Impact of Colour Space Transformation on Smoke Detection Accuracy using RESNET50

Mohannad Taha; Mohamed Safaa

doi:10.51173/ijds.v2i1.15

Authors

Mohannad T. Mohammed Middle Technical University https://orcid.org/0000-0001-9021-1466
Mohamed Safaa Shubber Middle Technical University https://orcid.org/0009-0006-7931-6375

DOI:

https://doi.org/10.51173/ijds.v2i1.15

Keywords:

Color Space Conversion, Convolutional Neural Networks, Deep Learning, Early Fire Prevention, Smoke Detection

Abstract

Detecting smoke that precedes fire is a vital matter since it will detect fire incidents in a very early stage since these incidents have very high catastrophic effects on people's lives as well as industrial matters. In order to produce a more reliable detection system, in this article, we dove deeper to examine the effect of colour conversion of the captured footage to enhance the detection percentage using a pre-trained CNN model (ResNet50) that was altered to do a binary classification and was trained on a dataset that consists of smoke and non-smoke scenario images. We examined the system using the footage's original status (RGB) and also tested four colour spaces (HSV, YCbCr, LAB, and grayscale). The testing results showed that HSV had the highest accuracy of 92.1% and the lowest errors during training and testing. Regarding accuracy, the order after HSV was RGB, YCbCr, LAB, and finally, grayscale. Grayscale was the lowest in the testing results, with 85.4%. These results indicate that colour spaces do affect the detection quality and using them would improve the quality of smoke detection systems.

Downloads

Download data is not yet available.

References

R. N. Vasconcelos et al., "Fire Detection with Deep Learning: A Comprehensive Review," Land, vol. 13, no. 10, p. 1696, Oct. 2024, doi: 10.3390/land13101696.

B. M. Diaconu, "Recent Advances and Emerging Directions in Fire Detection Systems Based on Machine Learning Algorithms," Fire, vol. 6, no. 11, p. 441, Nov. 2023, doi: 10.3390/fire6110441.

O. V. Ekunke et al., "Innovations in Fire Detection and Suppression Systems for Oil Refinery Operations," Path Sci., vol. 10, no. 11, pp. 4001–4015, Nov. 2024, doi: 10.22178/pos.111-7.

W. Y. Hwang et al., "Computational design of a smoke detector with high sensitivity considering three-dimensional flow characteristics," Case Stud. Therm. Eng., vol. 53, p. 103896, Jan. 2024, doi: 10.1016/j.csite.2023.103896.

F. M. Talaat and H. ZainEldin, "An improved fire detection approach based on YOLO-v8 for smart cities," Neural Comput. Appl., vol. 35, no. 28, pp. 20939–20954, Oct. 2023, doi: 10.1007/s00521-023-08809-1.

M. M. Umar, L. C. De Silva, M. S. A. Bakar, and M. I. Petra, "State of the art of smoke and fire detection using image processing," Int. J. Signal Imaging Syst. Eng., vol. 10, no. 1/2, p. 22, 2017, doi: 10.1504/IJSISE.2017.084566.

R. W. Bukowski et al., "Performance of home smoke alarms analysis of the response of several available technologies in residential fire settings," Gaithersburg, MD, 2008. doi: 10.6028/NIST.TN.1455-1r2008.

J. Fang, J. Jie, Y. Hong-Yong, and Z. Yong-Ming, "Early fire smoke movements and detection in high large volume spaces," Build. Environ., vol. 41, no. 11, pp. 1482–1493, Nov. 2006, doi: 10.1016/j.buildenv.2005.05.036.

G. Lin, Y. Zhang, G. Xu, and Q. Zhang, "Smoke Detection on Video Sequences Using 3D Convolutional Neural Networks," Fire Technol., vol. 55, no. 5, pp. 1827–1847, Sep. 2019, doi: 10.1007/s10694-019-00832-w.

K. Lakhwani Associate Professor, P. D. Murarka Professor Arya, and N. Singh Chauhan, "Colour Space Transformation for Visual Enhancement of noisy colour Image," Int. J. ICT Manag., vol. 2, no. October, pp. 2026–6839, 2015.

M. Shafiq and Z. Gu, "Deep Residual Learning for Image Recognition: A Survey," Appl. Sci., vol. 12, no. 18, p. 8972, Sep. 2022, doi: 10.3390/app12188972.

