Fire Flame Detection Research Articles

An attention-based dual-encoding network for fire flame detection using optical remote sensing

Automatic extraction of flame area plays an important role in forest fire detection, which can accurately understand the spatial distribution and development trend of forest fire, so as to effectively realize the protection of forest resources. However, due to the instability and spread of fires, and the complexity of the background, accurate early fire detection is extremely challenging. At the same time, the image pixel proportion of the flame area in early stage is much smaller than that in the background, which causes a serious class imbalance problem. With the fast development of deep learning, some achievements have been made in flame extraction, but there are still some deficiencies in the existing networks, such as limited feature representation, poor feature capturing ability on micro objects, insufficiency processing of local features, etc. This paper proposes an attention-based dual-encoding segmentation network, abbreviated as ADE-Net, for pixelwise early fire detection. To realize strong feature representation, a dual-encoding path, consisting of semantic units and spatial units, is introduced to extract richer features, and an attention fusion module (AFM) is introduced to fully integrate spatial and semantic information and achieve effective feature aggregation. In addition, faced with the class imbalance problem, a multi-attention fusion (MAF) module is introduced to obtain more discriminating features to make the segmentation network to focus on the key pixel areas. Furthermore, a feature enhancement module, named attention-guided enhancement (AGE) module, is proposed to enrich the feature representation of local feature maps. Finally, to realize better multi-scale global feature extraction and fusion, a global context fusion (GCF) module is proposed into the bottleneck layer for multi-scale feature enhancement. Experimental results show that the proposed ADE-Net has a good early fire detection ability from remote sensing images, and it has obtained a competitive advantage compared with advanced segmentation models.

Visually activated sprinklers applied in atria to mitigate the interaction of water spray with the smoke layer

This research investigates the fire suppression effectiveness of sprinklers in a large atrium of a public transport hub in Taipei, Taiwan, during a fire using FDS. The thermally-activated sprinkler had the shortcoming of delayed activation, with a thick smoke layer accumulating at the ceiling. Thereafter, the interaction of sprinkler spray with the thick smoke layer would cause a large amount of smoke falling to the floor level, significantly impacting safe egress. The novelty of this study is to couple a sprinkler system with a vision-based fire flame detection system (VFDS) having the advantage of locating the fire instantly to suppress fire. A combination of different atrium heights, fire sizes, and scenarios for a total of 27 cases were investigated. The research results have indicated that VFDS-activated sprinklers can suppress an atrium fire at the early stage, greatly reduce the amount of smoke generation and smoke accumulation. In consequence, the interaction of water spray and smoke layer is largely mitigated to prevent early fall of smoke. When the fire is suppressed, the atrium can maintain a clear height that is crucial to safe egress. The research finding of VFDS-activated sprinklers system is significant for fire safety of buildings with large atria.

Research on Flame Image Detection

Fire flame detection can reduce the damage of people’s life and property in maximum. We analysis the significant characteristics such as color feature, sharp corners, flicker frequency, change of area, flame core features such as the relative area in the suspected areas as fire classification. Through the characteristics of the fire video image analysis, first, select color features to pre-judge, then couple with area change rate and sharp corners to determine the false fire target, last, adapt the algorithm to tall space, outdoor environment and some fire detection under complicated environment. Comparing with traditional detection, the algorithm can find the fire accurately and timely, reduce the amount of calculation, improves fire recognition accuracy, and reduce false positives omission phenomenon.

Real‐time multi‐feature based fire flame detection in video

In this study, the authors present a new approach to detect fire flame by processing and analysing the stationary camera videos. For a fire detection system, it is desired to be sensitive and reliable. The proposed method improves not only the sensitivity but also the reliability through reducing the susceptibility to false alarms. The proposed approach based on multi-feature, i.e. chromatic features, dynamic features, texture features, and contour features, can both improve the sensitivity and reliability in fire detection. In their approach, the authors adopt a novel algorithm to extract the moving region and analyse the frequency of flickers. Experimental results show that the proposed method can run in real-time and performs favourably against the state-of-the-art methods with higher accuracy in fire videos, lower false alarm rates in non-fire videos and faster response time.

