Page 1
A Swarm of Crop Spraying Drones Solution for
Optimising Safe Pesticide Usage in Arable Lands
Project Proposal
M.C.A. Amarasinghe
Supervisor Dr K.L. Jayaratne
Co-supervisor
Mr V.B. Wijesuriya
Adviser
Dr D.M. Ganepola
May, 2018
Submitted in partial fulfillment of the requirements for the degree of
Master of Philosophy in Computer Science
Page 2
2
Table of Contents
1. Background ............................................................................................................................................................. 5
2. Introduction ........................................................................................................................................................... 6
3. Research Question ............................................................................................................................................... 7
4. Significance ............................................................................................................................................................. 7
5. Open Challenges.................................................................................................................................................... 8
5.1. Challenges Related to Drones ................................................................................................................. 8
5.1.1. Battery Lifetime ................................................................................................................................... 8
5.1.2. Load Balancing ..................................................................................................................................... 8
5.1.3. Covering Area ....................................................................................................................................... 8
5.1.4. Capturing Images of the Entire Area ........................................................................................... 9
5.1.5. Camera Quality .................................................................................................................................... 9
5.2. Other Challenges .......................................................................................................................................... 9
5.2.1. Unemployment .................................................................................................................................... 9
6. Research Methodology ....................................................................................................................................... 9
6.1. Literature Review ........................................................................................................................................ 9
6.2. Development of a Solution Concept .................................................................................................. 10
6.3. Training Users............................................................................................................................................ 13
6.4. Evaluation .................................................................................................................................................... 13
6.5. Possible Extensions ................................................................................................................................. 13
6.6. Deliverables ................................................................................................................................................ 13
7. A Viable System Design ................................................................................................................................... 14
7.1. Mapping the Farmland ........................................................................................................................... 14
7.2. Capturing Images of the Farmland .................................................................................................... 14
7.3. Generating the 2D Grid World ............................................................................................................. 17
7.4. Spraying Pesticides .................................................................................................................................. 17
7.5. Design of a Slave Drone .......................................................................................................................... 18
7.5.1. Spray Tank .......................................................................................................................................... 19
7.5.2. Charging Port ..................................................................................................................................... 19
7.5.3. Fill Valve .................................................................................................................................................. 19
8. Work Plan ............................................................................................................................................................. 20
9. Brief Literature Review................................................................................................................................... 21
Page 3
3
9.1. Sensing Technologies .............................................................................................................................. 21
9.1.1. Remote Sensing Imagery .............................................................................................................. 21
9.1.2. Machine Vision .................................................................................................................................. 21
9.1.3. Thermography .................................................................................................................................. 22
9.2. Object Recognition ................................................................................................................................... 22
9.3. Detection of Plant Water Stress .......................................................................................................... 22
9.4. Detection of Plant Diseases................................................................................................................... 23
9.5. Drones for Agriculture ............................................................................................................................ 23
9.5.1. Using Drones for Monitoring ....................................................................................................... 23
9.5.2. Using Drones for Irrigation Management .............................................................................. 24
9.5.3. Using Drones for Detecting Diseases in Plants ..................................................................... 25
9.5.4. Using Drones for Pest Controlling ............................................................................................. 25
9.6. Challenges of Using Drones in Agriculture ..................................................................................... 27
9.7. Discussion .................................................................................................................................................... 27
10. References ....................................................................................................................................................... 29
Page 4
4
Table of Figures
Figure 6.2.1: The Flow Diagram of the Proposed System ............................................................ 12
Figure 6.2.2: The Block Diagram of the Captured Area ................................................................. 12
Figure 7.1.1: Marking the Farmland via the Discovery Drone.................................................... 14
Figure 7.2.1: Capturing Images of the Farmland ............................................................................. 15
Figure 7.3.1: Generating the Grid World of the Farmland ........................................................... 16
Figure 7.4.1: Spraying Pesticides ........................................................................................................... 18
Figure 7.5: The Design of a Slave Drone .............................................................................................. 19
Figure 8: Work Plan of the Research .................................................................................................... 20
List of Tables
Table 9.7: The Advantages and the Disadvantages of Available Pesticides Systems and Multi-
UAV Systems .................................................................................................................................................. 28
Page 5
5
1. Background
In pursuit of controlling harmful organisms in arable farmlands thereby accruing financial
benefits from a continuous rich and high quality profusion of crop harvest, pesticides have
emerged as an indispensable asset among practitioners of contemporary agriculture in Sri
Lanka. Pesticides are chemical mixtures which are utilised to kill pests, including weeds, fungi,
rodents and insects [1]. Furthermore, pesticides help kill agricultural pests who harm crops.
However, pesticides are toxic to living beings including humans and it is essential to consider
their use in a safer manner [1].
According to [2], 3.5 billion kilograms of pesticides are used every year to acquire a greater
quality and quantity of harvest. Increasing population, rising urbanisation and expanding
economies drastically increase the demand for food production and in turn the use of
pesticides.
The World Health Organization (WHO) believes that one of the root causes of chronic kidney
disease (CKD) is the use of pesticides which consist of heavy metals such as Arsenic, Lead,
Cadmium, etc., [3, 4]. Sri Lanka’s CKD-victimised male-to-female ratio was 12:5 in 2015 [3].
Their mean age was 54.7 ± 8 years; while 92% of them were farmers and 93% of them used
water from shallow wells which are located near commercial farms [3]. Furthermore,
researchers have also identified that pesticides are a fundamental cause of cancer,
neurotoxicity and depression [6, 7].
Pesticides can mix with surface water and therefore cause contamination via superfluity from
treated soil and plants. In 2001, researchers found 90% of water and fish samples in selected
streams contain several harmful pesticides [8]. Also, United States Geological Survey (USGS)
and National Academy of Sciences has identified that the indicated dosage of some pesticides
exceeds the allowed limit defined in the national guidelines for aquatic life protection [9, 10].
Pesticides have been a threat to the purity of groundwater. It might take many years to cleanse
such contaminated groundwater naturally. However, the cleanup process can be a costly and
complex or nearly an impossible effort [11]. Soil fertility depends on micro-organisms such as
bacteria and fungi. Since overuse of pesticides has consequences on organisms in soil, it is
likely that soil may be driven towards non-fertility [12]. When spraying pesticides, it is
possible that these compounds may get mixed with air particles and affect non-targeted
vegetation and organisms.
Page 6
6
2. Introduction
Even though pesticides improve productivity, in turn protecting yield reduction, controlling
disease vectors and enhancing quality of food; they directly or indirectly impact all living
beings [12].
The farmers and the families who are working in and living near commercial farms are the
most common groups who would easily get exposed to the adverse effects of pesticides, if they
do not take seriously into account their personal safety by wearing protective equipment such
as respirators, cotton gloves, etc.; preparing and cleaning their pesticides equipment [13, 14].
Backpack sprayers are the most common type of pesticide sprayers used in developing
countries [15]. However, implicit leakages and maintain irregularities aggrandise the outcomes
due to accidental exposure [15].
Researchers have identified that inappropriate pesticides usage as a major consequence of
pesticide waste. They have also categorised pesticide waste into two groups; hazardous waste
and solid waste. Storage irregularities are one of the major reasons for hazardous waste; and
improper disposal of pesticides and excess mixture results in solid waste [16]. To solve
aforementioned issues, it is important to come up with a solution that enables spaying
pesticides with minimum human intervention.
A drone has a considerably large popularity rather than other unmanned equivalents due to its
size and flexibility. Furthermore, drones have been successfully utilised in different fields such
as surveying, inspection, construction, mapping, public safety, security, agriculture, disaster
monitoring, emergency assistance, military services (border surveillance, search and rescue
missions), communication, etc., [17 – 21]. Drone technology has successfully been applied to
agriculture through soil and field analysis, planting, crop spraying, crop monitoring, irrigation
and health assessment [22]. “Precision agriculture” is such a farming management concept
which sometimes motivates the use of drones in commercial agriculture sector [38].
Using individual drones for spraying pesticides is not a new approach and a drone can
minimise the excessive pesticides usage if operated appropriately [23]. Drones may therefore
assist to reduce pesticide burn and decrease pesticides runoff on surface water and
groundwater [23]. Unfortunately, an agricultural drone usually costs at least $4,000 [24].
A swarm of drones is not a novel approach either. However, it can be regarded as a novel
initiative for some agriculture-related problems, intuitively optimising pesticide usage [22, 23].
Through this research, we try to leverage a swarm of drones solution by applying precision
agriculture concepts, to spray pesticides in arable lands with optimal pesticides usage and
minimum human intervention.
Page 7
7
3. Research Question
Our proposed research addresses the following question. “How to develop a swarm of drones
solution for spraying pesticides in arable lands with optimal safe pesticide usage and minimum
human intervention?”
