Abstract
Several methods for fire detection from camera streams have been proposed in recent years. While traditional techniques often emphasize recall, they frequently neglect critical factors such as minimizing false positives, ensuring timely alarm notifications and optimizing performance for devices with limited computational resources. The ONFIRE 2023 contest evaluates various approaches for detecting fire using smart cameras and establishes new evaluation metrics to measure precision, recall, notification promptness, processing speed and resource utilization. The eight participating teams received a training set that integrated all publicly available video datasets and were evaluated on a private test set. The latter includes positive samples where fire is not present at the beginning of the clip, as well as negative samples featuring moving fire-like objects. In this paper, we provide an overview of the competition’s dataset and review the proposed solutions, highlighting the winning approach, the limitations of existing datasets and the evaluation metrics used. By analyzing the results of the competition, we propose possible design choices and future directions that may help to reduce the false positive rate while preserving accuracy.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ayala A, Fernandes B, Cruz F et al (2020) Kutralnet: a portable deep learning model for fire recognition. In: International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1–8
Cao Y, Tang Q, Lu X (2022) Stcnet: spatiotemporal cross network for industrial smoke detection. Multimedia Tools Appl 81(7):10261–10277
Cao Y, Tang Q, Xu S et al (2022) Quasivsd: efficient dual-frame smoke detection. Neural Comput Appl 34(11):8539–8550
Cao Y, Tang Q, Wu X et al (2021) Effnet: enhanced feature foreground network for video smoke source prediction and detection. IEEE Trans Circ Syst Video Tech 32(4):1820–1833
Chaoxia C, Shang W, Zhang F (2020) Information-guided flame detection based on faster r-cnn. IEEE Access 8:58923–58932
Cob-Parro AC, Losada-Gutiérrez C, Marrón-Romera M et al (2021) Smart video surveillance system based on edge computing. Sensors 21(9):2958
De Venâncio PVA, Campos RJ, Rezende TM et al (2023) A hybrid method for fire detection based on spatial and temporal patterns. Neural Comput Appl 35(13):9349–9361
De Venâncio PVA, Rezende TM, Lisboa AC et al (2021) Fire detection based on a two-dimensional convolutional neural network and temporal analysis. In: LA-CCI, IEEE, pp 1–6
Dessì D, Fenu G, Marras M et al (2019) Bridging learning analytics and cognitive computing for big data classification in micro-learning video collections. Comput Hum Behav 92:468–477
Dewangan A, Pande Y, Braun HW et al (2022) Figlib & smokeynet: dataset and deep learning model for real-time wildland fire smoke detection. Remote Sens 14(4):1007
Dey A, Biswas S, Abualigah L (2024) Efficient violence recognition in video streams using resdlcnn-gru attention network. ECTI Trans Comput Inf Tech 18(3):329–341
Di Lascio R, Greco A, Saggese A et al (2014) Improving fire detection reliability by a combination of videoanalytics. In: International Conference on Image Analysis and Recognition. Springer, pp 477–484
Dimitropoulos K, Barmpoutis P, Grammalidis N (2014) Spatio-temporal flame modeling and dynamic texture analysis for automatic video-based fire detection. IEEE Trans Circ Syst Video Tech 25(2):339–351
Dunnings AJ, Breckon TP (2018) Experimentally defined convolutional neural network architecture variants for non-temporal real-time fire detection. In: International Conference on Image Processing (ICIP), pp 1558–1562
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 Circ Syst Video Tech 25(9):1545–1556
Gaur A, Singh A, Kumar A et al (2020) Video flame and smoke based fire detection algorithms: a literature review. Fire Tech 56(5):1943–1980
Geetha S, Abhishek C, Akshayanat C (2021) Machine vision based fire detection techniques: a survey. Fire Tech 57(2):591–623
Gragnaniello D, Greco A, Sansone C et al (2023) Onfire contest 2023: real-time fire detection on the edge. In: International Conference on Image Analysis and Proceeding, pp 273–281
