Fire Flame Detection in Tunnel Based on Halcon and ResNet50: Fid-Bau Portal

Fachinformationsdienst BAUdigital

A platform for research: civil engineering, architecture and urbanism

Fire Flame Detection in Tunnel Based on Halcon and ResNet50

Jia, Fengyuan

Fires in tunnels have the problem of difficult detection and rescue. Thus, fire monitoring is crucial for prompt discovery of fires. Aiming at the problems of high false detection rate of traditional tunnel fire detection methods, a flame detection method based on Halcon and ResNet50 is designed. Gamma decoding is used for image preprocessing. The gamma decoding reduces the details of the dark part in the image and highlights the flame part. With the help of ResNet50 network, the flame after pretreatment is detected. The experimental result shows that the method has high recall and precision. This method provides an important reference value for the design of tunnel fire monitoring system.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Fire Flame Detection in Tunnel Based on Halcon and ResNet50

Jia, Fengyuan

Fires in tunnels have the problem of difficult detection and rescue. Thus, fire monitoring is crucial for prompt discovery of fires. Aiming at the problems of high false detection rate of traditional tunnel fire detection methods, a flame detection method based on Halcon and ResNet50 is designed. Gamma decoding is used for image preprocessing. The gamma decoding reduces the details of the dark part in the image and highlights the flame part. With the help of ResNet50 network, the flame after pretreatment is detected. The experimental result shows that the method has high recall and precision. This method provides an important reference value for the design of tunnel fire monitoring system.

Fire Flame Detection in Tunnel Based on Halcon and ResNet50

Jia, Fengyuan

Fires in tunnels have the problem of difficult detection and rescue. Thus, fire monitoring is crucial for prompt discovery of fires. Aiming at the problems of high false detection rate of traditional tunnel fire detection methods, a flame detection method based on Halcon and ResNet50 is designed. Gamma decoding is used for image preprocessing. The gamma decoding reduces the details of the dark part in the image and highlights the flame part. With the help of ResNet50 network, the flame after pretreatment is detected. The experimental result shows that the method has high recall and precision. This method provides an important reference value for the design of tunnel fire monitoring system.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Document information

Title:

Fire Flame Detection in Tunnel Based on Halcon and ResNet50

Contributors:

Jia, Fengyuan (author)

Published in:

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) ; 256-259

Publication date:

2023-02-24

Size:

479592 byte

ISBN:

979-8-3503-3597-2

DOI:

https://doi.org/10.1109/NNICE58320.2023.10105717

Type of media:

Conference paper

Type of material:

Electronic Resource

Language:

English

Similar titles

Titel+Thema Spanien - Halcon Cerámicas: Europa im Hinterkopf

Online Contents | 2003

ResNet50-1D-CNN: A new lightweight resNet50-One-dimensional convolution neural network transfer learning-based approach for improved intrusion detection in cyber-physical systems

Saheed, Yakub Kayode / Abdulganiyu, Oluwadamilare Harazeem / Majikumna, Kaloma Usman et al. | Elsevier | 2024

Pneumonia Detection in Chest X-ray Images using ResNet50 Model

Barneih, Feras / Nasir, Nida / Kansal, Afreen et al. | IEEE | 2023

A Study on the Inspection Technology of the Electrode Defects of Li-Ion Power Battery Based on HALCON

Han, L. / Liu, Y.M. / He, D.Y. et al. | British Library Conference Proceedings | 2014

Gradient Propagation Based DenseNet121 with ResNet50 Feature Extraction for Lymphoma Classification

Srinivasan, Deepthi / Kalaiarasan, C. | Springer Verlag | 2024