ArticlePDF Available

Real-time forest fire monitoring system using unmanned aerial vehicle

Authors:

Abstract and Figures

The main focus of this research is to develop a real-time forest fire monitoring system using an Unmanned Aerial Vehicle (UAV). The UAV is equipped with sensors, a mini processor (Raspberry Pi) and Ardu Pilot Mega (APM) for the flight controller. This system used five sensors. The first is a temperature sensor that served to measure the temperature in the monitored forest area. The others sensors are embedded in the APM. There are a barometer, Global Positioning Sensor (GPS), inertial measurement unit (IMU) and compass sensor. GPS and compass are used in the navigation system. The barometer measured the air pressure that is used as a reference to maintain the height of the UAV. The IMU consists of accelerometer and gyroscope sensors that are used to estimate the vehicle position. The temperature data from the sensor and the data from GPS are processed by the Raspberry Pi 3, which serves as a mini processor. The results of the data processing are sent to the server to be accessible online and real-time on the website. The data transmission used the Transmission Control Protocol (TCP) system. The experimental setup was carried out in an area of 40 meters × 40 meters with 10 hotspots. The diameter of the hotspots is 0.4 meters with a height of 0.5 meters. The UAV is flown at a constant speed of 5 m/s at an altitude of 20 meters above the ground. The flight path is set by using a mission planner so the UAV can fly autonomously. The experimental results show that the system could detect seven hotspots in the first trial and nine hotspots in the second trial. This happened because there is some data loss in the transmission process. Other results indicate that the coordinates of hotspots detected by the UAV have a deviation error of approximately 1 meter from the actual fire point coordinates. This is still within the standard GPS accuracy as this system uses GPS with a range accuracy of 2.5 meters.
Content may be subject to copyright.
Journal of Engineering Science and Technology
Vol. 13, No. 6 (2018) 1587 - 1594
© School of Engineering, Taylor’s University
1587
REAL-TIME FOREST FIRE MONITORING
SYSTEM USING UNMANNED AERIAL VEHICLE
ENI DWI WARDIHANI*, MAGFUR RAMDHANI, AMIN SUHARJONO,
THOMAS AGUNG SETYAWAN, SIDIQ SYAMSUL HIDAYAT, HELMY,
SARONO WIDODO, EDDY TRIYONO, FIRDANIS SAIFULLAH
Department of Electrical Engineering, Politeknik Negeri Semarang, Jl. Prof. H. Soedharto,
S.H., Tembalang, Semarang, Jawa Tengah, 50275, Indonesia
*Corresponding Author: edwardihani@gmail.com
Abstract
The main focus of this research is to develop a real-time forest fire monitoring
system using an Unmanned Aerial Vehicle (UAV). The UAV is equipped with
sensors, a mini processor (Raspberry Pi) and Ardu Pilot Mega (APM) for the
flight controller. This system used five sensors. The first is a temperature sensor
that served to measure the temperature in the monitored forest area. The others
sensors are embedded in the APM. There are a barometer, Global Positioning
Sensor (GPS), inertial measurement unit (IMU) and compass sensor. GPS and
compass are used in the navigation system. The barometer measured the air
pressure that is used as a reference to maintain the height of the UAV. The IMU
consists of accelerometer and gyroscope sensors that are used to estimate the
vehicle position. The temperature data from the sensor and the data from GPS are
processed by the Raspberry Pi 3, which serves as a mini processor. The results of
the data processing are sent to the server to be accessible online and real-time on
the website. The data transmission used the Transmission Control Protocol (TCP)
system. The experimental setup was carried out in an area of 40 meters × 40
meters with 10 hotspots. The diameter of the hotspots is 0.4 meters with a height
of 0.5 meters. The UAV is flown at a constant speed of 5 m/s at an altitude of 20
meters above the ground. The flight path is set by using a mission planner so the
UAV can fly autonomously. The experimental results show that the system could
detect seven hotspots in the first trial and nine hotspots in the second trial. This
happened because there is some data loss in the transmission process. Other
results indicate that the coordinates of hotspots detected by the UAV have a
deviation error of approximately 1 meter from the actual fire point coordinates.
This is still within the standard GPS accuracy as this system uses GPS with a
range accuracy of 2.5 meters.
