by Xin, C, Nguyen, M and Yan, W-Q
Abstract:
Identifying fire flames is based on object recognition which has valuable applications in intelligent surveillance. The focus of this book chapter is on flame recognition using deep learning and its evaluations. For achieving this goal, we design a Multi-Flame Detection scheme (MFD) which utilises Convolutional Neural Networks (CNNs). We take use of TensorFlow in deep learning with an NVIDIA GPU to train an image dataset and constructed a model for flame recognition. The contributions of this book chapter are: (1) data augmentation for flame recognition, (2) model construction for deep learning, and (3) result evaluations for flame recognition using deep learning.
Reference:
Multiple flames recognition using deep learning (Xin, C, Nguyen, M and Yan, W-Q), Chapter in Handbook of research on multimedia cyber security (Gupta, B, Gupta, D, eds.), IGI Global, 2020.
Bibtex Entry:
@incollection{xin2020multiplelearning,
author = {Xin, C and Nguyen, M and Yan, W-Q},
booktitle = {Handbook of research on multimedia cyber security},
editor = {Gupta, B and Gupta, D},
number = {15},
pages = {296--307},
publisher = {IGI Global},
school = {USA},
title = {Multiple flames recognition using deep learning},
url = {https://www.igi-global.com/book/handbook-research-multimedia-cyber-security/237827},
year = {2020},
abstract = {Identifying fire flames is based on object recognition which has valuable applications in intelligent surveillance. The focus of this book chapter is on flame recognition using deep learning and its evaluations. For achieving this goal, we design a Multi-Flame Detection scheme (MFD) which utilises Convolutional Neural Networks (CNNs). We take use of TensorFlow in deep learning with an NVIDIA GPU to train an image dataset and constructed a model for flame recognition. The contributions of this book chapter are: (1) data augmentation for flame recognition, (2) model construction for deep learning, and (3) result evaluations for flame recognition using deep learning.},
doi = {10.4018/978-1-7998-2701-6.ch015},
isbn = {1799827011},
isbn = {9781799827016},
}