Abstract
This paper deals with methods and approaches related to the solution of the task on early detection of fire outbreaks based on images and video streams from controlled territories. The images received from cameras, and also from unmanned aerial vehicles (UAVs), are exposed to automatic analysis, after which the conclusion about presence/absence of the fire within the controlled territory is made. In analysed studies of the last few years the artificial neural networks (ANN) are predominantly used for solving this task. ANN demonstrates high accuracy and recognition rate. This paper suggests the original method of detecting the fires in images and video streams, received from fixed cameras and UAV on-board cameras #COMESYSO11202.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gaur, A., Singh, A., Kumar, A., Kumar, A., Kapoor, K.: Video flame and smoke based fire detection algorithms: a literature review. Fire Technol. 56(5), 1943–1980 (2020). https://doi.org/10.1007/s10694-020-00986-y
Barmpoutis, P., Papaioannou, P., Dimitropoulos, K., Grammalidis, N.: A review on early forest fire detection systems using optical remote sensing. Sensors 20, 6442 (2020). https://doi.org/10.3390/s20226442
Abid, F.: A survey of machine learning algorithms based forest fires prediction and detection systems. Fire Technol. 57(2), 559–590 (2020). https://doi.org/10.1007/s10694-020-01056-z
Geetha, S., Abhishek, C.S., Akshayanat, C.S.: Machine vision based fire detection techniques: a survey. Fire Technol. 57(2), 591–623 (2020). https://doi.org/10.1007/s10694-020-01064-z
Ciprián-Sánchez, J.F., Ochoa-Ruiz, G., Rossi, L., Morandini, F.: Assessing the impact of the loss function, architecture and image type for deep learning-based wildfire segmentation. Appl. Sci. 11, 7046 (2021). https://doi.org/10.3390/app11157046
Cruz, H., Gualotuña, T., Pinillos, M., Marcillo, D., Jácome, S., Fonseca C., E.R.: Machine learning and color treatment for the forest fire and smoke detection systems and algorithms, a recent literature review. In: Botto-Tobar, M., Cruz, H., DÃaz Cadena, A. (eds.) CIT 2020. AISC, vol. 1326, pp. 109–120. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68080-0_8
Chaturvedi, S., Khanna, P., Ojha, A.: A survey on vision-based outdoor smoke detection techniques for environmental safety. ISPRS J. Photogram. Remote Sens. 185, 158–187 (2022). https://doi.org/10.1016/j.isprsjprs.2022.01.013
Favorskaya, M.N.: Early smoke detection in outdoor space: state-of-the-art, challenges and methods. In: Virvou, M., Tsihrintzis, G.A., Jain, L.C. (eds.) Advances in Selected Artificial Intelligence Areas. Learning and Analytics in Intelligent Systems, vol. 24. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-93052-3_8
Cheng, Y., Chen, K., Bai, H. et al.: An efficient fire detection algorithm based on multi-scale convolutional neural network. Fire Mater. 1–12 (2021). https://doi.org/10.1002/fam.3045
Huo, Y., Zhang, Q., Jia, Y. et al.: A deep separable convolutional neural network for multiscale image-based smoke detection. Fire Technol. (2022). https://doi.org/10.1007/s10694-021-01199-7
Miao, J., Zhao, G., Gao, Y., Wen, Y.: Fire detection algorithm based on improved YOLOv5 2021. In: International Conference on Control, Automation and Information Sciences (ICCAIS), pp. 776–781 (2021). https://doi.org/10.1109/ICCAIS52680.2021.9624619
Cai, Y., Guo, Y., Li, Y., Li, H., Liu, J.: Fire detection method based on improved deep convolution neural network. In: Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition (ICCPR ‘19). Association for Computing Machinery, New York, pp. 466–470 (2019). https://doi.org/10.1145/3373509.3373570
Li, Y., Zhang, W., Liu, Y., et al.: A visualized fire detection method based on convolutional neural network beyond anchor. Appl. Intell. (2022). https://doi.org/10.1007/s10489-022-03243-7
Abdel-Zaher, R.Y.M., Hisham, M., Darweesh, M.S.: Light-weight convolutional neural network for fire detection. In: 2021 International Conference on Electronic Engineering (ICEEM), pp. 1–5 (2021). https://doi.org/10.1109/ICEEM52022.2021.9480378
Wang, S., Zhao, J., Ta, N., Zhao, X., Xiao, M., Wei, H.: A real-time deep learning forest fire monitoring algorithm based on an improved Pruned + KD model. J. Real-Time Image Proc. 18(6), 2319–2329 (2021). https://doi.org/10.1007/s11554-021-01124-9
Ghali, R., Akhloufi, M.A., Mseddi, W.S.: Deep learning and transformer approaches for UAV-based wildfire detection and segmentation. Sensors 22, 1977 (2022). https://doi.org/10.3390/s22051977
Athanasis, N., Themistocleous, M., Kalabokidis, K., Chatzitheodorou, C.: Big data analysis in UAV surveillance for wildfire prevention and management. In: Themistocleous, M., Rupino da Cunha, P. (eds.) EMCIS 2018. LNBIP, vol. 341, pp. 47–58. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11395-7_5
Wang, S. et al.: Forest fire detection based on lightweight Yolo 2021. In: 33rd Chinese Control and Decision Conference (CCDC), pp. 1560–1565 (2021). https://doi.org/10.1109/CCDC52312.2021.9601362
Shamsoshoara, A., Afghah, F., Razi, A. et al.: The flame dataset: aerial imagery pile burn detection using drones (UAVS) (2021). https://ieee-dataport.org/open-access/flame-dataset-aerial-imagery-pile-burn-detection-using-drones-uavs. https://doi.org/10.21227/qad6-r683
GitHub – ultralytics/yolov5: YOLOv5 in PyTorch > ONNX > CoreML > TFLite (2022). https://github.com/ultralytics/yolov5/
Image classification from scratch (2020). https://keras.io/examples/vision/image_classification_from_scratch/
Thomson, W., Bhowmik, N., Breckon, T.P.: Efficient and compact convolutional neural network architectures for non-temporal real-time fire detection (2020). https://arxiv.org/pdf/2010.08833.pdf. https://doi.org/10.48550/arXiv.2010.08833
Akagic, A., Buza, E.: LW-FIRE: a lightweight wildfire image classification with a deep convolutional neural network. Appl. Sci. 12(5), 2646 (2022). https://doi.org/10.3390/app12052646
Public API for tf.keras.applications namespace (2022). https://www.tensorflow.org/api_docs/python/tf/keras/applications
Fralenko, V.P.: Experimental investigation of capabilities, characteristic for the neural network of «Darknet» type for the task of processing remote sensing photos. Aerosp. Instrum. Eng. 6, 44–52 (2017)
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
Abramov, N., Talalaev, A., Fralenko, V. (2023). Methods of Solution to the Task on Early Detection of Fire Outbreaks Based on Images and Video Streams from Controlled Territories. In: Silhavy, R., Silhavy, P., Prokopova, Z. (eds) Data Science and Algorithms in Systems. CoMeSySo 2022. Lecture Notes in Networks and Systems, vol 597. Springer, Cham. https://doi.org/10.1007/978-3-031-21438-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-21438-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21437-0
Online ISBN: 978-3-031-21438-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)