Keywords: APM, Hotspots, Raspberry Pi, Real-Time UAV.
1588 E. D. Wardihani et al.
Journal of Engineering Science and Technology June 2018, Vol. 13(6)
1. Introduction
Forests are an important component in maintaining the balance of nature. The
forests cover about a third of Earth's surface and are home to two-thirds of the
world's terrestrial species. Forests are the source of biodiversity on the Earth.
Unfortunately, every year, forest fires destroyed millions of hectares of forests and
hundreds of millions of dollars are spent to extinguish these fires [1]. Although
wildfires help to create new forests, it is difficult to ensure the uncontrolled fires
do not spread to places that threaten the ecological system of the forests and human
life. A forest fire has become a serious natural hazard. Therefore, early prevention
of forest fires is crucial [2].
This issue has been the subject of research for many years. There are a number
of solutions that have been developed to address this problem. One of the ways
used to prevent forest fires is the development of early fire detection systems in the
forest. Massive efforts have been made to monitor, detect, and extinguish the fire
quickly before it gets too large. Traditional fire monitoring and detection methods
use humans to monitor the forests unremittingly. But this method requires a high
cost and is not safe for humans. Recently, remote sensing systems have become
one of the most effective methods of forest monitoring. The development of
electronics, computer science, and digital camera technology have enabled
computer-based remote sensing systems for forest fire monitoring and detection.
Remote sensing approaches for forest fire monitoring and detection can be grouped
into three categories: land-based systems, manned air-based systems, and satellite-
based systems. However, each of these systems presents a variety of technological
issues and practices. Ground measurement equipment has very limited coverage.
Satellite systems are less effective for large numbers of hotspots. Manned air
vehicles are usually large and expensive. In addition, pilot safety is also a part to
be considered [3].
Unmanned aerial vehicles (UAVs) with computer-based remote sensing
systems are an increasingly becoming an attractive and realistic option. Besides
being faster and mobile, UAVs are also relatively cheaper to continuously monitor
and detect forest fires. The integration of UAVs with remote sensing techniques
can also add value to pre-existing methods. In addition, UAVs are able to operate
in hazardous areas that cannot be safely reached by humans. These are the reasons
that have made UAVs one of the solutions that are currently attracting the world's
attention to overcome forest fires [4-9].
In the beginning, the UAV system for forest fire detection was developed by
the United States Forest Services (USFS) Forest Fire Laboratory (Wilson and Davis
1988). Furthermore, the USRP and National Aeronautics and Space Administration
(NASA) developed a project called Wildfire Research and Applications Partnership
(WRAP), which aims to develop underserved forest fire applications [10]. A team
of researchers from the University of Cincinnati supported by the West Virginia
Department of Forestry (WVDF) used a UAV system called UAV Marcus
"Zephyr" to test the system's ability to detect forest fires [11].
This research develops a real-time forest fire monitoring system using a UAV.
The UAV is equipped with sensors, a mini processor and Ardu Pilot Mega (APM)
for the flight controller. Data from both the temperature sensor and GPS are processed
by the Raspberry Pi 3, which serves as a mini processor. The results of the data
Real-Time Forest Fire Monitoring System using Unmanned Aerial Vehicle 1589
Journal of Engineering Science and Technology June 2018, Vol. 13(6)
processing are sent to a server to be accessible online and real-time on the website.
The data transmission used the Transmission Control Protocol (TCP) system.
This paper is organized as follows: Section 1 is introduction while Section II is
system model. Numerical result and discussion are explained in Section III and
lastly, Section IV is the conclusion.
2. System Model
The purpose of this research is to develop a real-time forest fire monitoring system
using an Unmanned Aerial Vehicle (UAV). The configuration of the system can be
seen in Fig. 1. The UAV is equipped with sensors, a mini processor (Raspberry Pi)
and Ardu Pilot Mega (APM) for the flight controller. There are five sensors used
in this system. The first is a temperature sensor that serves to measure the
temperature in the monitored forest area. The temperature sensor uses a Non-
Contact Infra-Red Sensor. The principle of the Non-Contact Infra-Red Sensor is
like a conventional thermal camera, with 2 × 2-pixel resolution and a Field of View
(FOV) of five degrees. The other sensors are embedded in the APM.