In here, optimal pesticide usage corresponds to the correct dosage of a given pesticide as
recommended by a national or international public health agency. Spraying pesticides
manually takes up a considerable amount of time and requires a large human effort. One may
utilise a single drone to spray pesticides appropriately with minimum time and human
intervention. However, we suggest a swarm of drones here, since a single drone may prove to
be highly inefficient in covering a large area of land.
4. Significance
Tenants living near commercial farms face distinct health problems such as abdominal pain,
nausea, vomiting, bloody diarrhea, headache, dizziness, drowsiness, weakness, lethargy,
delirium, shock, kidney insufficiency, neuropathy, etc., due to overexposure to pesticides [25].
Our research approach suggests using a multitude of drones that support autonomous refilling
from a pesticide reservoir and recharging batteries using charging bay(s) located on site. We
believe that our solution will minimise human intervention in the spraying process and
effectively contribute to reducing the risk of contracting diseases that result from
overexposure.
The suggested research approach is geared towards optimal pesticides usage, which can assist
to reduce pesticide overuse, decrease pesticides runoff to surface water and groundwater. This
will help to safeguard aquatic life and the purity of surface and groundwater. As said earlier, it
will also help to lessen the damage to the micro-organisms in soil and reduce the rate of
driving soil to a non-fertile state. Therefore, the approach can contribute to minimising the
contamination of the environment. On the other hand, optimal pesticides usage will help
increase the quality and the quantity of the harvest and save money otherwise spent on an
excessive amount of pesticides.
When spraying pesticides manually, it is bound to take a considerable amount of time to cover
the target area but a single spraying drone can fly over and cover a large arable area more
speedily than a human. Furthermore, a swarm of spraying drones can cover a much larger area
more speedily than a single spraying drone. Thus, we believe that the proposed solution
concept will progressively help save time and the money of the user.
As said before, a typical commercial agricultural drone costs at least $4,000 [24]. If we assume
a swarm of drones consisting of at least 3 such drones, the associated cost will be at least
Page 8
8
$12,000 ($4,000 x 3). A usual farmer may not be able to bear such an exorbitant cost. This
motivates to build a cost-effective fully customised swarm of drones. It is expected to employ
agent-based modelling techniques [56] to solve the overall problem.
The benefits of the suggested approach are:
1. Minimise human intervention in the spraying process.
2. Contribute to reducing the risk of contracting diseases that result from overexposure.
3. Reduce pesticide overuse.
4. Minimise contamination of the environment.
5. Increase the quality and the quantity of harvest.
6. Save money spent on an excessive amount of pesticides.
7. Save time and the money of the user.
8. Enable farmers to use the resulting solution without the need to incur unreasonable costs.
9. A better and safer platform for the pesticide industry to market different pesticides brands.
5. Open Challenges
Described in this section, several open challenges that reign in the paradigm of our research.
5.1. Challenges Related to Drones
5.1.1. Battery Lifetime
A drone is powered by a rechargeable battery. Usually, a drone has a limited flying time due to
limited battery lifetime. DJI is one of the top-rated drone producers in the world [26]. Even the
battery life of a DJI Phantom 4 drone for a normal flight is around 23 – 24 minutes and takes a
considerable amount of time to recharge. When managing a customised swarm of drones, it is
highly important to consider the status of their batteries and finding ways to recharge them
efficiently.
5.1.2. Load Balancing
A single slave drone (slave drones will be discussed in section 7.5) should carry a payload of
liquid pesticides for crop spraying but the maximum weight that a drone can carry depends on
many factors including any requirements on its speed and stability.
5.1.3. Covering Area
As per the scope of this research, we consider arable land areas of no more than one acre that
require spraying a chosen common pesticide generally available in the Sri Lankan market.
Furthermore, we consider avoiding unsafe areas which are traps that if reached, the drone may
Page 9
9
not be able to get out; and forbidden areas including dams, ponds, wastelands, streams, private
properties, dead zones, etc. We are also interested in considering government regulations,
guidelines from national and international public health agencies, and other international
standardisation requirements for both operations of drones and safe pesticide usage.
5.1.4. Capturing Images of the Entire Area
Capturing images of an area up to one acre in one go is difficult for a single drone. When using a
multi-UAV system for capturing images, another issue arises over the way images should be
captured without having a single portion of land captured in two or more images.
5.1.5. Camera Quality
The quality of the drone camera is another crucial factor in aerial monitoring drones. In here,
the quality of the camera corresponds to capturing clearer images of the farmland.
Additionally, there are several other obstacles such as involving onboard sensors, embedded
processing, communicating through wireless links and limited sensing coverage [27].
