{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T05:28:10Z","timestamp":1786426090746,"version":"build-2736575974"},"reference-count":52,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper presents NexFire Pro, a deployable desktop framework for real-time fire and smoke surveillance across multiple simultaneous IP or USB camera streams. The research contribution is a failure-mode-driven pipeline design methodology: each of the five post-detection stages is derived from a distinct, identifiable failure-mode category (illumination drift, static false-positive objects, spatially expected heat sources, temporal noise), evaluated with a leakage-free, source-disjoint held-out protocol that avoids the temporal data leakage that frame-level splits introduce. A fine-tuned YOLO11s backbone serves as the fixed detection substrate, surrounded by a five-stage processing pipeline: (1) CLAHE and adaptive gamma correction; (2) neural detection; (3) MOG2-based motion validation; (4) normalised-coordinate ROI exclusion; and (5) temporal alarm hysteresis. On a leakage-free held-out image test set, the detector attains mAP@0.5 = 0.65 (F1 = 0.70). A leave-one-out ablation on non-fire video shows that motion validation is the dominant false-alarm suppressor, reducing a raw-detector baseline of eight false alarms to zero. The proposed design-and-evaluation framework is intended to be transferable to other reliability-oriented computer vision applications beyond fire detection.<\/jats:p>","DOI":"10.3390\/s26165038","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T09:24:53Z","timestamp":1786353893000},"page":"5038","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Stage Computer Vision Framework for Real-Time Fire Detection in Low-Light Multi-Camera Environments"],"prefix":"10.3390","volume":"26","author":[{"given":"Ruhi","family":"Ta\u015f","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, OSTIM Technical University, Ankara 06374, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"ref_1","unstructured":"National Fire Protection Association (NFPA) (2023). NFPA Report: Industrial and Manufacturing Properties, 2017\u20132021, NFPA. Available online: https:\/\/www.nfpa.org."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.firesaf.2008.05.005","article-title":"Fire detection in video sequences using a generic color model","volume":"44","author":"Demirel","year":"2009","journal-title":"Fire Saf. J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.firesaf.2015.11.010","article-title":"False alarm ratio of fire detection and fire alarm systems in Germany\u2014A meta analysis","volume":"79","author":"Festag","year":"2016","journal-title":"Fire Saf. J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103803","DOI":"10.1016\/j.imavis.2019.08.007","article-title":"Intelligent and vision-based fire detection systems: A survey","volume":"91","author":"Bu","year":"2019","journal-title":"Image Vis. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You Only Look Once: Unified, real-time object detection. Proceedings of the IEEE\/CVF CVPR, IEEE.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_6","first-page":"9417","article-title":"DSS YOLO: An improved lightweight real-time fire detection model based on YOLOv8","volume":"15","author":"Liu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"120465","DOI":"10.1016\/j.eswa.2023.120465","article-title":"A modified YOLOv5 architecture for efficient fire detection in smart cities","volume":"231","author":"Yar","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chino, D.Y.T., Avalhais, L.P.S., Rodrigues, J.F., and Traina, A.J.M. (2015). BoWFire: Detection of fire in still images by integrating pixel color and texture analysis. Proceedings of SIBGRAPI, IEEE.","DOI":"10.1109\/SIBGRAPI.2015.19"},{"key":"ref_9","unstructured":"Islam, A., and Habib, M.I. (2023). Fire detection from image and video using an improved YOLOv5 model. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Vijayalakshmi, S.R., and Muruganand, S. (2017). Smoke detection in video images using background subtraction method for early fire alarm system. Proceedings of the 2017 2nd International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, 19\u201320 October 2017, IEEE.","DOI":"10.1109\/CESYS.2017.8321258"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1109\/TII.2017.2757457","article-title":"Fast smoke detection for video surveillance using CUDA","volume":"14","author":"Filonenko","year":"2018","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"109496","DOI":"10.1016\/j.asoc.2022.109496","article-title":"Smoke detection in video using convolutional neural networks and efficient spatio-temporal features","volume":"128","author":"Hashemzadeh","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.cviu.2013.10.003","article-title":"Adaptive estimation of visual smoke detection parameters based on spatial data and fire risk index","volume":"118","year":"2014","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"T\u00f6reyin, M., Dedeo\u011flu, Y., and \u00c7etin, A.E. (2005). Flame detection in video using hidden Markov models. Proceedings of IEEE ICIP, IEEE.","DOI":"10.1109\/ICIP.2005.1530284"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"133","DOI":"10.5772\/58821","article-title":"A vision based approach to fire detection","volume":"11","author":"Gomes","year":"2014","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.patrec.2005.06.015","article-title":"Computer vision based method for real-time fire and flame detection","volume":"27","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Dewangan, A., Pande, Y., Braun, H.