Convolutional neural networks (CNNs) have yielded state-of-The-Art performance in image classification and other computer vision tasks. Their application in fire detection systems will substantially improve detection accuracy, which will eventually minimize fire disasters and reduce the ecological and social ramifications. However, the major concern with CNN-based fire detection systems is their implementation in real-world surveillance networks, due to their high memory and computational requirements for inference. In this paper, we propose an original, energy-friendly, and computationally efficient CNN architecture, inspired by the SqueezeNet architecture for fire detection, localization, and semantic understanding of the scene of the fire. It uses smaller convolutional kernels and contains no dense, fully connected layers, which helps keep the computational requirements to a minimum. Despite its low computational needs, the experimental results demonstrate that our proposed solution achieves accuracies that are comparable to other, more complex models, mainly due to its increased depth. Moreover, this paper shows how a tradeoff can be reached between fire detection accuracy and efficiency, by considering the specific characteristics of the problem of interest and the variety of fire data.

Muhammad K., Ahmad J., Lv Z., Bellavista P., Yang P., Baik S.W. (2019). Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance Applications. IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS. SYSTEMS, 49(7), 1419-1434 [10.1109/TSMC.2018.2830099].

Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance Applications

Bellavista P.;
2019

Abstract

Convolutional neural networks (CNNs) have yielded state-of-The-Art performance in image classification and other computer vision tasks. Their application in fire detection systems will substantially improve detection accuracy, which will eventually minimize fire disasters and reduce the ecological and social ramifications. However, the major concern with CNN-based fire detection systems is their implementation in real-world surveillance networks, due to their high memory and computational requirements for inference. In this paper, we propose an original, energy-friendly, and computationally efficient CNN architecture, inspired by the SqueezeNet architecture for fire detection, localization, and semantic understanding of the scene of the fire. It uses smaller convolutional kernels and contains no dense, fully connected layers, which helps keep the computational requirements to a minimum. Despite its low computational needs, the experimental results demonstrate that our proposed solution achieves accuracies that are comparable to other, more complex models, mainly due to its increased depth. Moreover, this paper shows how a tradeoff can be reached between fire detection accuracy and efficiency, by considering the specific characteristics of the problem of interest and the variety of fire data.
2019
Muhammad K., Ahmad J., Lv Z., Bellavista P., Yang P., Baik S.W. (2019). Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance Applications. IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS. SYSTEMS, 49(7), 1419-1434 [10.1109/TSMC.2018.2830099].
Muhammad K.; Ahmad J.; Lv Z.; Bellavista P.; Yang P.; Baik S.W.
File in questo prodotto:
File Dimensione Formato  
SMCA-17-10-1204-Final-3.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 2.75 MB
Formato Adobe PDF
2.75 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/729507
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 351
  • ???jsp.display-item.citation.isi??? 293
social impact