A new PSO-based approach to fire flame detection using K-Medoids clustering

Automated computer vision-based fire detection has gained popularity in recent years, as every fire detection needs to be fast and accurate. In this paper, a new fire detection method using image processing techniques is proposed. We explore how to create a fire flame-based colour space via a linear multiplication of a conversion matrix and colour features of a sample image. We show how the matrix multiplication can result in a differentiating colour space, in which the fire part is highlighted and the non-fire part is dimmed. Particle Swarm Optimization (PSO) and sample pixels from an image are used to obtain the weights of the colour-differentiating conversion matrix, and K-medoids provides a fitness metric for the PSO procedure. The obtained conversion matrix can be used for fire detection on different fire images without performing the PSO procedure. This allows a fast and easy implementable fire detection system. The empirical results indicate that the proposed method provides both qualitatively and quantitatively better results when compared to some of the conventional and state-of-the-art algorithms.

Fast fire flame detection in surveillance video using logistic regression and temporal smoothing

Real-time detection of fire flame in video scenes from a surveillance camera offers early warning to ensure prompt reaction to devastating fire hazards. Many existing fire detection methods based on computer vision technology have achieved high detection rates, but often with unacceptably high false-alarm rates. This paper presents a reliable visual analysis technique for fast fire flame detection in surveillance video using logistic regression and temporal smoothing. A candidate fire region is determined according to the color component ratio and motion cue of fire flame obtained by background subtraction. The candidate fire region is examined for genuine fire flame in terms of the proposed fire probability computed using logistic regression of prominent features of size, motion, and color information. Temporal smoothing is employed to reduce false alarm rates at a slight decrease in sensitivity. Experiments conducted on various benchmarking databases demonstrate that the proposed scheme successfully distinguishes fire flame from the background as well as moving fire-like objects in real-world indoor and outdoor video surveillance settings. The average time to fire detection was fastest among the state-of-the-art video-based fire flame detection techniques for comparison.

Spatio-Temporal Flame Modeling and Dynamic Texture Analysis for Automatic Video-Based Fire Detection

Every year, a large number of wildfires all over the world burn forested lands, causing adverse ecological, economic, and social impacts. Beyond taking precautionary measures, early warning and immediate response are the only ways to avoid great losses. To this end, in this paper we propose a computer vision approach for fire-flame detection to be used by an early-warning fire monitoring system. Initially, candidate fire regions in a frame are defined using background subtraction and color analysis based on a nonparametric model. Subsequently, the fire behavior is modeled by employing various spatio-temporal features, such as color probability, flickering, spatial, and spatio-temporal energy, while dynamic texture analysis is applied in each candidate region using linear dynamical systems and a bag-of-systems approach. To increase the robustness of the algorithm, the spatio-temporal consistency energy of each candidate fire region is estimated by exploiting prior knowledge about the possible existence of fire in neighboring blocks from the current and previous video frames. As a final step, a two-class support vector machine classifier is used to classify the candidate regions. Experimental results have shown that the proposed method outperforms existing state-of-the-art algorithms.

Flame Recognition Based on Video Image

The flame recognition system based on video image is applied to the fire flame detection, and it can be very good to avoid the shortage of the traditional fire flame detection system. Three frame difference algorithm is adopted to extract the motion features of the flame. And Lab color space is applied in analyzing the flame color. By analyzing the circular degree of the flame and the interference sources, the change rate of the flame area and the angle feature of the fire flame, it can be determined whether there is a fire in the image. The experimental results shows: this algorithm can not only effectively improve the accuracy and real-time performance of the flame detection and identification, but also eliminate the interference of other substances and reduce the misjudgment.

Color model and method for video fire flame and smoke detection using Fisher linear discriminant

Video fire detection is playing an increasingly important role in our life. But recent research is often based on a traditional RGB color model used to analyze the flame, which may be not the optimal color space for fire recognition. It is worse when we research smoke simply using gray images instead of color ones. We clarify the importance of color information for fire detection. We present a fire discriminant color (FDC) model for flame or smoke recognition based on color images. The FDC models aim to unify fire color image representation and fire recognition task into one framework. With the definition of between-class scatter matrices and within-class scatter matrices of Fisher linear discriminant, the proposed models seek to obtain one color-space-transform matrix and a discriminate projection basis vector by maximizing the ratio of these two scatter matrices. First, an iterative basic algorithm is designed to get one-component color space transformed from RGB. Then, a general algorithm is extended to generate three-component color space for further improvement. Moreover, we propose a method for video fire detection based on the models using the kNN classifier. To evaluate the recognition performance, we create a database including flame, smoke, and nonfire images for training and testing. The test experiments show that the proposed model achieves a flame verification rate receiver operating characteristic (ROC I) of 97.5% at a false alarm rate (FAR) of 1.06% and a smoke verification rate (ROC II) of 91.5% at a FAR of 1.2%, and lots of fire video experiments demonstrate that our method reaches a high accuracy for fire recognition.

A Real-time Video Fire Flame and Smoke Detection Algorithm

Real-time video fire flame and smoke detection method based on foreground image accumulation and optical flow technique is presented. Accumulation images are calculated of the foreground images which are extracted using frame differential method. Two parameters are used for the foreground image accumulation to differentiate flame candidate areas from that of smoke. The flame regions are recognized by a statistical model build by foreground accumulation image, while the optical flow is calculated and a motion feature discriminating model to recognize smoke regions is used. The algorithm could realize the real-time fire detection of the following three detection cases: fire with flame and none smoke, fire with smoke and none flame, and fire with both flame and smoke.

Fire flame detection based on GICA and target tracking

To improve the video fire detection rate, a robust fire detection algorithm based on the color, motion and pattern characteristics of fire targets was proposed, which proved a satisfactory fire detection rate for different fire scenes. In this fire detection algorithm: (a) a rule-based generic color model was developed based on analysis on a large quantity of flame pixels; (b) from the traditional GICA (Geometrical Independent Component Analysis) model, a Cumulative Geometrical Independent Component Analysis (C-GICA) model was developed for motion detection without static background and (c) a BP neural network fire recognition model based on multi-features of the fire pattern was developed. Fire detection tests on benchmark fire video clips of different scenes have shown the robustness, accuracy and fast-response of the algorithm.

Fire flame detection in video sequences using multi-stage pattern recognition techniques

In this paper, we propose an effective technique that is used to automatically detect fire in video images. The proposed algorithm is composed of four stages: (1) an adaptive Gaussian mixture model to detect moving regions, (2) a fuzzy c-means (FCM) algorithm to segment the candidate fire regions from these moving regions based on the color of fire, (3) special parameters extracted based on the tempo-spatial characteristics of fire regions, and (4) a support vector machine (SVM) algorithm using these special parameters to distinguish between fire and non-fire. Experimental results indicate that the proposed method outperforms other fire detection algorithms, providing high reliability and a low false alarm rate.

Modeling and Formalization of Fuzzy Finite Automata for Detection of Irregular Fire Flames

Fire-flame detection using a video camera is difficult because a flame has irregular characteristics, i.e., vague shapes and color patterns. Therefore, in this paper, we propose a novel fire-flame detection method using fuzzy finite automata (FFA) with probability density functions based on visual features, thereby providing a systemic approach to handling irregularity in computational systems and the ability to handle continuous spaces by combining the capabilities of automata with fuzzy logic. First, moving regions are detected via background subtraction, and the candidate flame regions are then identified by applying flame color models. In general, flame regions have a continuous irregular pattern; therefore, probability density functions are generated for the variation in intensity, wavelet energy, and motion orientation and applied to the FFA. The proposed algorithm is successfully applied to various fire/non-fire videos, and its detection performance is better than that of other methods.

Nonparametric membership functions and fuzzy logic for vision sensor-based flame detection

This paper proposes an advanced fire-flame detection algorithm using camera images for a better performance than conventional sensor-based systems that are limited to a small area. First, candidate flame regions are detected from the captured images using a background model and flame-color model. After forming probability density functions for the intensity variation, wavelet energy, and motion orientation on a time axis, these probability density functions are changed into membership functions for fuzzy logic. Finally, the result function is made by defuzzification, and the probability value of a fire flame is estimated. The proposed algorithm is successfully applied to various fire videos, including indoor and outdoor fires, and shows a better detection performance when compared with other methods.

Simultaneous detection of ultraviolet and infrared radiation in a single GaN/GaAlN heterojunction

Results are presented for a dual-band detector that simultaneously detects UV radiation in the 250-360 nm and IR radiation in the 5-14 microm regions with near zero spectral cross talk. In this detector having separate UV- and IR-active regions with three contacts (one common contact for both regions) allows the separation of the UV and IR generated photocurrent components, identifying the relative strength of each component. This will be an important development in UV-IR dual-band applications such as fire-flame detection, solar astronomy, and military sensing, eliminating the difficulties of employing several individual detectors with separate electronics-cooling mechanisms.