-W., Vernon, F., Perez, I., Altintas, I., Cottrell, G.W., and Nguyen, M.H. (2022). FIgLib & SmokeyNet: Dataset and deep learning model for real-time wildland fire smoke detection. Remote Sens., 14.","DOI":"10.3390\/rs14041007"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Song, X., Luo, X., and Gong, Y. (2025). EFSD-YOLO: Fire and smoke detection based on enhanced YOLOv11. Proceedings of the 2025 4th International Conference on Intelligent Mechanical and Human-Computer Interaction Technology (IHCIT), Dalian, China, 22\u201324 August 2025, IEEE.","DOI":"10.1109\/IHCIT66787.2025.11199000"},{"key":"ref_19","unstructured":"\u00c7elik, T., Demirel, H., \u00d6zkaramanl\u0131, H., and Uyguro\u011flu, M. (2006). Fire detection in video sequences using statistical color model. Proceedings of the 2006 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toulouse, France, 14\u201319 May 2006, IEEE."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ateeq, Z., and Momani, M. (2020). Wireless sensor networks using image processing for fire detection. Proceedings of the 2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA), Sydney, Australia, 25\u201327 November 2020, IEEE.","DOI":"10.1109\/CITISIA50690.2020.9371798"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1939171","DOI":"10.1155\/2019\/1939171","article-title":"A real-time fire detection method from video with multifeature fusion","volume":"2019","author":"Gong","year":"2019","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.firesaf.2010.04.001","article-title":"Early fire detection algorithm based on irregular patterns of flames and hierarchical Bayesian networks","volume":"45","author":"Ko","year":"2010","journal-title":"Fire Saf. J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"125228","DOI":"10.1088\/2631-8695\/ae7ce7","article-title":"Real-time indoor early fire detection in industrial environments using optimized multi-sensor edge deep learning","volume":"8","author":"Hentati","year":"2026","journal-title":"Eng. Res. Express"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Jacob, I.J., Piramuthu, S., and Falkowski-Gilski, P. (2024). A review on YOLOv8 and its advancements. Data Intelligence and Cognitive Informatics, Springer. Algorithms for Intelligent Systems.","DOI":"10.1007\/978-981-99-7962-2"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1177\/07349041231163451","article-title":"Automatic early detection of wildfire smoke with visible-light cameras and EfficientDet","volume":"41","author":"Fernandes","year":"2023","journal-title":"J. Fire Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zell, O., P\u00e5lsson, J., Hernandez-Diaz, K., Alonso-Fernandez, F., and Nilsson, F. (2023). Image-based fire detection in industrial environments with YOLOv4. Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2023), Lisbon, Portugal, 22\u201324 February 2023, SciTePress.","DOI":"10.5220\/0011689400003411"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Tan, L., and Tiong, R.L.K. (2024). An improved fire and smoke detection method based on YOLOv8n for smart factories. Sensors, 24.","DOI":"10.3390\/s24154786"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiao, X., Wang, W., Wang, C., Jin, X., and Wang, Y. (2024). Improved lightweight flame smoke detection algorithm for YOLOv8n. Proceedings of the 2024 39th Youth Academic Annual Conference of Chinese Association of Automation (YAC), Dalian, China, 7\u20139 June 2024, IEEE.","DOI":"10.1109\/YAC63405.2024.10598605"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, Z. (2024). Enhanced fire detection algorithm for chemical plants using modified YOLOv9 architecture. Proceedings of the 2024 9th International Conference on Electronic Technology and Information Science (ICETIS), Zhuhai, China, 17\u201319 May 2024, IEEE.","DOI":"10.1109\/ICETIS61828.2024.10593793"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"25994","DOI":"10.1109\/ACCESS.2026.3664195","article-title":"Real-Time Fire Detection From Video Surveillance Cameras: Where Are We Now?","volume":"14","author":"Carletti","year":"2026","journal-title":"IEEE Access"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1943","DOI":"10.1007\/s10694-020-00986-y","article-title":"Video flame and smoke based fire detection algorithms: A literature review","volume":"56","author":"Gaur","year":"2020","journal-title":"Fire Technol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"124783","DOI":"10.1016\/j.eswa.2024.124783","article-title":"Fire and smoke detection from videos: A literature review under a novel taxonomy","volume":"255","author":"Gragnaniello","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.isprsjprs.2022.01.013","article-title":"A