Fire Area Detection based on Convolutional Neural Network and Improved A∗ Path Planning

Jia Hua Yu, Shin Nyeong Heo, Ji Sun Shin, HeeHyol Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this research, a new fire detection method and a new path planning algorithm are proposed. Traditional fire detection methods are based on fixed RGB models and they are not accurate enough under different circumstances. Traditional A∗ path planning algorithm always focuses on a minimum cost from a start point to an end point, so it is not suitable for complex environment. To solve fire detection problem, we use an object detection algorithm based on a convolutional neural network and trained it with real fire images to detect fire area in an image. For the path planning problem, an improved A∗ algorithm with new weight for different area and box blur method are used to ensure the output path is away from the obstacle. In the end of this paper, we simulate disaster environment in Unity3D and implement two algorithms to measure their performance.

Original languageEnglish
Title of host publication2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728119960
DOIs
Publication statusPublished - 2018 Nov 27
Event2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018 - Busan, Korea, Republic of
Duration: 2018 Sep 62018 Sep 8

Other

Other2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018
CountryKorea, Republic of
CityBusan
Period18/9/618/9/8

Fingerprint

Path Planning
Motion planning
neural network
Fires
Neural Networks
Neural networks
planning
Object Detection
End point
Disaster
Performance Measures
Disasters
disaster
Path
Output
Costs
costs
performance

Keywords

  • Convolution neural network
  • first responder
  • Object detection
  • Path planning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Electrical and Electronic Engineering
  • Control and Optimization
  • Communication

Cite this

Yu, J. H., Nyeong Heo, S., Shin, J. S., & Lee, H. (2018). Fire Area Detection based on Convolutional Neural Network and Improved A∗ Path Planning. In 2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018 [8549908] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICT-ROBOT.2018.8549908

Fire Area Detection based on Convolutional Neural Network and Improved A∗ Path Planning. / Yu, Jia Hua; Nyeong Heo, Shin; Shin, Ji Sun; Lee, HeeHyol.

2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8549908.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yu, JH, Nyeong Heo, S, Shin, JS & Lee, H 2018, Fire Area Detection based on Convolutional Neural Network and Improved A∗ Path Planning. in 2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018., 8549908, Institute of Electrical and Electronics Engineers Inc., 2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018, Busan, Korea, Republic of, 18/9/6. https://doi.org/10.1109/ICT-ROBOT.2018.8549908
Yu JH, Nyeong Heo S, Shin JS, Lee H. Fire Area Detection based on Convolutional Neural Network and Improved A∗ Path Planning. In 2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8549908 https://doi.org/10.1109/ICT-ROBOT.2018.8549908
Yu, Jia Hua ; Nyeong Heo, Shin ; Shin, Ji Sun ; Lee, HeeHyol. / Fire Area Detection based on Convolutional Neural Network and Improved A∗ Path Planning. 2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018. Institute of Electrical and Electronics Engineers Inc., 2018.
@inproceedings{e5467fbf2467491fb309361c321fa7fd,
title = "Fire Area Detection based on Convolutional Neural Network and Improved A∗ Path Planning",
abstract = "In this research, a new fire detection method and a new path planning algorithm are proposed. Traditional fire detection methods are based on fixed RGB models and they are not accurate enough under different circumstances. Traditional A∗ path planning algorithm always focuses on a minimum cost from a start point to an end point, so it is not suitable for complex environment. To solve fire detection problem, we use an object detection algorithm based on a convolutional neural network and trained it with real fire images to detect fire area in an image. For the path planning problem, an improved A∗ algorithm with new weight for different area and box blur method are used to ensure the output path is away from the obstacle. In the end of this paper, we simulate disaster environment in Unity3D and implement two algorithms to measure their performance.",
keywords = "Convolution neural network, first responder, Object detection, Path planning",
author = "Yu, {Jia Hua} and {Nyeong Heo}, Shin and Shin, {Ji Sun} and HeeHyol Lee",
year = "2018",
month = "11",
day = "27",
doi = "10.1109/ICT-ROBOT.2018.8549908",
language = "English",
booktitle = "2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Fire Area Detection based on Convolutional Neural Network and Improved A∗ Path Planning

AU - Yu, Jia Hua

AU - Nyeong Heo, Shin

AU - Shin, Ji Sun

AU - Lee, HeeHyol

PY - 2018/11/27

Y1 - 2018/11/27

N2 - In this research, a new fire detection method and a new path planning algorithm are proposed. Traditional fire detection methods are based on fixed RGB models and they are not accurate enough under different circumstances. Traditional A∗ path planning algorithm always focuses on a minimum cost from a start point to an end point, so it is not suitable for complex environment. To solve fire detection problem, we use an object detection algorithm based on a convolutional neural network and trained it with real fire images to detect fire area in an image. For the path planning problem, an improved A∗ algorithm with new weight for different area and box blur method are used to ensure the output path is away from the obstacle. In the end of this paper, we simulate disaster environment in Unity3D and implement two algorithms to measure their performance.

AB - In this research, a new fire detection method and a new path planning algorithm are proposed. Traditional fire detection methods are based on fixed RGB models and they are not accurate enough under different circumstances. Traditional A∗ path planning algorithm always focuses on a minimum cost from a start point to an end point, so it is not suitable for complex environment. To solve fire detection problem, we use an object detection algorithm based on a convolutional neural network and trained it with real fire images to detect fire area in an image. For the path planning problem, an improved A∗ algorithm with new weight for different area and box blur method are used to ensure the output path is away from the obstacle. In the end of this paper, we simulate disaster environment in Unity3D and implement two algorithms to measure their performance.

KW - Convolution neural network

KW - first responder

KW - Object detection

KW - Path planning

UR - http://www.scopus.com/inward/record.url?scp=85060052037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060052037&partnerID=8YFLogxK

U2 - 10.1109/ICT-ROBOT.2018.8549908

DO - 10.1109/ICT-ROBOT.2018.8549908

M3 - Conference contribution

AN - SCOPUS:85060052037

BT - 2018 International Conference on Information and Communication Technology Robotics, ICT-ROBOT 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -