Image Fire Detection Research Articles

Image fire detection module for automatic fire extinguishing system with unmanned ground vehicles

Especially in responding to large fires, the use of unmanned vehicles can reduce the risk of people getting hurt or encountering situations where they can get hurt. At the same time, the use of unmanned vehicles can increase the efficiency of the intervention. In this direction, one of the most important modules for the unmanned ground vehicles to be used to achieve the desired results is the fire detection module, which will detect the fire and report it to the necessary systems for intervention. In this study, certain deep learning networks were examined for fire detection. These networks are Faster-RCNN, Mask-RCNN, SSD and YOLO. After these networks were trained with the same data sets, they were compared with FPS and mAP data. As a result, it was seen that the YOLO algorithm gave a more positive result than other deep learning networks in terms of both detection and output speed. As a result, YOLO was selected and used as the deep learning network to be used for fire detection.

Unmanned Aerial Vehicle Fire Detection Platform Based on Semantic Yolov5 and Autonomous Recognition

In recent years, as fire image detection has become a research hotspot. One class of methods is color-based methods, which are very sensitive to brightness and shadows. As a result, the number of false alarms generated by these methods is high. Aiming at the task requirements of airborne binocular vision obstacle avoidance and target tracking, this paper establishes the verification platform architecture of UAV (Unmanned Aerial Vehicle) binocular vision obstacle avoidance and target tracking. For the update and maintenance of boundary regions, we can also continuously extract richer information from the boundary, make more elaborate plans, and develop an incremental method to detect locally updated maps within the boundary. The fire point can be independently and quickly identified through deep learning to extinguish the fire accurately. Assuming that the system incorrectly identifies 2 out of 80 non-fire sources as fire sources, so the results indicate a precision of about 88%, a recall of 90%. However, the traditional fire detection is around 80%.

Fire image detection and classification analysis based on VGG16 image processing model

Fire image classification technology refers to the classification and recognition of fire images through computer vision technology in order to take timely countermeasures. With the development of computer vision technology, fire image classification technology has been widely studied and applied. Deep learning techniques have achieved great success in the field of image classification, with researchers classifying and identifying fire images by using deep learning models such as convolutional neural networks. This paper introduces the research background and application of fire image classification technology, and the experimental results of detection and classification analysis of fire image based on vgg16 image processing model. The model can classify and identify fire images well and achieve good prediction effect. The accuracy of training set and test set is stable at 99%, the accuracy and accuracy of the model reach 98%, and the recall rate and F1 score reach 99%. The application of fire image classification technology is of great significance. By using computer vision technology to classify and identify fire images, it can improve the accuracy and efficiency of fire monitoring and early warning system, timely detect and control fire, and reduce the loss caused by fire. At the same time, the continuous development of deep learning technology also provides a broader space for the research and application of fire image classification technology.

Multiscale fire image detection method based on CNN and Transformer

Multiscale fire image detection method based on CNN and Transformer

Early Fire Detection and Alert System using Modified Inception-v3 under Deep Learning Framework

ADSI-2019 report states that there were approximately eleven thousand fire accidents reported across India in 2019. In this article, a deep learning model has been developed for fire and smoke detection from images. In this context, we have modified the Inception Convolution Neural Network of the third version (known as Inception-V3) model which is commonly applied for image classification and object discovery tasks for this work. The modified Inception-V3 has been applied on the fire image dataset including smoke for fire image detection. A new optimization function has been incorporated into this model which reduces the computational cost in an efficient way. We have compared the results such as deep learning-based models as well as early fire detection. In this study, the Inception v3 based model yielded the best result with the least number of false positives as compared to the early investigations.

FOREST FIRE DETECTION USING CONVOLUTIONAL NEURAL NETWORK

Fire outbreaks are a typical occurrence all throughout the world, and the harm they bring to both nature and humans is enormous. In comparison to classic sensor-based fire detection systems, vision-based fire detection systems have recently gained favour. The detection process using image processing techniques, on the other hand, is extremely time consuming. We designed a Convolutional Neural Network-based fire detection technique. Through training with datasets, obtain high-accuracy fire image detection that is consistent with fire detection. In this paper, we propose a system for detecting fire using Convolutional Neural Networks (CNN). This paper critically analyzes the scope of Artificial intelligence for detection with video from CCTV footages. This project uses dataset containing video frames with fire. The data is then preprocessed and use the CNN to build a model to detect fire. The dataset is given as input for validating the algorithm and experiments are noted. This project focus on building high accuracy and cost efficient machine that can be used for fire detection.There are 755 and 244 images in the datasets for fire and non-fire, respectively. There are 999 photos in all. These images were created using fire-related video and some images found on the internet. There are 999 images that have been scaled and reshaped to convert to a training dataset and 999 images that have been resized and reshaped to convert to a testing dataset. Convolution, activation functions, and the max pooling technique are used to train the model. The model is trained by varying batch sizes and epoch values. As a result, we obtain a high accuracy and detection rate. Key words: CNN,fire detection,machine learning.

Fire detection in video surveillances using convolutional neural networks and wavelet transform

Fire is one of the most frequent and common emergencies threatening public safety and social development. Recently, intelligent fire detection technologies represented by convolutional neural networks (CNNs) have been widely concerned by academia and industry, substantially improving detection accuracy. However, CNN-based fire detection systems are still subject to the interference of false alarms and the limitation of computing power. In this paper, taking advantage of traditional spectral analysis in fire image detection technology, a novel Wavelet-CNN method is proposed, which applies the 2D Haar transform to extract spectral features of the image and input them into CNNs at different layer stages. Two classic backbone networks, ResNet50 and MobileNet v2 (MV2) are used to test our method, and experimental results on a benchmark fire dataset and a video dataset show that the method improves fire detection accuracy and reduces false alarms, especially for the light-weight MV2. Despite the low computational needs, the Wavelet-MV2 achieves accuracy that is comparable to state-of-the-art methods.

Fire Detection Using Image Processing

Fire disasters have always been a threat to homes and businesses even with the various systems in place to prevent them. They cause property damage, injuries and even death. Preparedness is vital when dealing with fires. They spread uncontrollably and are difficult to contain. To contain them it is necessary for the fire to be detected early. Image fire detection heavily relies on an algorithmic analysis of images. However, the accuracy is lower, the detection is delayed and in common detection algorithms a large number of computation, including the image features being extracted manually and using machine. Therefore, in this paper, novel image detection which will be based on the advanced object detection like CNN model of YOLO v3 is proposed. The average precision of the algorithm based on YOLO v3 reaches to 81.76% and also it has the stronger robustness of detection performance, thereby satisfying the requirements of the real-time detection.

Research on Fire Image Detection Algorithm of Electrical Substation

In order to quickly identify the fire hazards and formulate the corresponding measures inside the transformer substation. A fire detection algorithm of transformer substation based on block marking is studied. On the basis of the transformer substation monitoring platform, the image of primary equipment in the transformer substation is collected through the video monitoring software. According to the flame characteristics, the affected parts are identified and located by block marking. The fire detection algorithm is realized by using OpenCV. Through the fire identification software, the operation of the equipment can be monitored inside the substation in real time, and the fire hazards can be detected in time. The experimental results show that: through the image preprocessing and block marking, comparing the characteristics of the flame, the monitoring and alarm analysis of the primary equipment area in the transformer substation can be realized, and the rapid response to the fire can be realized accurately.

Using knowledge inference to suppress the lamp disturbance for fire detection

Fire detection in buildings is crucial for people's lives and property. Conventional temperature and smoke sensors have many disadvantages: the limited cover range; detection delays; the difficulty in distinguishing smoke and fire. Recently, research on convolutional neural networks (CNN) for fire image detection has become a hot topic. However, existing fire classification and object detection methods are often interfered with by flashlights, red objects and the high-brightness background, resulting in a high false alarm rate. Besides, light and lamps often exist in buildings. To address this issue, this paper focuses on introducing scene prior knowledge and causal inference mechanisms to suppress the lamp disturbance. Firstly, we train the YoloV3 network to detect and recognize lamps. Secondly, to reduce the dataset bias, we mask the lamp regions with the proposed Local Grabcut segmentation method. Last, compared with direct fire classification methods, our proposed methods reduce about 34.6% false alarm rate based on InceptionV4 networks. The experimental results verify the effectiveness among different CNN architectures (Resnet101, Firenet, Densenet121). The code is online at https://github.com/kailaisun/fire-detection-without-lamp.

Evaluation of image fire detection algorithms based on image complexity

Early fire detection is crucial for reducing losses due to fire. Therefore, the development of an efficient fire detection algorithm and alarm system is essential. The image fire detection algorithm is based on the mathematical analysis of images. Current algorithm evaluation methods are not effective and cannot sufficiently distinguish the performance of different detection algorithms. Therefore, such methods are not conducive for evaluating and improving algorithms. Based on a large-scale fire image dataset, the ground-truth complexity of images was quantified according to the time required for humans to detect the presence or absence of fire in the images. Four image complexity metrics based on the characteristics of fire detection are proposed. A comparison of the ground-truth and predicted scores of image complexity revealed that the comprehensive image complexity metric based on the Inception Resnet -v2 predictor was the most effective measurement. Its predicted scores ranked approximately 85% image pairs in the same order as that of the ground-truth complexity scores. Finally, a novel method for evaluating the performance of an image fire detection algorithm based on image complexity is proposed. Evaluation of the performance of five algorithms revealed that the performance of algorithm differs considerably and the proposed method can accurately determine the detection level of the detection algorithm in different image complexity conditions. The results of the study provide a valuable reference for developing and optimizing detection algorithms.

Image fire detection algorithms based on convolutional neural networks

As a new fire detection technology, image fire detection has recently played a crucial role in reducing fire losses by alarming users early through early fire detection. Image fire detection is based on an algorithmic analysis of images. However, there is a lower accuracy, delayed detection, and a large amount of computation in common detection algorithms, including manually and machine automatically extracting image features. Therefore, novel image fire detection algorithms based on the advanced object detection CNN models of Faster-RCNN, R–FCN, SSD, and YOLO v3 are proposed in this paper. A comparison of the proposed and current algorithms reveals that the accuracy of fire detection algorithms based on object detection CNNs is higher than other algorithms. Especially, the average precision of the algorithm based on YOLO v3 reaches to 83.7%, which is higher than the other proposed algorithms. Besides, the YOLO v3 also has stronger robustness of detection performance, and its detection speed reaches 28 FPS, thereby satisfying the requirements of real-time detection.

Design of Outdoor Fire Intelligent Alarm System Based on Image Recognition

Fire is one of the most common serious disasters in human society. It is a kind of burning phenomenon that is out of control in time and space. When a fire occurs, how to detect the fire quickly and remove it in the budding state has become the key content of fire control work. Outdoor fire is very common in our daily life, and once it occurs without effective and timely control, it will cause huge losses. Therefore, it is particularly important to study an intelligent alarm system for outdoor fire. Generally, fire detection technology can be divided into sensor fire detection technology and image fire detection technology. Sensor fire detection technology is low cost and easy to design, but its application field is limited. Under the interference of many factors outside, misjudgement and missed judgement will occur. Image fire detection technology can achieve certain detection function through manual design of features and classifiers, but there are still defects in the application in the actual diversified environment. With the development of neural network technology in recent years, it has made great breakthroughs in the field of image recognition. Its judgment type is obtained through a large number of data training algorithms. Because of its automatic feature extraction and classification characteristics, it can effectively adapt to the external environment. Therefore, this paper proposes an end-to-end two-stream neural network model to detect fires, uses fire video on the network to train the algorithm, and then uses the fire database to test. Compared with the existing fire detection algorithms, it is found that the proposed method has good practicability and versatility, and provides a good reference for the development of fire detection technology.

A Fire Detection Algorithm Based on Tchebichef Moment Invariants and PSO-SVM

Automatic fire detection, which can detect and raise the alarm for fire early, is expected to help reduce the loss of life and property as much as possible. Due to its advantages over traditional methods, image processing technology has been applied gradually in fire detection. In this paper, a novel algorithm is proposed to achieve fire image detection, combined with Tchebichef (sometimes referred to as Chebyshev) moment invariants (TMIs) and particle swarm optimization-support vector machine (PSO-SVM). According to the correlation between geometric moments and Tchebichef moments, the translation, rotation, and scaling (TRS) invariants of Tchebichef moments are obtained first. Then, the TMIs of candidate images are calculated to construct feature vectors. To gain the best detection performance, a PSO-SVM model is proposed, where the kernel parameter and penalty factor of support vector machine (SVM) are optimized by particle swarm optimization (PSO). Then, the PSO-SVM model is utilized to identify the fire images. Compared with algorithms based on Hu moment invariants (HMIs) and Zernike moment invariants (ZMIs), the experimental results show that the proposed algorithm can improve the detection accuracy, achieving the highest detection rate of 98.18%. Moreover, it still exhibits the best performance even if the size of the training sample set is small and the images are transformed by TRS.