L. Wang, X. Zhang, L. Li, B. Li, and Z. Mei, "Experimental Study on Early Fire Smoke Characteristics in a High-Volume Space: A Fire Detection Perspective," Fire, vol. 7, no. 9, p. 298, Aug. 2024, doi: 10.3390/fire7090298.

S. B and A. P, "Effect of Different Colour Spaces on Deep Image Segmentation," in Proc. 2021 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), Dec. 2021, vol. 12, no. 3, pp. 1–4, doi: 10.1109/WIECON-ECE54711.2021.9829655.

O. Giwa and A. Benkrid, "A new flame‐based colour space for efficient fire detection," IET Image Process., vol. 18, no. 5, pp. 1229–1244, Apr. 2024, doi: 10.1049/ipr2.13022.

C. Emmy Prema, S. S. Vinsley, and S. Suresh, "Multi feature analysis of smoke in YUV colour space for early forest fire detection," Fire Technol., vol. 52, pp. 1319–1342, 2016.

Z. Han, Y. Tian, C. Zheng, and F. Zhao, "Forest Fire Smoke Detection Based on Multiple Colour Spaces Deep Feature Fusion," Forests, vol. 15, no. 4, p. 689, Apr. 2024, doi: 10.3390/f15040689.

H. M. Bui, M. Lech, E. Cheng, K. Neville, and I. S. Burnett, "Using grayscale images for object recognition with convolutional-recursive neural network," in Proc. 2016 IEEE Sixth International Conference on Communications and Electronics (ICCE), Jul. 2016, pp. 321–325, doi: 10.1109/CCE.2016.7562656.

Z. Wang, C. Zheng, J. Yin, Y. Tian, and W. Cui, "A Semantic Segmentation Method for Early Forest Fire Smoke Based on Concentration Weighting," Electronics, vol. 10, no. 21, p. 2675, Oct. 2021, doi: 10.3390/electronics10212675.

S. Q. M. Salih and A. S. A. Khamas, "Exploring Colour s Combinations Impact on the Vision Comfortable and 3D Model Lucidity," Appl. Model. Simul., vol. 4, pp. 31–39, 2020.

T. Liu et al., "Video Smoke Detection Method Based on Change-Cumulative Image and Fusion Deep Network," Sensors, vol. 19, no. 23, p. 5060, Nov. 2019, doi: 10.3390/s19235060.

M. Chyad et al., "Exploring adversarial deep learning for fusion in multi-colour channel skin detection applications," Inf. Fusion, vol. 114, p. 102632, Feb. 2025, doi: 10.1016/j.inffus.2024.102632.

O. Besbes and A. Benazza-Benyahia, "A novel video-based smoke detection method based on colour invariants," in Proc. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar. 2016, pp. 1911–1915, doi: 10.1109/ICASSP.2016.7472009.

O. Besbes and A. Benazza-Benyahia, "A novel video-based smoke detection method based on colour invariants," in Proc. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, pp. 1911–1915.

W. S. Qureshi, M. Ekpanyapong, M. N. Dailey, S. Rinsurongkawong, A. Malenichev, and O. Krasotkina, "QuickBlaze: Early Fire Detection Using a Combined Video Processing Approach," Fire Technol., vol. 52, no. 5, pp. 1293–1317, Sep. 2016, doi: 10.1007/s10694-015-0489-7.

J. Zhao, Y. Zhou, B. Shi, J. Yang, D. Zhang, and R. Yao, "Multi-stage fusion and multi-source attention network for multi-modal remote sensing image segmentation," ACM Trans. Intell. Syst. Technol., vol. 12, no. 6, pp. 1–20, 2021.

S. Haridasan, A. Rattani, Z. S. Demissie, and A. Dutta, "Multispectral Deep Learning Models for Wildfire Detection.," 2022.

A. S. Pundir and B. Raman, "Deep Belief Network For Smoke Detection," Fire Technol., vol. 53, no. 6, pp. 1943–1960, Nov. 2017, doi: 10.1007/s10694-017-0665-z.

