Abstract
Research on video smoke detection has become a hot topic in fire disaster prevention and control as it can realize early detection. Conventional methods use handcrafted features rely on prior knowledge to recognize whether a frame contains smoke. Such methods are often proposed for fixed fire scene and sensitive to the environment resulting in false alarms. In this paper, we use convolutional neural networks (CNN), which are state-of-the-art for image recognition tasks to identify smoke in video. We develop a joint detection framework based on faster RCNN and 3D CNN. An improved faster RCNN with non-maximum annexation is used to realize the smoke target location based on static spatial information. Then, 3D CNN realizes smoke recognition by combining dynamic spatial–temporal information. Compared with common CNN methods using image for smoke detection, 3D CNN improved the recognition accuracy significantly. Different network structures and data processing methods of 3D CNN have been compared, including Slow Fusion and optical flow. Tested on a dataset that comprises smoke video from multiple sources, the proposed frameworks are shown to perform very well in smoke location and recognition. Finally, the framework of two-stream 3D CNN performs the best, with a detection rate of 95.23% and a low false alarm rate of 0.39% for smoke video sequences.
Similar content being viewed by others
References
Çetin AE, Dimitropoulos K, Gouverneur B et al (2013) Video fire detection—review. Digit Signal Process 23(6):1827–1843
Ugur Töreyin B, Enis Cetin A (2007) Fire detection in infrared video using wavelet analysis. Opt Eng 46(6):7204
Toreyin BU, Dedeoglu Y, Cetin AE (2006) Contour based smoke detection in video using wavelets. In: European signal processing conference 2006. IEEE, pp 1–5
Yu C, Fang J, Wang J et al (2010) Video fire smoke detection using motion and color features. Fire Technol 46(3):651–666
Jia Y, Yuan J, Wang J et al (2016) A saliency-based method for early smoke detection in video sequences. Fire Technol 52(5):1–2
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied todocument recognition. Proc IEEE 86(11):2278–2324
Yin Z, Wan B, Yuan F et al (2017) A deep normalization and convolutional neural network for image smoke detection. IEEE Access 5(99):18429–18438
Mao W, Wang W, Dou Z et al (2018) Fire recognition based on multi-channel convolutional neural network. Fire Technol 54(2):531–554
Sharma J, Granmo OC, Goodwin M et al (2017) Deep convolutional neural networks for fire detection in images. In: Boracchi G, Iliadis L, Jayne C, Likas A (eds) International conference on engineering applications of neural networks. Springer, Cham, pp 183–193
Muhammad K, Ahmad J, Mehmood I et al (2018) Convolutional neural networks based fire detection in surveillance videos. IEEE Access 6:18174–18183
Xu G, Zhang Y, Zhang Q, Lin G et al (2017) Domain adaptation from synthesis to reality in single-model detector for video smoke detection. arXiv:1709.08142
Dung NM, Ro S (2018) Algorithm for fire detection using a camera surveillance system. In: Proceedings of the 2018 international conference on image and graphics processing. ACM, pp 38–42
Luo Y, Zhao L, Liu P et al (2018) Fire smoke detection algorithm based on motion characteristic and convolutional neural networks. Multimed Tools Appl 77:15075–15092
Wang Z, Wang Z, Zhang H et al (2017) A novel fire detection approach based on CNN-SVM using Tensorflow. In: International conference on intelligent computing. Springer, Cham, pp 682–693
Zhang Q, Xu J, Xu L et al (2016) Deep convolutional neural networks for forest fire detection. In: Proceedings of the 2016 international forum on management, education and information technology application. Atlantis Press
Zhang QX, Lin GH, Zhang YM et al (2018) Wildland forest fire smoke detection based on faster R-CNN using synthetic smoke images. Procedia Eng 211:441–446
Du T, Bourdev L, Fergus R et al (2015) Learning spatiotemporal features with 3D convolutional networks. In: IEEE International conference on computer vision. IEEE, pp 4489–4497
Ren S, Girshick R, Girshick R et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Hubel DH, Wiesel TN (1962) Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J Physiol 160(1):106–154
Girshick R, Donahue J, Darrell T et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580–587
Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. Comput Linguist 1(4):568–576
Donahue J, Hendricks LA, Rohrbach M et al (2017) Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans Pattern Anal Mach Intell 39(4):677–691
Xu H, Das A, Saenko K (2017) R-C3D: region convolutional 3D network for temporal activity detection. In: Proceedings of the IEEE international conference on computer vision, pp 5783–5792
Shou Z, Wang D, Chang SF (2016) Temporal action localization in untrimmed videos via multi-stage CNNs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1049–1058
Karpathy A, Toderici G, Shetty S et al (2014) Large-scale video classification with convolutional neural networks. In: IEEE conference on computer vision and pattern recognition. IEEE Computer Society, pp 1725–1732
Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov R (2012) Improving neural networks by preventing coadaptation of feature detectors. Computing Research Repository. http://arxiv.org/abs/1207.0580
http://signal.ee.bilkent.edu.tr/VisiFire/Demo. Accessed 5 May 2018
http://cvpr.kmu.ac.kr/. Accessed 5 May 2018
Li S, Wang B, Dong R et al (2016) A novel smoke detection algorithm based on fast self-tuning background subtraction. In: Control and decision conference. IEEE, pp 3539–3543
Tang Y (2013) Deep learning using linear support vector machines. arXiv:1306.0239
van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. JMLR 9:2579–2605
Acknowledgements
This work was supported by the National Key Research and Development Plan under Grant No. 2016YFC0800100, Anhui Provincial Key Research and Development Plan under Grant No. 1704a0902030, and the Fundamental Research Funds for the Central Universities under Grant No. WK2320000035. The authors gratefully acknowledge all of these supports.
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
Lin, G., Zhang, Y., Xu, G. et al. Smoke Detection on Video Sequences Using 3D Convolutional Neural Networks. Fire Technol 55, 1827–1847 (2019). https://doi.org/10.1007/s10694-019-00832-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10694-019-00832-w