Saliency Based Fire Detection Using Texture and Color Features

Jamali, Maedeh; Karimi, Nader; Samavi, Shadrokh

doi:10.1109/icee50131.2020.9260659

Cited by 7 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to locate the hotspot position, color filtration [41], [42] is applied to the image. Depending on the flame's temperature [43], [44], a hotspot color could range from yellow to brownish. This color dynamic is easier to be mapped using HSV [45] color model [46].…”

Section: Methodsmentioning

confidence: 99%

Determining Forest Fire Position from UAV Photogrammetry using Color Filtration Algorithm

Muid

Evita²,

Aminah³

et al. 2022

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Forest fires frequently happen worldwide, especially in the dry season. A forest fire early warning system (EWS) is needed to prevent this disaster. The main part of EWS is the hotspot detection system. On the other side, Unmanned Aerial Vehicle (UAV) technology offers an alternative solution to detect the hotspot for poor satellite image processing accuracy. Remote sensing techniques with UAV working drones are progressively challenging. Drones can provide results in 2D and 3D images with high resolution and real-time. Therefore, in this research, we have used a photogrammetry application from the number of images collected by a UAV with an optimum flight plan for the mission to determine the location of the forest fire. This paper describes remote sensing experiments using drones to detect land fires. The experiment was carried out using a quadcopter drone of the DJI Phantom 4 Pro. The photos are processed using Agisoft Metashape Professional image processing software and become a 2D image. These images captured a fire simulation in a known location. After a high resolution (GSD – Ground Sampling Distance – 0.87cm/px) orthophoto had been generated, a color filtration algorithm detected a hotspot to detect a fire at the exact location. The results are almost zero deviation of longitude and latitude from the real location with 1.44 m2 and 1.06 m2 fire area from 2 experiments. This algorithm program has TPR and FPR are 0,78 and 0, respectively. Further research can develop an EWS with a combination of UAV and Wireless Sensor Networks.

show abstract

Section: Methodsmentioning

confidence: 99%

Determining Forest Fire Position from UAV Photogrammetry using Color Filtration Algorithm

Muid

Evita²,

Aminah³

et al. 2022

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…They combined color and texture features to reduce the false positive rate [30]. Jamali et al [31] combined the same features to detect fire. They used the HSV (Hue Saturation Value) color space as a color descriptor and LBP-TOP (Local Binary Pattern on Three Orthogonal Planes) to model the texture of fire.…”

Section: Feature-based Fire Detection and Segmentation Methodsmentioning

confidence: 99%

Wildfire Segmentation Using Deep Vision Transformers

Ghali

Akhloufi

Jmal³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

In this paper, we address the problem of forest fires’ early detection and segmentation in order to predict their spread and help with fire fighting. Techniques based on Convolutional Networks are the most used and have proven to be efficient at solving such a problem. However, they remain limited in modeling the long-range relationship between objects in the image, due to the intrinsic locality of convolution operators. In order to overcome this drawback, Transformers, designed for sequence-to-sequence prediction, have emerged as alternative architectures. They have recently been used to determine the global dependencies between input and output sequences using the self-attention mechanism. In this context, we present in this work the very first study, which explores the potential of vision Transformers in the context of forest fire segmentation. Two vision-based Transformers are used, TransUNet and MedT. Thus, we design two frameworks based on the former image Transformers adapted to our complex, non-structured environment, which we evaluate using varying backbones and we optimize for forest fires’ segmentation. Extensive evaluations of both frameworks revealed a performance superior to current methods. The proposed approaches achieved a state-of-the-art performance with an F1-score of 97.7% for TransUNet architecture and 96.0% for MedT architecture. The analysis of the results showed that these models reduce fire pixels mis-classifications thanks to the extraction of both global and local features, which provide finer detection of the fire’s shape.

show abstract

“…Sheng et al [6] studied the color, texture, and gray-scale statistical features of flame images and constructed a deep belief network (DBN) for fire detection. Jamali et al [7] introduced texture features based on color features to detect fires. They combined different features to improve the accuracy of the fire detection system.…”

Section: Introductionmentioning

confidence: 99%

Random Forest Feature Selection and Back Propagation Neural Network to Detect Fire Using Video

et al. 2022

View full text Add to dashboard Cite

As the most common serious disaster, fire may cause a lot of damages. Early detection and treatment of fires are of great significance to ensure public safety and to reduce losses caused by fires. However, traditional fire detectors are facing some focus issues such as low sensitivity and limited detection scenes. To overcome these problems, a video fire detection hybrid method based on random forest (RF) feature selection and back propagation (BP) neural network is proposed. The improved flame color model in RGB and HSI space and the visual background extractor (ViBe) in moving target detection algorithm are used to segment the suspected flame regions. Then, multidimensional features of flames are extracted from the suspected regions, and these extracted features are combined and selected according to the RF feature importance analysis. Finally, a BP neural network model is constructed for multifeature fusion and fire recognition. The test results on several experimental video sets show that the proposed method can effectively avoid feature interference and has an excellent recognition effect on fires in a variety of scenarios. The proposed method is applicable for fire recognition applied in video surveillance and detection robots.

show abstract

Saliency Based Fire Detection Using Texture and Color Features

Cited by 7 publications

References 35 publications

Determining Forest Fire Position from UAV Photogrammetry using Color Filtration Algorithm

Determining Forest Fire Position from UAV Photogrammetry using Color Filtration Algorithm

Wildfire Segmentation Using Deep Vision Transformers

Random Forest Feature Selection and Back Propagation Neural Network to Detect Fire Using Video

Contact Info

Product

Resources

About