survey on vision-based outdoor smoke detection techniques for environmental safety","volume":"185","author":"Chaturvedi","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tatana, M.M., Tsoeu, M.S., and Maswanganyi, R.C. (2025). Low-light image and video enhancement for more robust computer vision tasks: A review. J. Imaging, 11.","DOI":"10.3390\/jimaging11040125"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yin, T., and Zhao, X. (2022). Using deep learning with thermal imaging for human detection in heavy smoke scenarios. Sensors, 22.","DOI":"10.3390\/s22145351"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zuiderveld, K. (1994). Contrast Limited Adaptive Histogram Equalization. Graphics Gems IV, Elsevier.","DOI":"10.1016\/B978-0-12-336156-1.50061-6"},{"key":"ref_37","unstructured":"Gonzalez, R.C., and Woods, R.E. (2018). Digital Image Processing, Pearson. [4th ed.]."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1142\/S0218001425540138","article-title":"A lightweight low-light image enhancement network via channel prior and gamma correction","volume":"39","author":"Weng","year":"2025","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Reis, M.J.C.S. (2025). Low-light image enhancement using deep learning: A lightweight network with synthetic and benchmark dataset evaluation. Appl. Sci., 15.","DOI":"10.3390\/app15116330"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.patcog.2016.06.008","article-title":"LLNet: A deep autoencoder approach to natural low-light image enhancement","volume":"61","author":"Lore","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zivkovic, Z. (2004). Improved adaptive Gaussian mixture model for background subtraction. Proceedings of ICPR, IEEE.","DOI":"10.1109\/ICPR.2004.1333992"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"100204","DOI":"10.1016\/j.cosrev.2019.100204","article-title":"Background subtraction in real applications: Challenges, current models and future directions","volume":"35","author":"Bouwmans","year":"2020","journal-title":"Comput. Sci. Rev."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"6181","DOI":"10.1007\/s00521-024-10963-z","article-title":"FLAME: Fire detection in videos combining a deep neural network with a model-based motion analysis","volume":"37","author":"Gragnaniello","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_44","first-page":"134","article-title":"Vision based fire detection","volume":"Volume 4","author":"Liu","year":"2004","journal-title":"Proceedings of the IEEE ICPR"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Quast, K., and Kaup, A. (2008). Spatial scalable region of interest transcoding of JPEG2000 for video surveillance. Proceedings of the 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance (AVSS), Santa Fe, NM, USA, 1\u20133 September 2008, IEEE.","DOI":"10.1109\/AVSS.2008.17"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Sun, L., Wang, W., Yuan, T., Mi, L., Dai, H., Liu, Y., and Fu, X. (2024). BiSwift: Bandwidth orchestrator for multi-stream video analytics on edge. Proceedings of IEEE INFOCOM 2024\u2014IEEE Conference on Computer Communications, Vancouver, BC, Canada, 20\u201323 May 2024, IEEE.","DOI":"10.1109\/INFOCOM52122.2024.10621392"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Tu, J., Xu, Q., and Chen, C. (2021). CANS: Communication limited camera network self-configuration for intelligent industrial surveillance. Proceedings of the 2021 47th Annual Conference of the IEEE Industrial Electronics Society (IECON), Toronto, ON, Canada, 13\u201316 October 2021, IEEE.","DOI":"10.1109\/IECON48115.2021.9589140"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Mukhiddinov, M., Abdusalomov, A.B., and Cho, J. (2022). A wildfire smoke detection system using unmanned aerial vehicle images based on the optimized YOLOv5. Sensors, 22.","DOI":"10.3390\/s22239384"},{"key":"ref_49","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., Michael, K., Xie, T., Fang, J. (2022). ultralytics\/yolov5: v7.0\u2014YOLOv5 SOTA Realtime Instance Segmentation, Zenodo."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.psep.2019.05.016","article-title":"An intelligent fire detection approach through cameras based on computer vision methods","volume":"127","author":"Xie","year":"2019","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"15349","DOI":"10.1007\/s00521-022-07467-z","article-title":"An automatic fire detection system based on deep convolutional neural networks for low-power, resource-constrained devices","volume":"34","author":"Lisboa","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"268","DOI":"10.2345\/0899-8205-46.4.268","article-title":"Monitor alarm fatigue: An integrative review","volume":"46","author":"Cvach","year":"2012","journal-title":"Biomed. Instrum. Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5038\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T04:37:43Z","timestamp":1786423063000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":52,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165038"],"URL":"https:\/\/doi.org\/10.3390\/s26165038","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,8]]}}}