KutralNext: An Efficient Multi-label Fire and Smoke Image Recognition Model
Early alert fire and smoke detection systems are crucial for management decision making as daily and security operations. One of the new approaches to the problem is the use of images to perform the detection. Fire and smoke recognition from visual scenes is a demanding task due to the high variance of color and texture. In recent years, several fire-recognition approaches based on deep learning methods have been proposed to overcome this problem. Nevertheless, many developments have been focused on surpassing previous state-of-the-art model's accuracy, regardless of the computational resources needed to execute the model. In this work, is studied the trade-off between accuracy and complexity of the inverted residual block and the octave convolution techniques, which reduces the model's size and computation requirements. The literature suggests that those techniques work well by themselves, and in this research was demonstrated that combined, it achieves a better trade-off. We proposed the KutralNext architecture, an efficient model with reduced number of layers and computacional resources for singleand multi-label fire and smoke recognition tasks. Additionally, a more efficient KutralNext+ model improved with novel techniques, achieved an 84.36% average test accuracy in FireNet, FiSmo, and FiSmoA fire datasets. For the KutralSmoke and FiSmo fire and smoke datasets attained an 81.53% average test accuracy. Furthermore, state-of-the-art fire and smoke recognition model considered, FireDetection, KutralNext uses 59% fewer parameters, and KutralNext+ requires 97% fewer flops and is 4x faster.
J. Barlow and C. A. Peres, “Avifaunal responses to single and recurrent wildfires in amazonian forests,” Ecological Applications, vol. 14, no. 5, pp. 1358–1373, 2004.
X. Úbeda and P. Sarricolea, “Wildfires in chile: A review,” Global and Planetary Change, vol. 146, pp. 152 – 161, 2016.
N. V. Urzúa Valenzuela and M. F. Cáceres Bueno, “Incendios forestales: principales consecuencias económicas y ambientales en chile,” Revista Interamericana de Ambiente y Turismo - RIAT, vol. 7, no. 1, pp. 18 – 24, 2011.
V. Quintanilla PÉrez, “Perturbaciones a la vegetación nativa por grandes fuegos de 50 años atrás, en bosques nordpatagónicos. caso de estudio en chile meridional,” Anales de Geografía de la Universidad Complutense, vol. 28, no. 1, pp. 85 – 104, 5 2008.
Y.-H. Kim, A. Kim, and H.-Y. Jeong, “Rgb color model based the fire detection algorithm in video sequences on wireless sensor network,” International Journal of Distributed Sensor Networks, vol. 10, no. 4, p. 923609, 2014.
G. Nikos, A. Cetin, K. Dimitropoulos, F. Tsalakanidou, K. Kose, O. Gunay, B. Gouverneur, D. Torri, E. Kuruoglu, S. Tozzi, A. Benazza- Benyahia, F. Chaabane, B. Kosucu, and C. Ersoy, “A multi-sensor network for the protection of cultural heritage,” 8 2011.
K. Dimitropoulos, P. Barmpoutis, and N. Grammalidis, “Spatio-temporal flame modeling and dynamic texture analysis for automatic video-based fire detection,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 2, pp. 339–351, 2 2015.
P. Barmpoutis, K. Dimitropoulos, and N. Grammalidis, “Real time video fire detection using spatio-temporal consistency energy,” in 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, 8 2013, pp. 365–370.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” CoRR, vol. abs/1409.1556, 2014.
J. Sharma, O. Granmo, M. Goodwin, and J. T. Fidje, “Deep convolutional neural networks for fire detection in images,” in Engineering Applications of Neural Networks. Cham: Springer International Publishing, 2017, pp. 183–193.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” CoRR, vol. abs/1512.03385, 2015.
K. Muhammad, J. Ahmad, Z. Lv, P. Bellavista, P. Yang, and S. W. Baik, “Efficient deep CNN-based fire detection and localization in video surveillance applications,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 49, no. 7, pp. 1419–1434, 2018.
A. Namozov and Y. I. Cho, “An efficient deep learning algorithm for fire and smoke detection with limited data,” Advances in Electrical and Computer Engineering, vol. 18, pp. 121–128, 2018.
F. Agostinelli, M. Hoffman, P. Sadowski, and P. Baldi, “Learning activation functions to improve deep neural networks,” arXiv preprint arXiv:1412.6830, 2014.
A. F. Agarap, “Deep learning using rectified linear units (relu),” arXiv preprint arXiv:1803.08375, 2018.
J. Gotthans, T. Gotthans, and R. Marsalek, “Deep convolutional neural network for fire detection,” in 2020 30th International Conference Radioelektronika (RADIOELEKTRONIKA), 2020, pp. 1–6.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Eds., vol. 25. Curran Associates, Inc., 2012, pp. 1097–1105.
F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size,” arXiv preprint arXiv:1602.07360, 2016.
A. Jadon, M. Omama, A. Varshney, M. S. Ansari, and R. Sharma, “FireNet: A specialized lightweight fire & smoke detection model for real-time iot applications,” CoRR, vol. abs/1905.11922, 2019.
A. Ayala, E. Lima, B. Fernandes, B. L. D. Bezerra, and F. Cruz, “Lightweight and efficient octave convolutional neural network for fire recognition,” in 2019 IEEE Latin American Conference on Computational Intelligence (LA-CCI), 2019, pp. 87–92.
Y. Chen, H. Fan, B. Xu, Z. Yan, Y. Kalantidis, M. Rohrbach, S. Yan, and J. Feng, “Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution,” arXiv preprint arXiv:1904.05049, 2019.
A. Ayala, B. Fernandes, F. Cruz, D. Macêdo, A. L. I. Oliveira, and C. Zanchettin, “Kutralnet: A portable deep learning model for fire recognition,” in 2020 International Joint Conference on Neural Networks (IJCNN), 2020, pp. 1–8.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 2018, pp. 4510–4520.
B. Xu, N. Wang, T. Chen, and M. Li, “Empirical evaluation of rectified activations in convolutional network,” CoRR, vol. abs/1505.00853, 2015.
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei, “ImageNet Large Scale Visual Recognition Challenge,” International Journal of Computer Vision (IJCV), vol. 115, no. 3, pp. 211–252, 2015.
Y. Cui, M. Jia, T.-Y. Lin, Y. Song, and S. Belongie, “Class-balanced loss based on effective number of samples,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 9268–9277.
T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988.
M. T. Cazzolato, L. P. Avalhais, D. Y. Chino, J. S. Ramos, J. A. de Souza, J. F. Rodrigues-Jr, and A. Traina, “Fismo: A compilation of datasets from emergency situations for fire and smoke analysis,” in Brazilian Symposium on Databases - SBBD, 2017, pp. 213–223.
G. Antzoulatos, P. Giannakeris, I. Koulalis, A. Karakostas, S. Vrochidis, and I. Kompatsiaris, “A Multi-Layer Fusion Approach For Real-Time Fire Severity Assessment Based on Multimedia Incidents,” Mar. 2020.