Flame Detection Using Appearance-Based Pre-Processing and Convolutional Neural Network

Ryu, Jin-Kyu; Kwak, D.

doi:10.3390/app11115138

Cited by 29 publications

(13 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [27] proposed to integrate the bottom color features and motion features of the flame to design a multistage flame detection method, but failed to detect the flame object in real time. As shown above, most research on flame-based detection focuses on dynamic detection, which can achieve better results than static detection [28].…”

Section: B Related Workmentioning

confidence: 99%

A Deep Learning-Based Experiment on Forest Wildfire Detection in Machine Vision Course

Wang

Zhang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

As an interdisciplinary course, Machine Vision combines AI and digital image processing methods. This paper develops a comprehensive machine vision experiment on forest wildfire detection that organically integrates digital image processing, machine learning and deep learning technologies. Although the research on wildfire detection has made great progress, many experiments are not suitable for students to operate. Also, the detection with high accuracy is still a big challenge. In this paper, we divide the task of forest wildfire detection into two modules, which are wildfire image classification and wildfire region detection. We propose a novel wildfire image classification algorithm based on Reduce-VGGnet, and a wildfire region detection algorithm based on the optimized CNN with the combination of spatial and temporal features. The experimental results show that the proposed Reduce-VGGNet model can reach 91.20% in accuracy, and the optimized CNN model with the combination of spatial and temporal features can reach 97.35% in accuracy. Our framework is a novel way to combine research and teaching. It can achieve good detection performance and can be used as a comprehensive experiment for Machine Vision course, which can provide the support for talent cultivation in machine vision area.

show abstract

Section: B Related Workmentioning

confidence: 99%

A Deep Learning-Based Experiment on Forest Wildfire Detection in Machine Vision Course

Wang

Zhang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Assume that the image plane coordinates of point 𝑃 are 𝑋 and 𝑌 , and the pixel coordinates are 𝑢 and 𝑣. The camera coordinates to the image plane coordinate can be converted by similar triangles in the imaging model, as shown in Equation (8).…”

Section: Geometric Modelmentioning

confidence: 99%

“…In order to get the three-dimensional coordinates of the point P (X, Y, Z), we also need to calculate the x-axis and y-axis values. Assume that the image plane coordinates of point P are X P and Y P , and the pixel coordinates are u and v. The camera coordinates to the image plane coordinate can be converted by similar triangles in the imaging model, as shown in Equation (8).…”

Section: Geometric Modelmentioning

confidence: 99%

“…Traditional forest fire recognition algorithm depends heavily on man-made flame characteristics, such as color, texture, shape, spatial relationship, and temporal relationship. Ryu et al [8] used HSV color conversion and Harris corner detection in the image preprocessing step. They extracted the corner point facing the upper direction nearby as a region of interest (ROI).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Vision-Based Detection and Spatial Localization Scheme for Forest Fire Inspection from UAV

et al. 2022

Forests

View full text Add to dashboard Cite

Forest fires have the characteristics of strong unpredictability and extreme destruction. Hence, it is difficult to carry out effective prevention and control. Once the fire spreads, devastating damage will be caused to natural resources and the ecological environment. In order to detect early forest fires in real-time and provide firefighting assistance, we propose a vision-based detection and spatial localization scheme and develop a system carried on the unmanned aerial vehicle (UAV) with an OAK-D camera. During the high incidence of forest fires, UAVs equipped with our system are deployed to patrol the forest. Our scheme includes two key aspects. First, the lightweight model, NanoDet, is applied as a detector to identify and locate fires in the vision field. Techniques such as the cosine learning rate strategy and data augmentations are employed to further enhance mean average precision (mAP). After capturing 2D images with fires from the detector, the binocular stereo vision is applied to calculate the depth map, where the HSV-Mask filter and non-zero mean method are proposed to eliminate the interference values when calculating the depth of the fire area. Second, to get the latitude, longitude, and altitude (LLA) coordinates of the fire area, coordinate frame conversion is used along with data from the GPS module and inertial measurement unit (IMU) module. As a result, we experiment with simulated fire in a forest area to test the effectiveness of this system. The results show that 89.34% of the suspicious frames with flame targets are detected and the localization error of latitude and longitude is in the order of 10−5 degrees; this demonstrates that the system meets our precision requirements and is sufficient for forest fire inspection.

show abstract

“…The wavelet coefficients that correspond to the extracted fire features are fed as inputs to train a selected class of DNNs to classify fire and non-fire events i.e., fire categories and human motion, within the viewing range of the PIR sensor. Image pre-processing increases the accuracy of flame recognition rate in DNNs [21,22]. Conventional machine learning approaches need a considerable amount of expertise to extract features, classify them, and predict a fire spread.…”

Section: Introductionmentioning

confidence: 99%

Development of an Early Fire Detection Technique Using a Passive Infrared Sensor and Deep Neural Networks

Xavier

Nanayakkara

2022

Fire Technol

View full text Add to dashboard Cite

Early detection of fire is key to mitigate fire related damages. This paper presents a differential pyro-electric infrared (PIR) sensor and deep neural networks (DNNs) based method to detect fire in real-time. Since the PIR sensor is sensitive to sudden body motions and emits a continuous time-varying signal, experiments are carried out to collect human and fire motions using a PIR sensor. These signals are processed using one-dimensional continuous wavelet transform to perform feature extraction. The corresponding wavelet coefficients are converted into RGB spectrum images that are then used as inputs for a deep convolutional neural network. Various pre-trained DNN architectures are adopted to train and identify the collected data for background (no motion), human motion, and fire categories: small quasi-static and spreading fires. Experimental results show that the ShuffleNet architecture yields the highest prediction accuracy of 87.8%. Experimental results for the real-time strategy which works at a speed of 12 frames-per-second show 95.34% and 92.39% fire and human motion detection accuracy levels respectively.

show abstract

Flame Detection Using Appearance-Based Pre-Processing and Convolutional Neural Network

Cited by 29 publications

References 29 publications

A Deep Learning-Based Experiment on Forest Wildfire Detection in Machine Vision Course

A Deep Learning-Based Experiment on Forest Wildfire Detection in Machine Vision Course

A Vision-Based Detection and Spatial Localization Scheme for Forest Fire Inspection from UAV

Development of an Early Fire Detection Technique Using a Passive Infrared Sensor and Deep Neural Networks

Contact Info

Product

Resources

About