Abstract
In the past decades, several computer vision-based fire detection techniques have been developed using color features, shape, and motion characteristics. However, the most deserved features have never been discussed. According to the facts, fire color characteristics have not been only in orange shades, but also in other colors shades such as green and blue shades, in the real world. We, hence, proposed a hybrid fire features selection model by considering fire textures. Our proposed model effectively utilized the collaborative techniques of maximal information coefficient (MIC) and random forests recursive feature elimination (RF-RFE), to discover the most significant features for fire detection. We developed a hybrid features selection model of fire detection named maximal information coefficient in collaboration with random forests recursive feature elimination (MIC-RF-RFE). Selected features were then leveraged for two recognition purposes. On one hand, they were utilized for fire detection even in unconventional fire colors. On the other hand, they were applied for four fire circumstance states recognition. Several video footages both fire and non-fire were collected to extract various observed features to be utilized for our training and test datasets. Our experiments demonstrated that fire texture detection with our proposed algorithms of fire patterns recognition based on the unification of color pattern and motion pattern not only significantly increased the accuracy of fire detection but also additionally identified fire circumstances.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
BangkokPost.com: fire hits Bangkok’s sampeng market, 2 killed. (2022) Retrieved 28 June 2022 at https://www.bangkokpost.com/thailand/general/2334118/fire-hits-bangkoks-sampeng-market-2-killed
CGTN.com: southwest China forest fire: situation under control, 30 confirmed dead (2022). Retrieved 16 June 2022 at https://news.cgtn.com/news/3d3d414d32557a4e33457a6333566d54/index.html
Smirg, O., Smekal, Z., Dutta, M.K., Kakani, B.: Automatic detection of the direction and speed of moving objects in the video. In: 2013 Sixth International Conference on Contemporary Computing (IC3), pp. 86–90 (2013)
Wattanachote, K., Shih, T.K.: Automatic dynamic texture transformation based on a new motion coherence metric. IEEE Trans. Circuit. Syst. Video Technol. 26, 1805–1820 (2016)
Chul Ko, B., Cheong, K.-H., Nam, J.-Y.: Fire detection based on vision sensor and support vector machines. Fire Safety J. 44, 322–329 (2009)
Çelik, T., Demirel, H.: Fire detection in video sequences using a generic color model. Fire Safety J. 44, 147–158 (2009)
Muhammad, K., Ahmad, J., Wook Baik, S.: Early detection using convolutional neural networks during surveillance for elective disaster management. Neurocomputing 288, 30–42 (2018)
Foggia, P., Saggese, A., Vento, M.: Real-time fire detection for video-surveillance applications using a combination of experts based on color, shape, and motion. IEEE Trans. Circuit. Syst. Video Technol. 25, 1545–1556 (2015)
Wahyono, Harjoko, A., Dharmawan, A., Adhinata, F.D., Kosala, G., Jo, K.-H.: Real-Time forest fire detection framework based on artificial intelligence using color probability model and motion feature analysis. Fire https://doi.org/10.3390/fire5010023
Maggie Maggio: Fire 2: Color and Temperature (2011). Retrieved June 8, 2022 at https://maggiemaggio.com/color/2011/08/fire-ii-color-and-temperature/
Maggie Maggio: Fire 3: Fauvist Flames (2011). Retrieved June 18, 2022 at https://maggiemaggio.com/color/2011/08/fire-iii-rainbow-flames/
Reshef, D., et al.: Detecting novel associations in large data sets. Science (New York, N.Y.) 334, 1518–1524 (2011). https://doi.org/10.1126/science.1205438
Albanese, D., Filosi, M., Visintainer, R., Riccadonna, S., Jurman, G., Furlanello, C.: minerva and minepy: a C engine for the MINE suite and its R, Python and MATLAB wrappers. Bioinformatics 29, 407–408 (2012). https://doi.org/10.1093/bioinformatics/bts707
Chen, Z., Yeo, C., Francis, B., Lau, C.: Combining MIC feature selection and feature-based MSPCA for network traffic anomaly detection, 176–181 (2016). https://doi.org/10.1109/DIPDMWC.2016.7529385
Prinzie, A., Van den Poel, D.: Random Forests for multiclass classification: random MultiNomial Logit. Expert Syst. Appl. 34, 1721–1732 (2008). https://doi.org/10.1016/j.eswa.2007.01.029
Ali, J., Khan, R., Ahmad, N., Maqsood, I.: Random forests and decision trees. Int. J. Comput. Sci. Issues (IJCSI) 9 (2012)
Qi, C., Meng, Z., Liu, X., Jin, Q., Su, R.: Decision variants for the automatic determination of optimal feature subset in RF-RFE. Genes 9, 301 (2018). https://doi.org/10.3390/genes9060301
Zupan, J.: Introduction to artificial neural network (ANN) methods: what they are and how to use them. Acta Chimica Slovenica 41 (1994)
Peng, J., Lee, K., Ingersoll, G.: An introduction to logistic regression analysis and reporting. J. Educ. Res. 96, 3–14 (2002). https://doi.org/10.1080/00220670209598786
Bi, Z.-J., Han, Y.-Q., Huang, C.-Q., Wang, M.: Gaussian Naive Bayesian data classification model based on clustering algorithm, 396–400 (2019). https://doi.org/10.2991/masta-19.2019.67
Wang, W. Lu, Y.: Analysis of the mean absolute error (MAE) and the root mean square error (RMSE) in assessing rounding model. IOP Conf. Ser.: Mater. Sci. Eng. 324, 012049 (2018). https://doi.org/10.1088/1757-899X/324/1/012049
Dunnings, A., Breckon, T.P.: Experimentally defined Convolutional nerual network architecture variants for non-temporal real-time fire detection (2018). https://doi.org/10.1109/ICIP.2018.8451657
Thomson, W., Bhowmik, N., Toby, B.: Efficient and compact convolutional neural network architectures for non-temporal real-time fire detection (2020)
Moses, Olafenwa, J.: FireNet is an artificial intelligence project for real-time fire detection. (2019). https://github.com/OlafenwaMoses/FireNET
Ryu, J., Kwak, D.: A study on a complex flame and smoke detection method using computer vision detection and convolutional neural network. Fire 5(4), 108 (2022). https://doi.org/10.3390/fire5040108
Muhammad, K., Ahmad, J., Mehmood, I., Rho, S., Baik, S.: Convolutional neural networks based fire detection in surveillance videos. IEEE Access 1–1 (2018). https://doi.org/10.1109/ACCESS.2018.2812835
Ghali, R., Jmal, M., Mseddi, W., Attia, R.: Recent advances in fire detection and monitoring systems: a review (2020). https://doi.org/10.1007/978-3-030-21005-2_32
Acknowledgment
The work was partially supported by the Research Projects of Guangdong University of Foreign Studies in project title of “Artificial Intelligence System Development for Fire Calamity Surveillance System based on Computer Vision”. This project is the responsibility of Kanoksak Wattanachote.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jetwiriyanon, J., Feng, Z., Wattanachote, K. (2023). A Novel Features Selection Model for Fire Detection and Fire Circumstances Recognition by Considering Fire Texture: MIC-RF-RFE. In: Arai, K. (eds) Intelligent Computing. SAI 2023. Lecture Notes in Networks and Systems, vol 711. Springer, Cham. https://doi.org/10.1007/978-3-031-37717-4_71
Download citation
DOI: https://doi.org/10.1007/978-3-031-37717-4_71
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-37716-7
Online ISBN: 978-3-031-37717-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)