There is a barometer, Global Positioning Sensor (GPS), an inertial measurement
unit (IMU) and compass. The GPS and compass are used as the navigation system.
The barometer measures the air pressure that is used as the reference to maintain
the height of the UAV. The IMU consists of accelerometer and gyroscope sensors
that are used to estimate the vehicle’s position. The data from both the temperature
sensor and GPS are processed by the Raspberry Pi 3, which serves as a mini
processor. The communication between the UAV and ground station uses telemetry
data link with a frequency of 433 MHz. The Raspberry Pi 3 sends data to the web
server to be accessible online and real-time on the website. The data transmission
uses the Transmission Control Protocol (TCP) system.
Fig. 1. System configuration.
1590 E. D. Wardihani et al.
Journal of Engineering Science and Technology June 2018, Vol. 13(6)
The forest fire information system website was developed by using CodeIgniter,
Grocery CRUD, PHP: Hypertext Preprocessor (PHP), Cascading Style Sheets
(CSS) [12] and jQuery [13]. The information system on the website shows the
number of hotspots, the coordinates of hotspots and the temperature of hotspots.
The website is integrated with Google Maps so the user can more easily pinpoint
the location of the hotspots. The flowchart of this system can be seen in Fig. 2.
Fig. 2. Flowchart of the system.
3. Numerical Result and Discussion
The experimental setup was carried out in an area of 40 meters × 40 meters with 10
hotspots, as shown in Fig. 3. The diameter of the hotspots is 0.4 meters with a height
of 0.5 meters. The UAV flies at a constant speed of 5 m/s at an altitude of 20 meters
above the ground. The flight path is set by using a mission planner so the UAV can
fly autonomously. The flight paths flown are shown in Fig. 4.
On the first flight, the drone can detect seven from 10 hotspots that have been
created. On the second flight, the drone can detect nine from 10 hotspots. This
Real-Time Forest Fire Monitoring System using Unmanned Aerial Vehicle 1591
Journal of Engineering Science and Technology June 2018, Vol. 13(6)
happens because of the difference of timeout on the first flight and the second flight.
The first flight has a timeout of 0.2 seconds and the second flight uses a timeout of
0.5 seconds. The smaller timeout value means more data is sent to the server.
Unfortunately, more data sent to the server also means more data lost. This is
because of the instability in the data transmission process. Another reason is the
wind speed, which makes the drone shifts slightly from the flight path. This issue
will be tackled in future works.
Figure 5 shows the display of UAV location on the website in real-time. If the
drone detects a temperature that exceeds the threshold in a certain coordinate, then
the display on the website will put a marker in this location.
The temperature data of the sensor is also displayed in the form of a contour
map so that the user can see in detail the temperature at each coordinate. This can
be seen in Fig. 6.
Fig. 3. The experimental setup.
Fig. 4. Flight paths.
1592 E. D. Wardihani et al.
Journal of Engineering Science and Technology June 2018, Vol. 13(6)
(a) Flight 1
(b) Flight 2
Fig. 5. Real-time website visualization.
Fig. 6. Contour map visualization.
(a) Flight 1 (b) Flight 2
Real-Time Forest Fire Monitoring System using Unmanned Aerial Vehicle 1593
Journal of Engineering Science and Technology June 2018, Vol. 13(6)
Figure 7 shows the coordinates of hotspots detected by the UAV. There is a
deviation error of approximately 1 meter from the actual fire point coordinates.
This is still in the range of GPS accuracy because this system uses GPS with a range
accuracy of 2.5 meters.
Fig. 7. Comparison of distance errors for
mapping 1 and 2 to the original coordinates.
4. Conclusion
A real-time forest fire monitoring system using an Unmanned Aerial Vehicle
(UAV) or drone has been developed. The drone can detect ground surface
temperatures from a height of 20 meters above the ground. The drone flies at a
constant speed of 5 m/s. The drone can also send the measured data to a web server
to be displayed on a forest fire information system website. The results also indicate
that the coordinates of hotspots detected by the drone have a deviation error of
approximately 1 meter from the actual fire point coordinates. This is still within the
standard GPS accuracy because this system uses a GPS system with a range
accuracy of 2.5 meters. Among the future works of this research is how to mitigate
data loss during the data transmission from the drone to the web server.