Gragnaniello D, Greco A, Sansone C et al (2024) Fire and smoke detection from videos: a literature review under a novel taxonomy. Expert Syst Appl 255(D):124783
Greco A, Saggese A, Vento B (2022) A robust and efficient overhead people counting system for retail applications. In: International Conference on Image Analysis and Proceeding. Springer, pp 139–150
Greco A, Saldutti S, Vento B (2022) Fast and effective detection of personal protective equipment on smart cameras. In: International Conference on Pattern Recognition. Springer, pp 95–108
Gu K, Xia Z, Qiao J et al (2019) Deep dual-channel neural network for image-based smoke detection. IEEE Trans Multimedia 22(2):311–323
Hsu YC, Huang THK, Hu TY, et al (2021) Project rise: recognizing industrial smoke emissions. In: AAAI Conference on Artificial Intelligence, pp 14813–14821
Huang Z, Yang S, Zhou M et al (2022) Making accurate object detection at the edge: review and new approach. Artif Intell Rev 55(3):2245–2274
Huang J, He Z, Guan Y et al (2023) Real-time forest fire detection by ensemble lightweight yolox-l and defogging method. Sensors 23(4):1894
Huo Y, Zhang Q, Zhang Y et al (2022) 3dvsd: an end-to-end 3d convolutional object detection network for video smoke detection. Fire Saf J 134:103690
Javadi SH, Mohammadi A (2019) Fire detection by fusing correlated measurements. J Ambient Intell Humaniz Comput 10(4):1443–1451
Khudayberdiev O, Zhang J, Elkhalil A et al (2022) Fire detection approach based on vision transformer. In: ICAIS, pp 41–53
Ko BC, Ham SJ, Nam JY (2011) Modeling and formalization of fuzzy finite automata for detection of irregular fire flames. IEEE Trans Circ Syst Video Tech 21(12):1903–1912
Li Z, Mihaylova L, Yang L (2021) A deep learning framework for autonomous flame detection. Neurocomputing 448:205–216
Majid S, Alenezi F, Masood S et al (2022) Attention based cnn model for fire detection and localization in real-world images. Expert Syst Appl 189:116114
Pascarella AE, Giacco GL, Rigiroli M et al (2023) Ai and sustainability: territorial monitoring and waste valorization. In: Ital-IA, pp 571–574
Prema CE, Suresh S, Krishnan MN et al (2022) A novel efficient video smoke detection algorithm using co-occurrence of local binary pattern variants. Fire Tech 58(5):3139–3165
Pundir AS, Raman B (2019) Dual deep learning model for image based smoke detection. Fire Tech 55(6):2419–2442
Shahid M, Hua Kl (2021) Fire detection using transformer network. In: International Conference on Multimedia Retrieval, pp 627–630
Tao H, Lu M, Hu Z et al (2022) Attention-aggregated attribute-aware network with redundancy reduction convolution for video-based industrial smoke emission recognition. IEEE Trans Ind Inform 18(11):7653–7664
Vincent G, Desantis L, Patten E et al (2023) Rapid fire detection with early exiting. In: International Conference on Image Analysis and Proc., pp 294–301
Xie Y, Zhu J, Guo Y et al (2022) Early indoor occluded fire detection based on firelight reflection characteristics. Fire Saf J 128:103542
Yang J, Zhang Z, Xiao S et al (2023) Efficient data-driven behavior identification based on vision transformers for human activity understanding. Neurocomputing 530:104–115
Yuan F, Zhang L, Wan B et al (2019) Convolutional neural networks based on multi-scale additive merging layers for visual smoke recognition. Mach Vis Appl 30:345–358
Zedda L, Loddo A, Di Ruberto C (2023) Firestart: fire ignition recognition with enhanced smoothing techniques and real-time tracking. In: International Conference on Image Analysis and Proceeding, pp 282–293
Funding
The authors acknowledge financial support from: PNRR MUR project PE0000013-FAIR.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Data availability
The authors distribute, upon request on the website of the contest https://mivia.unisa.it/onfire2023, the training set and the validation set and give the possibility to run and evaluate the method on the test set.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gragnaniello, D., Greco, A., Sansone, C. et al. Onfire 2023 Contest: what did we learn about real time fire detection from cameras?. J Ambient Intell Human Comput 16, 253–264 (2025). https://doi.org/10.1007/s12652-024-04939-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-024-04939-z