Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approach

The risk of fires in both indoor and outdoor scenarios is constantly rising around the world. The primary goal of a fire detection system is to minimize financial losses and human casualties by rapidly identifying flames in diverse settings, such as buildings, industrial sites, forests, and rural ar...

Full description

Saved in:
Bibliographic Details
Main Authors: Uttam U. Deshpande, Goh Kah Ong Michael, Sufola Das Chagas Silva Araujo, Sowmyashree H. Srinivasaiah, Harshel Malawade, Yash Kulkarni, Yash Desai
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Computer Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fcomp.2025.1636758/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239387503591424
author Uttam U. Deshpande
Goh Kah Ong Michael
Sufola Das Chagas Silva Araujo
Sowmyashree H. Srinivasaiah
Harshel Malawade
Yash Kulkarni
Yash Desai
author_facet Uttam U. Deshpande
Goh Kah Ong Michael
Sufola Das Chagas Silva Araujo
Sowmyashree H. Srinivasaiah
Harshel Malawade
Yash Kulkarni
Yash Desai
author_sort Uttam U. Deshpande
collection DOAJ
description The risk of fires in both indoor and outdoor scenarios is constantly rising around the world. The primary goal of a fire detection system is to minimize financial losses and human casualties by rapidly identifying flames in diverse settings, such as buildings, industrial sites, forests, and rural areas. Traditional fire detection systems that use point sensors have limitations in identifying early ignition and fire spread. Numerous existing computer vision and artificial intelligence-based fire detection techniques have produced good detection rates, but at the expense of excessive false alarms. In this paper, we propose an advanced fire and smoke detection system on the DetectNet_v2 architecture with ResNet-18 as its backbone. The framework uses NVIDIA’s Train-Adapt-Optimize (TAO) transfer learning methods to perform model optimization. We began by curating a custom data set comprising 3,000 real-world and synthetically augmented fire and smoke images to enhance models’ generalization across diverse industrial scenarios. To enable deployment on edge devices, the baseline FP32 model is fine-tuned, pruned, and subsequently optimized using Quantization-Aware Training (QAT) to generate an INT8 precision inference model with its size reduced by 12.7%. The proposed system achieved a detection accuracy of 95.6% for fire and 92% for smoke detections, maintaining a mean inference time of 42 ms on RTX GPUs. The comparative analysis revealed that our proposed model outperformed the baseline YOLOv8, SSD MobileNet_v2, and Faster R-CNN models in terms of precision and F1-scores. Performance benchmarks on fire instances such as mAP@0.5 (94.9%), mAP@0.5:0.95 (87.4%), and a low false rate of 3.5% highlight the DetectNet_v2 framework’s robustness and superior detection performance. Further validation experiments on NVIDIA Jetson Orin Nano and Xavier NX platforms confirmed their effective real-time inference capabilities, making them suitable for deployment in safety-critical scenarios and enabling human-in-the-loop verification for efficient alert handling.
format Article
id doaj-art-9083b67416464258b181530d313c0cc2
institution Kabale University
issn 2624-9898
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Computer Science
spelling doaj-art-9083b67416464258b181530d313c0cc22025-08-20T04:01:01ZengFrontiers Media S.A.Frontiers in Computer Science2624-98982025-08-01710.3389/fcomp.2025.16367581636758Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approachUttam U. Deshpande0Goh Kah Ong Michael1Sufola Das Chagas Silva Araujo2Sowmyashree H. Srinivasaiah3Harshel Malawade4Yash Kulkarni5Yash Desai6Department of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Belgaum, IndiaCenter for Image and Vision Computing, COE for Artificial Intelligence, Faculty of Information Science and Technology, Multimedia University, Melaka, MalaysiaDepartment of Computer Science and Engineering, Padre Conceição College of Engineering, Goa, IndiaDepartment of Computer Applications, Bangalore Institute of Technology, Bengaluru, IndiaDepartment of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Belgaum, IndiaDepartment of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Belgaum, IndiaDepartment of Electronics and Communication Engineering, KLS Gogte Institute of