References
1. Martinez-de Dios, J. R; Arrue, B.C; Ollero, A; Merino, L; Gómez-Rodríguez,
F. (2008). Computer vision techniques for forest fire perception. Image and
Vision Computing, 26(4), 550-562.
2. Lin, H.; Liu, Z.; Zhao, T.; and Zhang, Y. (2014). Early warning system of forest
fire detection based on video technology. Proceedings of the 9th International
Symposium on Linear Drives for Industry Applications. Berlin: 751-758.
1594 E. D. Wardihani et al.
Journal of Engineering Science and Technology June 2018, Vol. 13(6)
3. Chisholm, R.A.; Cui, J.; Lum, S.K.; and Chen, B.M. (2013). UAV LiDAR for
below- canopy forest surveys. Journal of Unmanned Vehicle System, 1, 61-68.
4. Ambrosia, V.G.; and Zajkowski, T. (2015). Selection of appropriate class
UAS/sensors to support fire monitoring: experiences in the United States. In
Handbook of unmanned aerial vehicles. Netherlands: Springer.
5. Merino, L.; Martínez-de Dios, J.R.; and Ollero, A. (2015). Cooperative
unmanned aerial systems for fire detection, monitoring, and extinguishing. In
Handbook of unmanned aerial vehicles. Netherlands: Springer.
6. Shahbazi, M.; Théau, J.; and Ménard, P. (2014). Recent applications of
unmanned aerial imagery in natural resource management. GIScience &
Remote Sensing, 51(4), 339-365.
7. Sharifi, F.; Zhang, Y.M.; and Aghdam, A.G. (2014). Forest fire detection and
monitoring using a network of autonomous vehicles. Proceedings of the 10th
International Conference on Intelligent Unmanned Systems (ICIUS 2014),
Quebec, Canada.
8. Bosch, I.; Serrano, A.; and Vergara, L. (2013). Multisensor network system for
wildfire detection using infrared image processing. The Scientific World
Journal, Article ID 402196.
9. Merino, L.; Caballero, F.; Martínez-de-Dios, J.R.; Maza, I.; and Ollero, A.
(2012). An unmanned aircraft system for automatic forest fire monitoring and
measurement. Journal of Intelligent & Robotic Systems, 65(1-4), 533-548.
10. Ambrosia, V.G.; Wegener, S.; Zajkowski, T.; Sullivan, D.V.; Buechel, S.;
Enomoto, F.; Lobitz, B.; Johan, S.; Brass, J.; and Hinkley, E. (2011). The
Ikhana unmanned airborne system (UAS) western states fire imaging missions:
from concept to reality (2006-2010). Geocarto International, 26(2), 85-101.
11. Charvat, R.; Ozburn, R.; Bushong, J.; and Cohen, K. (2012). SIERRA team flight
of Zephyr UAV at West Virginia wild land fire burn. Proceedings of the AIAA
Infotech@Aerospace Conference. California, United States of America, 19-21.
12. Nixon, R. (2014). Learning PHP, MySQL, JavaScript, CSS & HTML5: A
step-by-step guide to creating dynamic websites. United States of America:
O’Reilly Media.
13. Suehring. S; and Valade, J (2013) PHP, MySQL, Javascript & HTML5 all-in-
one for dummies. United States of America: Wiley
... Effective early warning systems are critical for detecting forest fires as soon as they ignite, enabling rapid and efficient responses to prevent them from spreading. Current methods for forest fire detection include satellite-based monitoring systems, drones, and manual observation by forest rangers or local inhabitants [5,6]. While these methods have proven useful in some instances, they are often limited by factors such as delayed detection, low spatial resolution, and the need for human intervention. ...
Article
Full-text available
This article presents the design and implementation of a solar fire detection system using a Wireless Sensor Node (WSN). The system incorporates a temperature sensor, Bluetooth module, and intelligent battery charging management to provide real-time monitoring and early detection of forest fires, while also ensuring energy conservation and battery protection. By employing a DC-DC converter, the system maintains a stable 9V supply to the Arduino board under various power supply conditions. The integration of the temperature sensor and Bluetooth module enables accurate temperature data transmission to mobile or computer terminals for real-time monitoring. The energy-saving and battery protection features optimize charging cycles and prolong battery life, contributing to environmental sustainability and enhanced safety for communities at risk. The successful testing of the system demonstrates its reliability and potential as an effective early warning system to combat the devastating effects of forest fires.
