Fire Detection Using Both Infrared and Visual Images With Application to Unmanned Aerial Vehicle Forest Fire Surveillance

2019 ◽  
Author(s):  
Chi Yuan ◽  
Zhixiang Liu ◽  
Anim Hossain ◽  
Youmin Zhang
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Forest Fire ◽  
Forest Fires ◽  
Low Cost ◽  
Fire Detection ◽  
Visual Images ◽  
Camera System ◽  
Real Time Processing ◽  
Computational Performance ◽  
Aerial Vehicle

Abstract Forest fires are a universal problem that destroy a large amount of natural resources and creates environmental pollution. Forest firefighting is one of today’s most important events for natural and environmental resources protection and conservation. Unmanned aerial vehicle (UAV) with remote sensing system can offer a rapid, safe and low-cost approach for effective forest fire detection which have attracted researchers attention worldwide. In this paper, automatic detection of fire regions using both visual and infrared images is investigated. In order to improve the computational performance to satisfy the requirement of real-time processing, a reduced complexity fusion method is adopted in this research. Through testing the proposed approach on real video sequences, good detection performance is achieved and it is indicated that using multi-modal camera system to detect forest fire with application to firefighting UAV is very promising.

Unmanned Aerial Vehicle (UAV) based Forest Fire Detection and monitoring for reducing false alarms in forest-fires

2020 ◽  
Vol 149 ◽  
pp. 1-16 ◽  
Author(s):  
S. Sudhakar ◽  
V. Vijayakumar ◽  
C. Sathiya Kumar ◽  
V. Priya ◽  
Logesh Ravi ◽  
...  
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Forest Fire ◽  
Forest Fires ◽  
Fire Detection ◽  
False Alarms ◽  
Aerial Vehicle ◽  
Forest Fire Detection

scholarly journals Early Fire Detection Based on Aerial 360-Degree Sensors, Deep Convolution Neural Networks and Exploitation of Fire Dynamic Textures

2020 ◽  
Vol 12 (19) ◽  
pp. 3177 ◽  
Author(s):  
Panagiotis Barmpoutis ◽  
Tania Stathaki ◽  
Kosmas Dimitropoulos ◽  
Nikos Grammalidis
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Forest Fires ◽  
Large Scale ◽  
Computational Cost ◽  
Fire Detection ◽  
Adaptive Method ◽  
Field Of View ◽  
Aerial Vehicle ◽  
Remote Sensing Systems ◽  
Early Fire Detection

The environmental challenges the world faces have never been greater or more complex. Global areas that are covered by forests and urban woodlands are threatened by large-scale forest fires that have increased dramatically during the last decades in Europe and worldwide, in terms of both frequency and magnitude. To this end, rapid advances in remote sensing systems including ground-based, unmanned aerial vehicle-based and satellite-based systems have been adopted for effective forest fire surveillance. In this paper, the recently introduced 360-degree sensor cameras are proposed for early fire detection, making it possible to obtain unlimited field of view captures which reduce the number of required sensors and the computational cost and make the systems more efficient. More specifically, once optical 360-degree raw data are obtained using an RGB 360-degree camera mounted on an unmanned aerial vehicle, we convert the equirectangular projection format images to stereographic images. Then, two DeepLab V3+ networks are applied to perform flame and smoke segmentation, respectively. Subsequently, a novel post-validation adaptive method is proposed exploiting the environmental appearance of each test image and reducing the false-positive rates. For evaluating the performance of the proposed system, a dataset, namely the “Fire detection 360-degree dataset”, consisting of 150 unlimited field of view images that contain both synthetic and real fire, was created. Experimental results demonstrate the great potential of the proposed system, which has achieved an F-score fire detection rate equal to 94.6%, hence reducing the number of required sensors. This indicates that the proposed method could significantly contribute to early fire detection.

scholarly journals REMOTE SPECTRAL IMAGING USING A LOW COST UAV SYSTEM

2015 ◽  
Vol XL-1/W4 ◽  
pp. 25-31 ◽  
Author(s):  
C. Tsouvaltsidis ◽  
N. Zaid Al Salem ◽  
G. Benari ◽  
D. Vrekalic ◽  
B. Quine
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Low Cost ◽  
Soil Health ◽  
Ground Truth ◽  
Bare Soil ◽  
Camera System ◽  
Experimental Procedure ◽  
Field Campaign ◽  
Aerial Vehicle ◽  
Geolocation Accuracy

The purpose of this scientific survey is to support the research being conducted at York University in the field of spectroscopy and nanosatellites using Argus 1000 micro- spectrometer and low cost unmanned aerial vehicle (UAV) system. <br><br> On the CanX-2 mission, the Argus spectrometer observes reflected infrared solar radiation emitted by Earth surface targets as small as 1.5 km within the 0.9-1.7 μm range. However, limitations in the volume of data due to onboard power constraints and a lack of an onboard camera system make it very difficult to verify these objectives using ground truth. In the last five years that Argus has been in operation, we have made over 200 observations over a series of land and ocean targets. <br><br> We have recently examined algorithms to improve the geolocation accuracy of the spectrometer payload and began to conduct an analysis of soil health content using Argus spectral data. A field campaign is used to obtain data to assess geolocation accuracy using coastline crossing detection and to obtain airborne bare soil spectra in ground truth form. The payload system used for the field campaign consists of an Argus spectrometer, optical camera, GPS, and attitude sensors, integrated into a low-cost, unmanned aerial vehicle (UAV), which will be presented along with the experimental procedure and field campaign results.