Robustness, flexibility, navigation and communication with other drones are some of the
important features that drones in a swarm should entail [28 – 30].
5.2. Other Challenges
5.2.1. Unemployment
Many people who live near the commercial farms depend on undertaking secondary support
jobs related to farming such as pesticides spraying. Since the aim of this research is to
introduce a swarm of drones solution to spray optimal amounts of pesticides with minimum
human intervention, there exists a risk factor that may cause such personnel to lose their jobs.
6. Research Methodology
Herein outline our proposed research methodology.
6.1. Literature Review
We plan to extensively review existing literature to identify different approaches that adapt
swarm of drones in diverse application areas and associated challenges. Furthermore, different
approaches for spraying pesticides via agricultural drones and their complications will also be
reviewed.
Page 10
10
6.2. Development of a Solution Concept
An overview of the proposed system is shown in Figure 6.2.1. The plan for a robust
development of viable solution concept is outlined as follows:
1. Develop a drone, viz., discovery drone, to mark the boundary of the selected farmland for
spraying a designated pesticide. The drone should consist of a global positioning system
(GPS) sensor for geo-location identification, a general packet radio service (GPRS) sensor
for communication via internet, a camera to capture pertinent images and a charging port
for recharging its battery from a charging station.
Rather than using a discovery drone, we also consider using a handheld GPS sensor for
marking the boundary of the farmland as an alternate solution. Then the farmer can walk
along the boundary of the farmland to capture boundary geo-locations [54].
2. Develop a mobile application, viz., app-A, to facilitate the farmer to connect with the above
described discovery drone to mark the boundary of target farmland before spraying can
commence. This application should also be able to monitor the flying path of the drone.
3. Develop several comm-drones (similar in operation to the discovery drone) and associate
with each, a set of slave drones to create clusters of workgroups each guided and controlled
by a single comm-drone. Comm-drones have collision detection and avoidance mechanisms
that support the whole cluster to detect and avoid such complications.
Slave drones are primarily worker drones that actually perform the spraying. Each slave
drone consists of a GPS sensor for geo-location identification, a spray tank and a battery
charging port. More details are provided in section 7.5.
4. Develop a cloud-based (central) system to centrally manage the swarm operations and
synthesise policies for optimising safe pesticide spraying. After the discovery drone
completes its flight, boundary geo-locations are uploaded to the central system.
5. The central system commands all comm-drones to fly over the farmland and capture
ground images. The flying paths are determined by a planning algorithm. Develop a second
mobile application, viz., app-B, for connecting the farmer with the central system.
6. Captured images are subsequently uploaded to the central system.
7. With the images at hand, the central system generates the terrain of the farmland and
subsequently produces the 2D grid world of the terrain via image processing techniques
[57]. This will identify and locate safe areas (e.g. areas with crops) and unsafe areas (e.g.
traps, dams, ponds, wastelands, streams, etc.,) in the terrain.
Page 11
11
8. The central system plans by dividing safe areas to clusters according to the available
number of comm-drones. Each cluster consists of a set of squares and each square consists
of some circles. A capture of a sample farmland is shown in Figure 6.2.2. The size of a circle
is the maximum area that a slave drone can cover at a given time instance, when spraying
pesticides.
9. The central system assigns each comm-drone and several slave drones to a single cluster.
10. The farmer provides user input to the central system via app-B. User input may include the
total amount of spray liquid available, specific weather conditions, selecting a specific
standardised procedure (e.g. WHO recommendation), etc. Using the given user input and
already available data, the central system synthesises policies for the behaviour of the
entire swarm, inside clusters and that for each slave.
11. Apart from spraying pesticides, any slave drone can proceed to the charging or filling
stations when needed by informing its associated comm-drone, the comm-drone
subsequently informs the central system. The comm-drone then receives instructions to
assign the former slave drone’s remaining workload to another slave in the cluster. Inter-
cluster slave transfers can also occur. If a comm-drone wants to perform similar
maintenance tasks, it should also inform the central system. The central system then
assigns the salves in that cluster to that of another comm-drone, if the former comm-drone
could not finish its task before pursuing maintenance.
After a slave drone has finished recharging or refilling, it uses the uplink in the station to
inform the central system. After a comm-drone completes its tasks in the associated cluster,
the central system assigns to it another safe area.
12. After finishing all spray jobs in the selected farmland all drones are directed to a hangar.
Page 12
12
Figure 6.2.1: The Flow Diagram of the Proposed System
Figure 6.2.2: The Block Diagram of the Captured Area
Page 13
13
6.3. Training Users
Target user group of this research is farmers. In the training phase, farmers will be trained to
basically handle a smartphone, install and use aforementioned mobile applications. Also,
mobile applications will inform farmers the optimal location to place both charging and filling
stations.