... Furthermore, forest fire risk prediction models have been created to predict the time of fire occurrence, fire-spread direction, and fire intensity using deep learning to analyze various factors affecting forest fire [19][20][21][22][23]. Park et al. [24] proposed a semi-supervised classification model using support vector machine technology to divide forest areas into high, medium, and low activity based on the likelihood of a forest fire in an area. ...
Article
Full-text available
Monitoring and early warning technology for forest fires is crucial. An early warning/monitoring system for forest fires was constructed based on deep learning and the internet of things. Forest fire recognition was improved by combining the size, color, and shape characteristics of the flame, smoke, and area. Complex upper-layer fire-image features were extracted, improving the input conversion by building a forest fire risk prediction model based on an improved dynamic convolutional neural network. The proposed back propagation neural network fire (BPNNFire) algorithm calculated the image processing speed and delay rate, and data were preprocessed to remove noise. The model recognized forest fire images, and the classifier classified them to distinguish images with and without fire. Fire images were classified locally for feature extraction. Forest fire images were stored on a remote server. Existing algorithms were compared, and BPNNFire provided real-time accurate forest fire recognition at a low frame rate with 84.37% accuracy, indicating superior recognition. The maximum relative error between the measured and actual values for real-time online monitoring of forest environment indicators, such as air temperature and humidity, was 5.75%. The packet loss rate of the forest fire monitoring network was 5.99% at Longshan Forest Farm and 2.22% at Longyandong Forest Farm.
... Not only those in the realm of the defense department or research agencies, including universities that conducted research and development, but the industrial world and the civil sector have also begun to use this unmanned system technology a lot in supporting their daily activities. Real-time monitoring and mapping of critical areas such as strategic areas such as mining areas, maritime affairs, inter-state borders, natural disaster damage assessment, plantations, etc. are objects of great potential for the utilization of these unmanned systems [1]- [5]. Drones are also used for indoor aerial monitoring [6]. ...
Article
Full-text available
In Indonesia, the COVID-19 pandemic has had an impact on a variety of sectors. Using all available technology for disaster mitigation is critical for pandemic prevention and control. Recent studies have uncovered the advantage of Unmanned Aerial Vehicle (UAV) or drones, particularly those with rotary wings, in dealing with the pandemic. Much effort has been devoted to developing a rotary-wing drone system as a flying platform for aerial monitoring. However, several factors must be considered when visually observing a specific region, i.e., the area's size, topographic contours, locations of special interest inside the area, approach points to the area, and the observation timeframe. Since fever is a common symptom of COVID-19, human body temperature monitoring is highlighted for fever screening, with the objective of minimizing people with high body temperatures going to the crowd. A major challenge is creating a system that can provide accurate body temperature data, which is critical for fighting the pandemic. The purpose of this paper is to present a rotary wing drone application for aerial human body temperature measurements. The paper also proposed an alternative solution based on using a portable, low-cost, Forward-looking Infrared (FLIR) thermal imaging camera. The FLIR thermal camera is incorporated into the drone's electronic system. Furthermore, thermal image data are transmitted into the ground station via a radio telemetry transceiver to allow flexible surveillance by the operator. Indoor and outdoor experiments reveal that the system has been effectively installed and provide data collection for further research. The results show that the system can be used for small-scale area aerial monitoring.
... The drone can detect the temperature from 20 m above the ground surface. However, data loss during the data transmission from the drone to the web server needs to be improved [28]. Color feature extraction results in inaccuracy; to overcome the issue, a two-dimensional discrete wavelet transform (DWT) is used. ...
Article
Full-text available
Forest fires are caused naturally by lightning, high atmospheric temperatures, and dryness. Forest fires have ramifications for both climatic conditions and anthropogenic ecosystems. According to various research studies, there has been a noticeable increase in the frequency of forest fires in India. Between 1 January and 31 March 2022, the country had 136,604 fire points. They activated an alerting system that indicates the location of a forest fire detected using MODIS sensor data from NASA Aqua and Terra satellite images. However, the satellite passes the country only twice and sends the information to the state forest departments. The early detection of forest fires is crucial, as once they reach a certain level, it is hard to control them. Compared with the satellite monitoring and detection of fire incidents, video-based fire detection on the ground identifies the fire at a faster rate. Hence, an unmanned aerial vehicle equipped with a GPS and a high-resolution camera can acquire quality images referencing the fire location. Further, deep learning frameworks can be applied to efficiently classify forest fires. In this paper, a cheaper UAV with extended MobileNet deep learning capability is proposed to classify forest fires (97.26%) and share the detection of forest fires and the GPS location with the state forest departments for timely action.
