer after convolution layer to find the feature map more obvious. We can use Deep Learning to simulate the Artificial Intelligence model environment instead of manual recognition, simulate Drone to recognize the runway number automatically and drive into the tower path planning runway area correctly. Specific images such as runway numbers, area locations, etc., provide an unexpectedly increased opportunity to resolve the 'Runway Incursion' case.

原文English
主出版物標題Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018
發行者Institute of Electrical and Electronics Engineers Inc.
頁面153-157
頁數5
ISBN(電子)9781538670361
DOIs
出版狀態Published - 2019 二月 19
事件4th International Symposium on Computer, Consumer and Control, IS3C 2018 - Taichung, Taiwan
持續時間: 2018 十二月 62018 十二月 8

出版系列

名字Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018

Conference

Conference4th International Symposium on Computer, Consumer and Control, IS3C 2018
國家Taiwan
城市Taichung
期間18-12-0618-12-08

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Control and Systems Engineering
  • Energy Engineering and Power Technology
  • Computer Science Applications
  • Control and Optimization
  • Signal Processing

指紋 深入研究「Neural network learning to identify airport runway taxiway numbers」主題。共同形成了獨特的指紋。

引用此