Q. Zhang, G. Lin, Y. Zhang, G. Xu, and J. Wang, “Wildland Forest Fire Smoke Detection Based on Faster R-CNN using Synthetic Smoke Images,” Procedia Eng., vol. 211, pp. 441–446, 2018, doi: 10.1016/j.proeng.2017.12.034.

S. Aslan, U. Gudukbay, B. U. Toreyin, and A. Enis Cetin, "Early Wildfire Smoke Detection Based on Motion-based Geometric Image Transformation and Deep Convolutional Generative Adversarial Networks," in Proc. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, pp. 8315–8319, doi: 10.1109/ICASSP.2019.8683629.

K. Gu, Z. Xia, J. Qiao, and W. Lin, "Deep Dual-Channel Neural Network for Image-Based Smoke Detection," IEEE Trans. Multimed., vol. 22, no. 2, pp. 311–323, Feb. 2020, doi: 10.1109/TMM.2019.2929009.

F. Safarov, S. Muksimova, M. Kamoliddin, and Y. I. Cho, "Fire and Smoke Detection in Complex Environments," Fire, vol. 7, no. 11, 2024, doi: 10.3390/fire7110389.

Z. G. Hadi, A. R. Ajel, and A. Q. Al-Dujaili, "Comparison Between Convolutional Neural Network CNN and SVM in Skin Cancer Images Recognition," J. Tech., vol. 3, no. 4, pp. 15–22, Dec. 2021, doi: 10.51173/jt.v3i4.390.

S. Frizzi, R. Kaabi, M. Bouchouicha, J.-M. Ginoux, E. Moreau, and F. Fnaiech, "Convolutional neural network for video fire and smoke detection," in Proc. IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society, 2016, pp. 877–882, doi: 10.1109/IECON.2016.7793196.

D. Singh and B. Singh, "Investigating the impact of data normalization on classification performance," Appl. Soft Comput., vol. 97, p. 105524, Dec. 2020, doi: 10.1016/j.asoc.2019.105524.

T. D. Nguyen, M.-H. Shih, D. Srivastava, S. Tirthapura, and B. Xu, "Stratified random sampling from streaming and stored data," Distrib. Parallel Databases, vol. 39, no. 3, pp. 665–710, Sep. 2021, doi: 10.1007/s10619-020-07315-w.

H.-Y. Cheng, J.-L. Yin, B.-H. Chen, and Z.-M. Yu, "Smoke 100k: A Database for Smoke Detection," in Proc. 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE), Oct. 2019, pp. 596–597, doi: 10.1109/GCCE46687.2019.9015309.

"Smoke100k | A Database for Smoke Detection." available: https://bigmms.github.io/cheng_gcce19_smoke100k (accessed Oct. 04, 2024).

"Kaggle." available:https://www.kaggle.com (accessed Oct. 04, 2024).

S. van der Walt, S. C. Colbert, and G. Varoquaux, "The NumPy Array: A Structure for Efficient Numerical Computation," Comput. Sci. Eng., vol. 13, no. 2, pp. 22–30, Mar. 2011, doi: 10.1109/MCSE.2011.37.

J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," in Proc. 2009 IEEE conference on computer vision and pattern recognition, 2009, pp. 248–255.

M. Lin, "Network in network," arXiv Prepr. arXiv1312.4400, 2013, doi: 10.48550/arXiv.1312.4400.

H. Li, J. Li, X. Guan, B. Liang, Y. Lai, and X. Luo, "Research on Overfitting of Deep Learning," in Proc. 2019 15th International Conference on Computational Intelligence and Security (CIS), 2019, pp. 78–81, doi: 10.1109/CIS.2019.00025.

H. Iiduka, "Appropriate Learning Rates of Adaptive Learning Rate Optimization Algorithms for Training Deep Neural Networks," IEEE Trans. Cybern., vol. 52, no. 12, pp. 13250–13261, Dec. 2022, doi: 10.1109/TCYB.2021.3107415.

S. Mannor, D. Peleg, and R. Rubinstein, "The cross entropy method for classification," in Proc. 22nd International Conference on Machine Learning, 2005, pp. 561–568, doi: 10.1145/1102351.1102422.

R. Yacouby and D. Axman, "Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models," in Proc. First Workshop on Evaluation and Comparison of NLP Systems, 2020, pp. 79–91, doi: 10.18653/v1/2020.eval4nlp-1.9.