Chapter
Forest fire has been one of the most dangerous threats to the forest, wildlife, and firefighters, causing disastrous economic problems and unrepairable environmental effects (Hossain et al. (J Unmanned Veh Syst 8:285–309, 2020) , Merino et al. (J Intell Robot Syst 65(1–4):533–548, 2012), Mysorewala et al. (J Intell Robot Syst 54(4):535–565, 2009), Yuan et al. (Can J Forest Res 45(7):783–792, 2015)). Nowadays, the traditional human fire-fighting methods are still widely used, and the firefighters usually go to the fire scene to put out the fire, imposing fatal threats to the safety of firefighters. Forest fire fighting is usually based on the visual observations from the fire-fighting experts, which may cause calamitous results if the spread direction of the forest fire, easily changed by the varied wind direction, is not monitored promptly (Merino et al. (Automatic forest fire monitoring and measurement using unmanned aerial vehicles, in International Congress on Forest Fire Research, Coimbra, Portugal, 2010)). Since UAV can provide the aerial image of the forest fire, observe the spread direction, and put out the forest fire by spraying water or launching fire extinguishing bombs, it is a desired platform for forest fire monitoring and fighting (Hossain et al. (J Unmanned Veh Syst 8:285–309, 2020), Skorput et al. (The use of unmanned aerial vehicles for forest fire monitoring, in International Symposium on Electronics in Marine, Zadar, Croatia, 2016), Sudhakar et al. (Comput Commun 149:1–16, 2020), Wardihani et al. (J Eng Technol 13(6):1587–1594, 2018), Yuan et al. (J Intell Robot Syst 88(2–4):635–654, 2017), Yuan, et al. (Can J Forest Res 45(7):783–792, 2015)).
Article
Unmanned Aircraft Systems (UAS) (also referred to as Unmanned Aerial Systems (UAS), Unmanned Autonomous Vehicles (UAVs), or drones) operations, focused on natural hazards, have experienced rapid expansion in the last decade. UAS uses before, during, and after natural hazard events, provide value for emergency management operations (e.g. Search-and-Rescue (SAR)), and post-event analytics. The Department of Homeland Security and Emergency Services (DHSES) manages UAS programs for public safety and emergency response activities in New York State. They also have the first FEMA-approved, locally adopted, web-based, interactive Hazard Mitigation Plans (HMPs). With recent advances in communication technologies (e.g. 5G), opportunities are emerging to establish a stewardship role to maximize regionwide UAS operations, including preparing for catastrophic natural hazards (e.g. earthquakes, hurricanes), leveraging existing HMPs, and incorporating new machine-learning techniques to use swarming networks before, during, and after a natural hazard event. A variety of stewardship approaches are discussed.
Article
Deep hashing algorithms are widely exploited in retrieval tasks due to its low storage and retrieval efficiency. Most of which focus on global feature learning, whilst neglecting local fine-grained features and saliency information for drone images. In this paper, we tackle these dilemmas with a novel Deep Saliency Smoothing Hashing (DSSH) algorithm, which can leverage saliency capture mechanism, distribution smoothing term, global features and local fine-grained features to learn effective hash codes for drone image retrieval. The DSSH algorithm first designs information extraction module to capture global features and local fine-grained features for drone images. Meanwhile, a saliency capture module is proposed to perform information interaction attention and visual enhancement attention, which can capture the saliency area of drone images effectively. On top of the two paths, a novel objective function is designed to preserve the similarity of hash codes, smooth the distribution of drone image datasets and reduce the quantization errors between hash codes and hash-like codes concurrently. Extensive experiments on the Drone Action Dataset and ERA Drone Dataset demonstrate that the DSSH algorithm can further improve the retrieval performance compared to other deep hashing algorithms.