Fire Image Detection System Based on Cloud Workflow

Fire image detection is a kind of important means of early prevention of fire. The current fire image detection is focus on the feature extraction, the concrete algorithm, etc., there is the lack of unified scheduling and the realization of automatic mechanism in the feature extraction of smoke or flame, the integration of all stages and other aspects of cohesion, and there is no uniform model in terms of integration. In addition, the traditional fire image detection system is facing problems such as high investment and insufficient computing capacity. To effectively reduce the detecting and early warning time, in this paper, fire image detection system based on the cloud workflow is studied. In view of the smoke image detection, we have integrated the various key of discrete nodes in fire detection through cloud workflow technology, and connect effectively the other related nodes. By building cloud workflow architecture, we organize and ensure the operation and regulation of the key nodes and their child nodes of child nodes. Through the experimental test, the method reduce the time in the whole process of fire detection, also won't reduce the accuracy of the original mode of fire detection.

Early Image Fire-Detection Based on Maximum Margin Criterion

Nowadays as camera is applied widely, image fire detection becomes much popular. Many researchers are committed to analyze the RGB color model or even gray images. Actually they have some disadvantages. So this paper will present a new model based on Maximum Margin Criterion, a feature extraction criterion. As it is maximizing the difference of between-class scatter matrices and within-class scatter matrices, it does not depend on the nonsingularity of the within-class scatter matrix. First we will introduce the main idea and then give a mathematical description to apply the model to fire detection, with the algorithm we can calculate the result we need. At last we will put them into practice, use a database to do some experiments to present the performance of this method.

Image fire detection based on independent component analysis and support vector machine

Image-based fire detection can effectively solve the problems of large space fire detection contactlessly and rapidly.It is a new research direction in fire detection.Its essential issue is the classification of flames and disruptors.The ordinary detection methods are to extract one or a few characteristics of the flame in the image as a basis for identification.The disadvantages are to need a large number of experiential thresholds and the lower recognition rate by the inappropriate feature selection.Considering the entire characteristics of fire flame,a flame detection method based on Independent Component Analysis(ICA) and Support Vector Machine(SVM) was proposed.Firstly,a series of frames were pre-processed in RGB space.And suspected target areas were extracted depending on the flickering feature and fuzzy clustering analysis.Then the flame image features were described with ICA.Finally,SVM model was used in order to achieve flame recognition.The experimental result shows that the proposed method improves the accuracy and speed of image fire detection in a variety of fire detection environments.

Study of a Video Image Fire Detection System for Protection of Large Industrial Applications and Atria

This paper presents the results of full-scale fire and environmental tests to study the use of a newly developed video image detection (VID) system for the protection of large industrial applications and atria. The detector of this new flame/smoke VID system consists of one color camera, one infrared (IR) camera and one infrared (IR) light source. The effects of VID system variables, fire sources and environments on the performance of the VID system were investigated in a large test atrium facility and in a large burn hall. The VID system demonstrated its capability to work in various challenging fire and environment conditions presented in the study. The field of view and camera position of the VID system had substantial impact on the performance of the VID system in detecting small unobstructed and obstructed fires.

Image fire detection algorithm based on support vector machine

Concerning the shortcomings of traditional fire detection,an image fire detection algorithm based on Support Vector Machine(SVM)was presented,and compared with the image fire detection based on neural network.The results show that the presented algorithm overcame the disadvantages of neural network such as over learning,being easily trapped in local minimum,etc.,and reduced the complexity of doing a lot of experiments and statistical analysis to obtain recognition threshold.The experimental results show that the image fire detection algorithm based on SVM has higher accuracy,and it is effective to solve the recognition with small samples,multi-dimension and nonlinear property.

An automatic fire searching and suppression system for large spaces

An automatic fire searching and suppression system with remote-controlled fire monitors for large spaces is developed. The fire searching method is realized based on computer vision theory via one CCD camera fixed at the end of a fire monitor chamber. While the fire monitor is pivoting, continuous images are taken from the CCD camera and transmitted into a computer. Then the images are processed with an image fire detection method to determine whether a fire occurs in the vision field. Once a fire is detected, it will be automatically located through an image processing algorithm. Displacement and pivot angle of the CCD camera in searching process are the essential parameters to calculate the space coordinates of a fire. When the coordinates of the fire are obtained, the fire monitor can be adjusted to the appropriate direction and elevation to spray according to water pressure.