Fire smoke detection algorithm based on motion characteristic and convolutional neural networks

Luo, Yanmin; Zhao, Liang; Liu, Peizhong; Huang, Detian

doi:10.1007/s11042-017-5090-2

Cited by 122 publications

(56 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Non-temporal detection models are highly suited to the non- stationary fire detection scenario posed by the future use of autonomous systems in a fire fighting context [23]. Within this work we show that comparable fire detection results are achievable to the recent temporally dependent work of [21,20,22], both exceeding the prior non-temporal approach of Chenebert et al [17] and within significantly lower CNN model complexity than the recent work of [22]. Our reduced complexity network architectures are experimentally defined as architectural subsets of seminal CNN architectures offering maximal performance for the fire detection task.…”

mentioning

confidence: 52%

“…Overall we show that reduced complexity CNN, experimentally defined from leading architectures in the field, can achieve 0.93 accuracy for the binary classification task of fire detection. This significantly outperforms prior work in the field on non-temporal fire detection [17] at lower complexity than prior CNN based fire detection [22]. Furthermore, reduced complexity FireNet and InceptionV1-OnFire architectures offer classification accuracy within less than 1% of their more complex parent architectures at 3-4× of the speed (FireNet offering 17 fps).…”

Section: Discussionmentioning

confidence: 85%

“…Here, by contrast to previous classifier-driven work [3,16,4,21,20,22], we instead consider a non-temporal classification model for fire detection following the theme non-temporal fire detection championed by Chenebert et al [17] and further supporting by the non-stationary camera visual fire detection challenge posed by Steffans et al [23]. Non-temporal detection models are highly suited to the non- stationary fire detection scenario posed by the future use of autonomous systems in a fire fighting context [23].…”

mentioning

confidence: 94%

“…Other recent approaches consider the use shape-invariant features [18] or simple patches [19] within varying machine learning approaches. However, the majority of recent work is temporally dependent considering a range of dynamic features [20] and motion characteristics [21,22] between consecutive video frames with the most recent work of [22] considering convolutional neural networks (CNN) for fire detection within this context.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Experimentally Defined Convolutional Neural Network Architecture Variants for Non-Temporal Real-Time Fire Detection

Dunnings

Breckon

2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this work we investigate the automatic detection of fire pixel regions in video (or still) imagery within real-time bounds without reliance on temporal scene information. As an extension to prior work in the field, we consider the performance of experimentally defined, reduced complexity deep convolutional neural network architectures for this task. Contrary to contemporary trends in the field, our work illustrates maximal accuracy of 0.93 for whole image binary fire detection, with 0.89 accuracy within our superpixel localization framework can be achieved, via a network architecture of signficantly reduced complexity. These reduced architectures additionally offer a 3-4 fold increase in computational performance offering up to 17 fps processing on contemporary hardware independent of temporal information. We show the relative performance achieved against prior work using benchmark datasets to illustrate maximally robust real-time fire region detection.

show abstract

mentioning

confidence: 52%

Section: Discussionmentioning

confidence: 85%

mentioning

confidence: 94%

mentioning

confidence: 99%

See 2 more Smart Citations

Experimentally Defined Convolutional Neural Network Architecture Variants for Non-Temporal Real-Time Fire Detection

Dunnings

Breckon

2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Hu [6] proposes a spatial-temporal architecture for a multitask learning to recognize smoke and estimate optical flow simultaneously. Luo [7] introduces a smoke detection algorithm based on the combination of motion characteristic and convolutional neural network (CNN). Xu designs a deep domain adaptation network in [8] for smoke recognition using synthetic smoke images.…”

Section: Introductionmentioning

confidence: 99%

Video smoke detection based on deep saliency network

Zhang

et al. 2019

Fire Safety Journal

View full text Add to dashboard Cite

Video smoke detection is a promising fire detection method especially in open or large spaces and outdoor environments. Traditional video smoke detection methods usually consist of candidate region extraction and classification, but lack powerful characterization for smoke. In this paper, we propose a novel video smoke detection method based on deep saliency network. Visual saliency detection aims to highlight the most important object regions in an image. The pixel-level and object-level salient convolutional neural networks are combined to extract the informative smoke saliency map. An end-to-end framework for salient smoke detection and existence prediction of smoke is proposed for application in video smoke detection. The deep feature map is combined with the saliency map to predict the existence of smoke in an image. Initial and augmented dataset are built to measure the performance of frameworks with different design strategies.Qualitative and quantitative analysis at frame-level and pixel-level demonstrate the excellent performance of the ultimate framework.

show abstract

An efficient fire detection algorithm based on multi‐scale convolutional neural network

et al. 2021

View full text Add to dashboard Cite

Video fire detection (VFD) technology has shown a broad application prospect with the popularization of camera monitoring systems. Since the initial stage is the best time for firefighting, it's crucial to develop a robust algorithm for early warning. In this paper, an efficient VFD fusion algorithm is presented. First, the fire candidate areas (FCA) are located quickly based on low-level visual features to guarantee well timeliness. Furthermore, a multi-scale convolutional neural network with spatial pyramid pooling is built and trained on the dedicated flame data set without the requirement of sample labeling. In this case, FCA with different aspect ratios and scales can be accurately identified. The method is fully tested on various databases of arbitrarysized images and videos. Experimental results show that the proposed fusion algorithm, in addition to improving the detection efficiency, also ensures the accurate identification of flames on different scales.

show abstract

Fire smoke detection algorithm based on motion characteristic and convolutional neural networks

Cited by 122 publications

References 25 publications

Experimentally Defined Convolutional Neural Network Architecture Variants for Non-Temporal Real-Time Fire Detection

Experimentally Defined Convolutional Neural Network Architecture Variants for Non-Temporal Real-Time Fire Detection

Video smoke detection based on deep saliency network

An efficient fire detection algorithm based on multi‐scale convolutional neural network

Contact Info

Product

Resources

About