Article
Full-text available
The intensity and frequency of bushfires have increased significantly, destroying property and living species in recent years. Presently, unmanned aerial vehicle (UAV) technology advancements are becoming increasingly popular in bushfire management systems because of their fundamental characteristics, such as manoeuvrability, autonomy, ease of deployment, and low cost. UAVs with remote-sensing capabilities are used with artificial intelligence, machine learning, and deep-learning algorithms to detect fire regions, make predictions, make decisions, and optimize fire-monitoring tasks. Moreover, UAVs equipped with various advanced sensors, including LIDAR, visual, infrared (IR), and monocular cameras, have been used to monitor bushfires due to their potential to provide new approaches and research opportunities. This review focuses on the use of UAVs in bushfire management for fire detection, fire prediction, autonomous navigation, obstacle avoidance, and search and rescue to improve the accuracy of fire prediction and minimize their impacts on people and nature. The objective of this paper is to provide valuable information on various UAV-based bushfire management systems and machine-learning approaches to predict and effectively respond to bushfires in inaccessible areas using intelligent autonomous UAVs. This paper aims to assemble information about the use of UAVs in bushfire management and to examine the benefits and limitations of existing techniques of UAVs related to bushfire handling. However, we conclude that, despite the potential benefits of UAVs for bushfire management, there are shortcomings in accuracy, and solutions need to be optimized for effective bushfire management.
Conference Paper
Full-text available
This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency Response Robotic Aircraft (SIERRA) Team of The University of Cincinnati in supporting continued development of technology for Emergency Management Operations. This paper represents the experimental and post flight analysis of the SIERRA program during the late 2011 time frame in which the team flew 2 successful demonstrations in West Virginia. This paper is the conclusion of “Intelligent Integration of UAV Systems for WildlandFire Management: Towards Concept Demonstration” from AIAA Infotech 2011.
Article
Full-text available
Unmanned aerial vehicles have become popular platforms for remote-sensing applications, particularly when spaceborne technology, manned airborne techniques, and in situ methods are not as efficient for various reasons. These reasons include the temporal and spatial data resolutions, accessibility over time and space, cost efficiency, and operational safety. Given that most commercial developers tend to focus on the hardware development of unmanned aerial systems, less attention is paid to the development and evaluation of their data processing techniques. Therefore, critical reviews of previous studies are required to describe the current state of research using data from unmanned remote sensing platforms. Accordingly, this article presents the results of a comprehensive review of applications of unmanned aerial imagery for the management of agricultural and natural resources. This review attempts to demonstrate that developing robust methodologies and reliable assessments of results are significant issues for successful applications of unmanned aerial imagery.
Article
Full-text available
This paper presents the next step in the evolution of multi-sensor wireless network systems in the early automatic detection of forest fires. This network allows remote monitoring of each of the locations as well as communication between each of the sensors and with the control stations. The result is an increased coverage area, with quicker and safer responses. To determine the presence of a forest wildfire, the system employs decision fusion in thermal imaging, which can exploit various expected characteristics of a real fire, including short-term persistence and long-term increases over time. Results from testing in the laboratory and in a real environment are presented to authenticate and verify the accuracy of the operation of the proposed system. The system performance is gauged by the number of alarms and the time to the first alarm (corresponding to a real fire), for different probability of false alarm (PFA). The necessity of including decision fusion is thereby demonstrated.
Article
Full-text available
The paper presents an Unmanned Aircraft System (UAS), consisting of several aerial vehicles and a central station, for forest fire monitoring. Fire monitoring is defined as the computation in real-time of the evolution of the fire front shape and potentially other parameters related to the fire propagation, and is very important for forest fire fighting. The paper shows how an UAS can automatically obtain this information by means of on-board infrared or visual cameras. Moreover, it is shown how multiple aerial vehicles can collaborate in this application, allowing to cover bigger areas or to obtain complementary views of a fire. The paper presents results obtained in experiments considering actual controlled forest fires in quasi-operational conditions, involving a fleet of three vehicles, two autonomous helicopters and one blimp.