Computer Vision Method for Forest Fires Detection Based on RGB Images Obtained by Unmanned Motor Glider

2021 ◽  
pp. 71-78
Author(s):  
Michael Yu. Kataev ◽  
Eugene Yu. Kartashov
Keyword(s):  
Unmanned Aerial Vehicles ◽  
Forest Fire ◽  
Forest Fires ◽  
Fire Detection ◽  
Monitoring Systems ◽  
Colour Space ◽  
Fire Monitoring ◽  
Aerial Vehicle ◽  
Rgb Images ◽  
Forest Fire Detection

The article proposes a method (algorithm) of forest fire detection by means of RGB images obtained by using an unmanned aerial vehicle (motor glider). It includes several stages associated with background detection and subtraction and recognition of fire areas by means of RGB colour space. The proposed method was tested using images of forest fires. It is proposed to use unmanned aerial vehicles capable to monitor large areas continuously for several hours. The results of calculations are shown, which demonstrate that the proposed method allows us to detect areas of images occupied by forest fires and may be used in automatic forest fire monitoring systems.

scholarly journals A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN

Forests ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 768
Author(s):  
Jin Pan ◽  
Xiaoming Ou ◽  
Liang Xu
Keyword(s):  
Forest Fire ◽  
Forest Fires ◽  
Learning Strategy ◽  
Early Stage ◽  
Fire Detection ◽  
Surveillance Systems ◽  
Region Detection ◽  
Decision Network ◽  
Fire Smoke ◽  
Weakly Supervised

Forest fires are serious disasters that affect countries all over the world. With the progress of image processing, numerous image-based surveillance systems for fires have been installed in forests. The rapid and accurate detection and grading of fire smoke can provide useful information, which helps humans to quickly control and reduce forest losses. Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection. However, the research of CNN-based region detection and grading of fire is extremely scarce due to a challenging task which locates and segments fire regions using image-level annotations instead of inaccessible pixel-level labels. This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN. The multi-task framework can simultaneously implement the early-stage alarm, region detection, classification, and grading of fire smoke. To provide an accurate segmentation on image-level, we propose the weakly supervised fine segmentation method, which consists of a segmentation network and a decision network. We aggregate image-level information, instead of expensive pixel-level labels, from all training images into the segmentation network, which simultaneously locates and segments fire smoke regions. To train the segmentation network using only image-level annotations, we propose a two-stage weakly supervised learning strategy, in which a novel weakly supervised loss is proposed to roughly detect the region of fire smoke, and a new region-refining segmentation algorithm is further used to accurately identify this region. The decision network incorporating a residual spatial attention module is utilized to predict the category of forest fire smoke. To reduce the complexity of the Faster R-CNN, we first introduced a knowledge distillation technique to compress the structure of this model. To grade forest fire smoke, we used a 3-input/1-output fuzzy system to evaluate the severity level. We evaluated the proposed approach using a developed fire smoke dataset, which included five different scenes varying by the fire smoke level. The proposed method exhibited competitive performance compared to state-of-the-art methods.

scholarly journals Internet of Trees

2021 ◽  
Vol 10 (2) ◽  
pp. 750-753
Keyword(s):  
Forest Fires ◽  
Low Cost ◽  
Web Server ◽  
Fire Risk ◽  
Fire Detection ◽  
Natural Habitats ◽  
The Public ◽  
Recorded Data ◽  
The Impact ◽  
The Internet Of Things

The frequency of the forest fires that have occurred in the different parts of the world, In recent decades significant population problems and causing the death if the wild animals as the impact of these fires extend beyond the destruction of the natural habitats. The proliferation of the Internet of Things industry, resolutions for initial fire detection should be developed. The valuation of the fire risk of an area and communication of this realities to the population could reduce the amount of fires originated by accident or due to carelessness of the public user. This paper proposes a low-cost network based on NXP Rapid IOT kit and Long Range (Lora) technology to autonomously estimate the level of fire risk in the forest. The system comprises of NXP Rapid IOT kit which humidity, air quality and detection of the tree fall. The data from each node stored and processed in a in a web server or the mobile application that sendsthe recorded data to a web server for graphical conception of collected data.

Sign in / Sign up

Export Citation Format

Share Document