Fire Detection from Images Using Faster R-CNN and Multidimensional Texture Analysis

Barmpoutis, Panagiotis; Dimitropoulos, Kosmas; Kaza, Kyriaki; Grammalidis, Nikos

doi:10.1109/icassp.2019.8682647

Cited by 92 publications

(60 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Zhang et al 2018;Q.X. Zhang 2018;Yuan et al 2018;Akhloufi et al 2018;Barmpoutis et al 2019;Jakubowski et al 2019;Sousa et al 2019;, T. Li et al 2019Muhammad et al 2018;Wang et al 2019). Of particular note, Q.X.…”

Section: Fire Detectionunclassified

“…Of particular note, Q.X. found that CNNs outperformed a SVM-based method, and Barmpoutis et al (2019) found that a faster region-based CNN outperformed another CNN based on YOLO ("you only look once"). Yuan et al (2018) used CNN combined with optical flow to include time-dependent information.…”

Section: Fire Detectionmentioning

confidence: 99%

“…By comparison, the SVM-based method, which was unable to extract spatial features, only had an accuracy of 43%. Alexandrov et al (2019) found that YOLO was both faster and more accurate than a region-based CNN method in contrast to Barmpoutis et al (2019).…”

Section: Fire Detectionmentioning

confidence: 99%

See 2 more Smart Citations

A review of machine learning applications in wildfire science and management

et al. 2020

View full text Add to dashboard Cite

Artiﬁcial intelligence has been applied in wildﬁre science and management since the 1990s, with early applications including neural networks and expert systems. Since then the ﬁeld has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildﬁre science and management. Our overall objective is to improve awareness of ML methods among wildﬁre researchers and managers, as well as illustrate the diverse and challenging range of problems in wildﬁre science available to ML data scientists. To that end, we ﬁrst present an overview of popular ML approaches used in wildﬁre science to date, and then review the use of ML in wildﬁre science as broadly categorized into six problem domains, including: 1) fuels characterization, ﬁre detection, and mapping; 2) ﬁre weather and climate change; 3) ﬁre occurrence, susceptibility, and risk; 4) ﬁre behavior prediction; 5) ﬁre eﬀects; and 6) ﬁre management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildﬁres within a data science context. In total, we identfied 300 relevant publications up to the end of 2019, where the most frequently used ML methods across problem domains included random forests, MaxEnt, artiﬁcial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent based learning — in the wildﬁre sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML methods to learn on their own, expertise in wildﬁre science is necessary to ensure realistic modelling of ﬁre processes across multiple scales, while the complexity of some ML methods, such as deep learning, requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildﬁre research and management communities play an active role in providing relevant, high quality, and freely available wildﬁre data for use by practitioners of ML methods.

show abstract

Section: Fire Detectionunclassified

Section: Fire Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A review of machine learning applications in wildfire science and management

et al. 2020

View full text Add to dashboard Cite

show abstract

“…After the clustering of a fire image, a GoogleNet [28] or simpler network is applied to classify the super-pixels of a real fire. In addition, Barmpoutis et al [30] proposed a fire detection method in which Faster R-CNN [31] was applied followed by an analysis of the multi-dimensional textures in the candidate fire regions.…”

Section: Machine Learning and Deep Learning-based Fire Detectionmentioning

confidence: 99%

Two-Step Real-Time Night-Time Fire Detection in an Urban Environment Using Static ELASTIC-YOLOv3 and Temporal Fire-Tube

Park

2020

Sensors

View full text Add to dashboard Cite

While the number of casualties and amount of property damage caused by fires in urban areas are increasing each year, studies on their automatic detection have not maintained pace with the scale of such fire damage. Camera-based fire detection systems have numerous advantages over conventional sensor-based methods, but most research in this area has been limited to daytime use. However, night-time fire detection in urban areas is more difficult to achieve than daytime detection owing to the presence of ambient lighting such as headlights, neon signs, and streetlights. Therefore, in this study, we propose an algorithm that can quickly detect a fire at night in urban areas by reflecting its night-time characteristics. It is termed ELASTIC-YOLOv3 (which is an improvement over the existing YOLOv3) to detect fire candidate areas quickly and accurately, regardless of the size of the fire during the pre-processing stage. To reflect the dynamic characteristics of a night-time flame, N frames are accumulated to create a temporal fire-tube, and a histogram of the optical flow of the flame is extracted from the fire-tube and converted into a bag-of-features (BoF) histogram. The BoF is then applied to a random forest classifier, which achieves a fast classification and high classification performance of the tabular features to verify a fire candidate. Based on a performance comparison against a few other state-of-the-art fire detection methods, the proposed method can increase the fire detection at night compared to deep neural network (DNN)-based methods and achieves a reduced processing time without any loss in accuracy.

show abstract

“…Additionally, scene complexity and low-video quality can affect the robustness of vision-based flame detection algorithms, thus increasing the false alarm rate. Barmpoutis et al [34,35] also asserted that high false alarm rates are caused by natural objects, which have similar characteristics with flame, and by the variation of flame appearance. Other causes have claimed environmental changes that complicate fire detection including clouds, movement of rigid body objects in the scene, and sun and light reflections.…”

Section: Introductionmentioning

confidence: 99%

False Positive Decremented Research for Fire and Smoke Detection in Surveillance Camera using Spatial and Temporal Features Based on Deep Learning

Lee

Shim

2019

Electronics

View full text Add to dashboard Cite

Fire must be extinguished early, as it leads to economic losses and losses of precious lives. Vision-based methods have many difficulties in algorithm research due to the atypical nature fire flame and smoke. In this study, we introduce a novel smoke detection algorithm that reduces false positive detection using spatial and temporal features based on deep learning from factory installed surveillance cameras. First, we calculated the global frame similarity and mean square error (MSE) to detect the moving of fire flame and smoke from input surveillance cameras. Second, we extracted the fire flame and smoke candidate area using the deep learning algorithm (Faster Region-based Convolutional Network (R-CNN)). Third, the final fire flame and smoke area was decided by local spatial and temporal information: frame difference, color, similarity, wavelet transform, coefficient of variation, and MSE. This research proposed a new algorithm using global and local frame features, which is well presented object information to reduce false positive based on the deep learning method. Experimental results show that the false positive detection of the proposed algorithm was reduced to about 99.9% in maintaining the smoke and fire detection performance. It was confirmed that the proposed method has excellent false detection performance.

show abstract

Fire Detection from Images Using Faster R-CNN and Multidimensional Texture Analysis

Cited by 92 publications

References 17 publications

A review of machine learning applications in wildfire science and management

A review of machine learning applications in wildfire science and management

Two-Step Real-Time Night-Time Fire Detection in an Urban Environment Using Static ELASTIC-YOLOv3 and Temporal Fire-Tube

False Positive Decremented Research for Fire and Smoke Detection in Surveillance Camera using Spatial and Temporal Features Based on Deep Learning

Contact Info

Product

Resources

About