Login / Register Submit Your Article
cover
Journal of Globe Scientific Reports

Volume 6, 2024 - Issue 3

Submit Manuscript Journal Homepage
Latest Issue
Input keywords, title, abstract, author, affiliation etc..
Article Menu
Browse this journal
Vol. 7 (2025)
Vol. 6 (2024)
Vol. 5 (2023)
Vol. 4 (2022)
Vol. 3 (2021)
Vol. 2 (2020)
Vol. 1 (2019)
Recommend Papers
Current Challenges and Strategies for EU Immigration Policy
Case Study: Predicting Academic Success in Business English through Learning Behavior and Psychological Support Analysis with Machine Learning
Deep Learning and Computational Mathematics in Crisis Detection for International Students
Utilizing Fuzzy Neural Networks for Accurate English Grade Forecasting
Attention Mechanism-Enhanced Imaging Techniques for Brain Tumor Classification
Journal Article An open access journal
Journal Article

High-Resolution Fire Image Generation via SCGAN-Controlled Methods and Optimized DDPM Models

by Lanyan Yang 1 ,  Yuanhang Cheng 1,* ,  Fang Xu 2,3 ,  Boning Li 2,3,4  and  Xiaoxu Li 2,3,4
1
School of Information Engineering, Shenyang University, Liaoning Shenyang 110044, China
2
Shenyang Fire Research Institute of M.E.M., Shenyang Liaoning 110034, China
3
National Engineering Research Center of Fire and Emergency Rescue., Shenyang Liaoning 110034, China
4
Key Laboratory of Fire Prevention Technology, Liaoning Provincial., Shenyang Liaoning 110034, China
*
Author to whom correspondence should be addressed.
JGSR  2024 6(3):113; https://doi.org/10.69610/j.gsr.202408314
Received: / Accepted: / Published Online: 31 August 2024
View Full-Text
Download PDF

Abstract

Existing deep learning-based image fire detection algorithms require training the model with a large number of diverse image datasets and accurate annotations to achieve high accuracy and strong anti-interference capabilities. However, in the field of fire detection, there is a lack of sufficiently rich datasets of real fire scenes to train the detection models, leading to unreliable detection results. In this paper, we propose a new flame image generation method that aims to enhance the efficiency and adaptability of fire detection systems, particularly when the number of samples is unbalanced. By constructing extensive datasets containing different environments (e.g., factories, warehouses, and forests), we address the practical challenges of safety control and fire initiation.

Our approach is based on two main networks: the flame generation network and the hybrid network. The flame generation network utilizes the SCGAN technique to generate diverse flame images by controlling the shape of  flames based on the input reference information. The hybrid network synthesizes fire images from different scenes into an improved DDPM to create realistic images by fine-tuning textures and styles. Our approach has three main advantages: the ability to control the generated flame images, the preservation of high-quality background details, and training on real datasets, making the generated images suitable for engineering application scenarios.

Keywords: Generative adversarial network; ; DDPM Models; Image blending; Image synthesis;
Copyright: © 2024 by Yang, Cheng, Xu, Li and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (Creative Commons Attribution 4.0 International License). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
Show Figures

Share and Cite

ACS Style
Yang, L.; Cheng, Y.; Xu, F.; Li, B.; Li, X. High-Resolution Fire Image Generation via SCGAN-Controlled Methods and Optimized DDPM Models. Journal of Globe Scientific Reports, 2024, 6, 113. doi:10.69610/j.gsr.202408314
AMA Style
Yang L, Cheng Y, Xu F et al.. High-Resolution Fire Image Generation via SCGAN-Controlled Methods and Optimized DDPM Models. Journal of Globe Scientific Reports; 2024, 6(3):113. doi:10.69610/j.gsr.202408314
Chicago/Turabian Style
Yang, Lanyan; Cheng, Yuanhang; Xu, Fang; Li, Boning; Li, Xiaoxu 2024. "High-Resolution Fire Image Generation via SCGAN-Controlled Methods and Optimized DDPM Models" Journal of Globe Scientific Reports 6, no.3:113. doi:10.69610/j.gsr.202408314

