TY - GEN
T1 - Neural network learning to identify airport runway taxiway numbers
AU - Chen, Zhi Ha
AU - Juang, Jyh Ching
N1 - Funding Information:
ACKNOWLEDGMENT This paper is supported by the Ministry of Science and Technology (MOST), Taiwan, under grant MOST 105-2221-E-006-106-MY3.
Publisher Copyright:
© 2018 IEEE.
PY - 2019/2/19
Y1 - 2019/2/19
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85063239519&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063239519&partnerID=8YFLogxK
U2 - 10.1109/IS3C.2018.00046
DO - 10.1109/IS3C.2018.00046
M3 - Conference contribution
AN - SCOPUS:85063239519
T3 - Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018
SP - 153
EP - 157
BT - Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Symposium on Computer, Consumer and Control, IS3C 2018
Y2 - 6 December 2018 through 8 December 2018
ER -