Technology, Belgaum, IndiaThe risk of fires in both indoor and outdoor scenarios is constantly rising around the world. The primary goal of a fire detection system is to minimize financial losses and human casualties by rapidly identifying flames in diverse settings, such as buildings, industrial sites, forests, and rural areas. Traditional fire detection systems that use point sensors have limitations in identifying early ignition and fire spread. Numerous existing computer vision and artificial intelligence-based fire detection techniques have produced good detection rates, but at the expense of excessive false alarms. In this paper, we propose an advanced fire and smoke detection system on the DetectNet_v2 architecture with ResNet-18 as its backbone. The framework uses NVIDIA’s Train-Adapt-Optimize (TAO) transfer learning methods to perform model optimization. We began by curating a custom data set comprising 3,000 real-world and synthetically augmented fire and smoke images to enhance models’ generalization across diverse industrial scenarios. To enable deployment on edge devices, the baseline FP32 model is fine-tuned, pruned, and subsequently optimized using Quantization-Aware Training (QAT) to generate an INT8 precision inference model with its size reduced by 12.7%. The proposed system achieved a detection accuracy of 95.6% for fire and 92% for smoke detections, maintaining a mean inference time of 42 ms on RTX GPUs. The comparative analysis revealed that our proposed model outperformed the baseline YOLOv8, SSD MobileNet_v2, and Faster R-CNN models in terms of precision and F1-scores. Performance benchmarks on fire instances such as mAP@0.5 (94.9%), mAP@0.5:0.95 (87.4%), and a low false rate of 3.5% highlight the DetectNet_v2 framework’s robustness and superior detection performance. Further validation experiments on NVIDIA Jetson Orin Nano and Xavier NX platforms confirmed their effective real-time inference capabilities, making them suitable for deployment in safety-critical scenarios and enabling human-in-the-loop verification for efficient alert handling.https://www.frontiersin.org/articles/10.3389/fcomp.2025.1636758/fullartificial intelligencefire and smoke detectionDetectNet_v2transfer learningmodel pruningtrain adapt optimize (TAO)
spellingShingle Uttam U. Deshpande
Goh Kah Ong Michael
Sufola Das Chagas Silva Araujo
Sowmyashree H. Srinivasaiah
Harshel Malawade
Yash Kulkarni
Yash Desai
Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approach
Frontiers in Computer Science
artificial intelligence
fire and smoke detection
DetectNet_v2
transfer learning
model pruning
train adapt optimize (TAO)
title Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approach
title_full Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approach
title_fullStr Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approach
title_full_unstemmed Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approach
title_short Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approach
title_sort real time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision based transfer learning approach
topic artificial intelligence
fire and smoke detection
DetectNet_v2
transfer learning
model pruning
train adapt optimize (TAO)
url https://www.frontiersin.org/articles/10.3389/fcomp.2025.1636758/full
work_keys_str_mv AT uttamudeshpande realtimefireandsmokedetectionsystemfordiverseindoorandoutdoorindustrialenvironmentalconditionsusingavisionbasedtransferlearningapproach
AT gohkahongmichael realtimefireandsmokedetectionsystemfordiverseindoorandoutdoorindustrialenvironmentalconditionsusingavisionbasedtransferlearningapproach
AT sufoladaschagassilvaaraujo realtimefireandsmokedetectionsystemfordiverseindoorandoutdoorindustrialenvironmentalconditionsusingavisionbasedtransferlearningapproach
AT sowmyashreehsrinivasaiah realtimefireandsmokedetectionsystemfordiverseindoorandoutdoorindustrialenvironmentalconditionsusingavisionbasedtransferlearningapproach
AT harshelmalawade realtimefireandsmokedetectionsystemfordiverseindoorandoutdoorindustrialenvironmentalconditionsusingavisionbasedtransferlearningapproach
AT yashkulkarni realtimefireandsmokedetectionsystemfordiverseindoorandoutdoorindustrialenvironmentalconditionsusingavisionbasedtransferlearningapproach
AT yashdesai realtimefireandsmokedetectionsystemfordiverseindoorandoutdoorindustrialenvironmentalconditionsusingavisionbasedtransferlearningapproach