Article Metrics

Article Access Statistics

References

  1. Mahmoud Afifi, Marcus A Brubaker, and Michael S Brown. Histogan: Controlling colors of gan-generated and real images via color histograms. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7941–7950, 2021.
  2. Grigory Antipov, Moez Baccouche, and Jean-Luc Dugelay. Face aging with conditional generative adversarial networks. In 2017 IEEE international conference on image processing (ICIP), pages 2089–2093. IEEE, 2017.
  3. Martin Arjovsky, Soumith Chintala, and Léon Bottou. Wasserstein generative adversarial networks. In International conference on machine learning, pages 214–223. PMLR, 2017.
  4. Yochai Blau, Roey Mechrez, Radu Timofte, Tomer Michaeli, and Lihi Zelnik-Manor. Pirm challenge on perceptual image super-resolution (2018), 2018.
  5. Arantxa Casanova, Marlene Careil, Jakob Verbeek, Michal Drozdzal, and Adriana Romero Soriano. Instance-conditioned gan. Advances in Neural Information Processing Systems, 34:27517–27529, 2021.
  6. Yunjey Choi, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8789–8797, 2018.
  7. Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, and Mubarak Shah. Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  8. Brian Dolhansky and Cristian Canton Ferrer. Eye in-painting with exemplar generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7902–7911, 2018.
  9. Jeff Donahue, Philipp Krähenbühl, and Trevor Darrell. Adversarial feature learning. arXiv preprint arXiv:1605.09782, 2016.
  10. Alexei A Efros and Thomas K Leung. Texture synthesis by non-parametric sampling. In Proceedings of the seventh IEEE international conference on computer vision, volume 2, pages 1033–1038. IEEE, 1999.
  11. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning. MIT press, 2016.
  12. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial networks. Communications of the ACM, 63(11):139–144, 2020.
  13. Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020.
  14. A Ignatov, N Kobyshev, R Timofte, K Vanhoey, and L Wespe Van Gool. Weakly supervised photo enhancer for digital cameras. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 691–700.
  15. Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196, 2017.
  16. Tero Karras, Samuli Laine, and Timo Aila. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4401–4410, 2019.
  17. Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  18. Christian Ledig, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, et al. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4681–4690, 2017.
  19. Jianxin Lin, Yingce Xia, Tao Qin, Zhibo Chen, and Tie-Yan Liu. Conditional image-to-image translation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5524–5532, 2018.
  20. Mehdi Mirza and Simon Osindero. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014.
  21. Zhaoqing Pan, Weijie Yu, Xiaokai Yi, Asifullah Khan, Feng Yuan, and Yuhui Zheng. Recent progress on generative adversarial networks (gans): A survey. IEEE access, 7:36322–36333, 2019.
  22. Alec Radford, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015.
  23. Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. Hierarchical text-conditional image generation with clip latents. arxiv 2022. arXiv preprint arXiv:2204.06125, 2022.
  24. Zhixin Shu, Ersin Yumer, Sunil Hadap, Kalyan Sunkavalli, Eli Shechtman, and Dimitris Samaras. Neural face editing with intrinsic image disentangling. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5541–5550, 2017.
  25. Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, pages 2256–2265. PMLR, 2015.
  26. Yang Song and Stefano Ermon. Improved techniques for training score-based generative models. Advances in neural information processing systems, 33:12438–12448, 2020.
  27. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018.
  28. Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017.
  29. Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017.
  30. Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A Efros, Oliver Wang, and Eli Shechtman. Toward multimodal image-to-image translation. Advances in neural information processing systems, 30, 2017.
  31. Song Chun Zhu, Ying Nian Wu, and David Mumford. Minimax entropy principle and its application to texture modeling. Neural computation, 9(8):1627–1660, 1997.