Content uploaded by Sidiq Syamsul Hidayat
Author content
All content in this area was uploaded by Sidiq Syamsul Hidayat on Nov 07, 2018
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