Chapter
This chapter deals with the application of cooperative unmanned aerial systems to forest fires. Fire detection and fire monitoring and measurement to assist in fire extinguishing are discussed. The chapter presents a decision and control architecture for multi-UAS teams in forest firefighting. Then, the applications to fire detection and fire monitoring/measurement are studied by including in both cases the sensors, mainly infrared and visual cameras, the perception techniques (fire segmentation, geolocalization, and data fusion), and some experimental results. Finally the fire extinguishing is also considered, and some results are presented.
Chapter
As government agencies around the globe strive to improve their disaster monitoring capabilities and speed response and recovery efforts, requirements for more accurate and safer data collection mean that Unmanned Aerial System (UAS) are being examined more closely for their potential roles in safely gathering data over those events. Wildfires are consistently one of the most common worldwide “disaster” events, and therefore the wildfire management community is experiencing a surge in UAS interest to support intelligence gathering and pertinent data delivery over those fire incidents. There are numerous, often confusing differences amongst UAS platforms and their sensors. Coupled with the various mission roles required by observation platforms in the wildfire domain, the UAS landscape can be a daunting place for a wildfire manager (or any disaster manager) to select the appropriate UAS solution capability that matches his/her requirements. This chapter describes some of the UAS lessons learned by both the U.S.. Forest Service (USFS) and the National Aeronautics and Space Administration (NASA) during their C10-year efforts on identifying appropriate UAS wildfire observation capabilities. The agencies, along with the UAS community, have demonstrated the use of both Low-Altitude, Short-Endurance (LASE) and Medium-Altitude, Long-Endurance (MALE) platforms for wildfire sensor intelligence gathering. Those experiences are identified in this chapter as well as an examination of the future direction of UAS systems for supporting the wildfire management community.
Article
Remote sensing tools are increasingly being used to survey forest structure. Most current methods rely on GPS signals, which are available in above-canopy surveys or in below-canopy surveys of open forests, but may be absent in below-canopy environments of dense forests. We trialled a technology that facilitates mobile surveys in GPS-denied below-canopy forest environments. The platform consists of a battery-powered UAV mounted with a LiDAR. It lacks a GPS or any other localisation device. The vehicle is capable of an 8 min flight duration and autonomous operation but was remotely piloted in the present study. We flew the UAV around a 20 m × 20 m patch of roadside trees and developed postprocessing software to estimate the diameter-at-breast-height (DBH) of 12 trees that were detected by the LiDAR. The method detected 73% of trees greater than 200 mm DBH within 3 m of the flight path. Smaller and more distant trees could not be detected reliably. The UAV-based DBH estimates of detected trees were positively correlated with the human-based estimates (R ² = 0.45, p = 0.017) with a median absolute error of 18.1%, a root-mean-square error of 25.1% and a bias of −1.2%. We summarise the main current limitations of this technology and outline potential solutions. The greatest gains in precision could be achieved through use of a localisation device. The long-term factor limiting the deployment of below-canopy UAV surveys is likely to be battery technology.
Article
Between 2006 and 2010, National Aeronautics and Space Administration (NASA) and the US Forest Service flew 14 unmanned airborne system (UAS) sensor missions, over 57 fires in the western US. The missions demonstrated the capabilities of a UAS platform (NASA Ikhana UAS), a multispectral sensor (autonomous modular sensor (AMS)), onboard processing and data visualization (Wildfire Collaborative Decision Environment (W-CDE)), to provide fire intelligence to management teams. Autonomous, on-board processing of the AMS sensor data allowed real-time fire product delivery to incident management teams on the wildfire events. The fire products included geo-rectified, colour-composite quick-look imagery, fire detection shape files, post-fire real-time normalized burn ratio imagery and burn area emergency response (BAER) imagery. The W-CDE was developed to allow the ingestion and visualization of AMS data and other pertinent fire-related information layers. This article highlights the technologies developed and employed, the UAS wildfire imaging missions performed and the outcomes and findings of the multi-year efforts.
Article
This paper presents computer vision techniques for forest fire perception involving measurement of forest fire properties (fire front, flame height, flame inclination angle, fire base width) required for the implementation of advanced forest fire-fighting strategies. The system computes a 3D perception model of the fire and could also be used for visualizing the fire evolution in remote computer systems. The presented system integrates the processing of images from visual and infrared cameras. It applies sensor fusion techniques involving also telemetry sensors, and GPS. The paper also includes some results of forest fire experiments.