Abstract
The detection and prevention of flame is of great value to protect people’s lives and property safety. At present, most flame detection methods use a single classifier and have achieved some results. However, a single classification algorithm has poor adaptability to fire detection in a variety of complex situations. Therefore, a multi-classifier fusion flame detection algorithm is proposed based on Dempster-Shafer (DS) evidence theory is proposed. In short, firstly four classifiers are used to classify the same flame feature, and the four classification results are fused to make preliminary decision. The four classifiers include support vector machine (SVM), K-nearest neighbor (KNN), decision tree (DT) and random forest (RF). Second, three complementary flame features are chosen, namely color, texture and shape changes. Finally, the preliminary decision results of the three features are fused to obtain the final classification result. It should be noted that when different classifiers have strong conflicts on the classification result of the same feature, the fusion rule of DS evidence theory will be invalid. To solve this problem, the DS evidence theory is improved. For the experiment, the public flame videos are collected to construct a data set including different complex scenes for algorithm verification, where the frame rate of the video is 15 or 24 frames/s and the resolution is 320 × 240. The experimental results show that there is a strong complementary among the results of different single classifier. The multi-classifier fusion algorithm can achieve better classification performance and robust performance than the single classifier by integrating the results of each classifier, and its average detection rate reaches 93.08%. In addition, for the changes of different environments, the proposed method has higher adaptability and stability than other state-of-art methods.
Similar content being viewed by others
References
Akshay T, Poonam S (2015) Hybrid approach to detect a fire based on motion color and edge. Digital Image Processing 7(9)
Alamgir N, Nguyen K, Chandran V et al (2018) Combining multi-channel color space with local binary co-occurrence feature descriptors for accurate smoke detection from surveillance videos. Fire Safety Journal 102(DEC.):1–10. https://doi.org/10.1016/j.firesaf.2018.09.003
Cao JT, Qin YY, Ji XF (2020) Review on video based flame detection algorithm. J Data Acquisit Process 1(35):35–52. https://doi.org/10.16337/j.1004-9037.2020.01.003
Chen K, Li YH, You F et al (2017) Smoke detection algorithm about video image with multiple features based on serial and parallel processing model. Comput Moderniz 4(1):1–6. https://doi.org/10.3969/j.issn.1006-2475.2017.04.001
Chi R, Lu Z, Ji M et al (2017) Real-time multi-feature based fire flame detection in video. Image Process 11(1):31–37. https://doi.org/10.1049/iet-ipr.2016.0193
Choi HS, Moon KS, Kim JN, Park SS (2016) Fire detection algorithm based on motion information and color information analysis. J Korea Multimed Society 19(2):180–188. https://doi.org/10.9717/kmms.2016.19.2.180
Emmy PC, Vinsley SS, Suresh S (2016) Multi feature analysis of smoke in YUV color space for early forest fire detection. Fire Technol 52(5):1319–1342. https://doi.org/10.1007/s10694-016-0580-8
Emmy PC, Vinsley SS, Suresh S (2017) Efficient flame detection based on static and dynamic texture analysis in forest fire detection. Fire Technol 8(54):255–288. https://doi.org/10.1007/s10694-017-0683-x
Foggia P, Saggese A, Vento M (2015) Real-time fire detection for video-surveillance applications using a combination of experts based on color, shape, and motion. IEEE Trans Circuits Syst Video Technol 9(25):1545–1556
Han XF, Jin JS, Wang MJ et al (2017) Video fire detection based on Gaussian mixture model and multi-color features. Signal Image Video P 5:1–7
http://www.voidcn.com/article/p-aqyrfugn-brs.html. Accepted 06 June 2018
http://www.voidcn.com/article/p-pnamezca-bca.html. Accepted 30 March 2013
https://blog.csdn.net/qq_36512295/article/details/89448583. Accepted 30 April 2019
https://blog.csdn.net/zfcjhdq/article/details/515668755. Accepted 06 February 2016
https://wenku.baidu.com/view/a659291e7c1cfad6185fa79f.html. Accessed 30 June 2018
Liu Y, Cheng MM, Fan DP et al (2019) Semantic edge detection with diverse deep supervision. IEEE Transaction on Pattern Analysis and Machine Intelligence, TPAMI on 2018 Dec 26
Lu C, Lu M, Lu X, Cai M, Feng X (2018) Forest fire smoke recognition based on multiple feature fusion. IOP Confer Series Mater Sci Eng 435(1):012006. https://doi.org/10.1088/1757-899X/435/1/012006
Minichino J, Howse J (2015) Learning OpenCV computer vision with python. In: Background subtractor: KNN, MOG2 and GMG, second edn, Ireland
Wang L, Li AG (2017) Early fire recognition based on multi-feature fusion of video, vol 7. Proceeding of the 36th Chinese Control Conference, pp 26–28
Wang T, Bu LP, Yang ZK et al (2020) A new fire detection method using a multi-expert system based on color dispersion similarity and centroid motion in indoor environment. IEEE/CAA J Autom Sinica 1(7):263–275
Wu XY, Yan YY, Du J et al (2015) Fire detection based on fusion of multiple feature. CAAI Transactions on Intelligent Systems 10(iceiti):1–8. https://doi.org/10.12783/dtcse/iceiti2016/6207
Wu X, Lu X, Leung H et al (2018) A video based fire smoke detection using robust AdaBoost. Sensors 18(11). https://doi.org/10.3390/s18113780
Zeng ST, Wu HB, Shen PH (2017) Video fire detection based on fusion of multiple features. J Graph 4(38):549–557. https://doi.org/10.11996/JG.j.2095-302X.2017040549
Zhao Q, Sun FD, Li WH et al (2018) Flame detection using generic color model and improved block-based PCA in active infrared camera. Int J Pattern Recognit Artif Intell 5(32):1–15. https://doi.org/10.1142/S0218001418500143
Zhao JX, Liu J, Fan DP et al (2019) EGNet:Edge guidance network for salient object detection. 2019. IEEE International Conference on Computer Vision (ICCV) 8(22):8779–8788
Zhao JX, Cao Y, Fan DP et al (2020) Contrast prior and fluid pyramid integration for rgbd salient object detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. https://doi.org/10.1109/CVPR.2019.00405
Acknowledgements
This work is supported by the Liaoning Provincial Science Public Welfare Research Fund Project (2016002006), the Liaoning Provincial Department of Education Scientific Research Service Local Project (L201708).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Qin, Y., Cao, J., Ji, X. et al. Research on video flame detection algorithm based on improved DS evidence theory. Multimed Tools Appl 79, 26747–26763 (2020). https://doi.org/10.1007/s11042-020-09287-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09287-6