6.4. Evaluation
On the whole evaluation will be based on empirical studies. We plan on collecting feedback
from the target user group via interviews and questionnaires. Furthermore, a chemical analysis
will be performed on crops and soil collected from test sites.
6.5. Possible Extensions
As mentioned earlier, the current scope of the research plans to cover a limited arable
farmland of size no more than one acre. In future extensions (as time permits), we hope to
extend the coverage to at least ten acres. Further enhancements can include extending
stationary charging stations with wireless charging capabilities. This enhancement will help
minimise recharging time and increase spraying efficiency.
6.6. Deliverables
As the research progresses, we plan to publish a set of conference and journal papers in nexus
to different aspects and checkpoints targeted by this research. Some of these are given in the
work plan as illustrated in Figure 8.1. At the end of the research, in addition to the final thesis,
we plan to deliver working prototypes of the central system and different types of drones
employed in the swarm.
Page 14
14
7. A Viable System Design
A viable system design is proposed in this section that is subject to change as the research
progresses.
7.1. Mapping the Farmland
The discovery drone flies over the boundary of the selected farmland under the supervision of
the farmer through mobile application app-A while identifying the relevant boundary geo-
locations. This is illustrated in Figure 7.1.1. These geo-locations are uploaded to the central
system using the uplink on the drone.
Figure 7.1.1: Marking the Farmland via the Discovery Drone
7.2. Capturing Images of the Farmland
To capture aerial photographs of the farmland, the central system directs comm-drones to scan
the area surrounded by the boundary geo-locations. Furthermore, the farmer can monitor all
related incidents via mobile application app-B. The associated workflow is shown in Figure
7.2.1.
Page 15
15
Figure 7.2.1: Capturing Images of the Farmland
Page 16
16
Figure 7.3.1: Generating the Grid World of the Farmland
Page 17
17
7.3. Generating the 2D Grid World
According to Figure 7.3.1, the 2D grid world is generated from the set of aerial photographs
taken by drones previously. As shown in Figure 7.4.1, the safe areas are divided into clusters,
with each cluster consisting of squares, each designated as the workspace for single slave
drone at a given instance and each square consists of circles. Each circle is a single spray area
for a stationary slave and upon completion of all circles, a slave may be assigned a new square.
7.4. Spraying Pesticides
As illustrated in Figure 6.2.2, the workflow for spraying pesticides is as follows:
1. The farmer informs the type of crop (e.g. paddy) to central system via mobile application
app-B. Central system determines the appropriate dosage from prior knowledge.
2. Central system commands comm-drones to spray pesticides using slaves, inside their
allocated cluster.
3. Each comm-drone issues commands to its assigned slave drones to spray pesticides in the
allocated squares.
4. Each slave drone sprays pesticides being stationary over the centre of its current circle.
5. Meanwhile, any comm-drone may proceed to charging station(s) and any slave drone may
also advance to charging and/or filling station(s) as discussed in Section 6.2.
6. After finishing the whole spray job, all drones proceed to a hangar.
Page 18
18
Figure 7.4.1: Spraying Pesticides
7.5. Design of a Slave Drone
We hope to use two embedded computing platforms to design the slave drone [5]: Raspberry
Pi [58] and Arduino [59]. The proposed design is shown in Figure 7.5.
Page 19
19
7.5.1. Spray Tank
Slave drones consist of a spray tank. The spray tank is located under the lower part of the
drone as illustrated in Figure 7.5. It consists of a single solid cone (or full cone) nozzle [60]
attached to an irrigation solenoid valve with a flow meter. The tank also has two level switches
(or level sensors) to guard against the liquid volume inside the tank decreasing or increasing
beyond the allowed lower and upper limits respectively [61].
7.5.2. Charging Port
Each drone (including the comm-drones) has a charging port for recharging its battery when
the battery has drained beyond 10% of its capacity.
Figure 7.5: Design of a Slave Drone
7.5.3. Fill Valve
The filling station contains a one-way fill valve to control the passage of pesticide liquid from
the station into the spray tank. Drones are provided the geo-locations of the closest charging
and filling station(s).
Page 20
20
8. Work Plan
Figure: 8.1: Work Plan of the Research
Page 21
21
9. Brief Literature Review
Agriculture is one of the central income-generating avenues in many countries. The
characteristics of a typical harvest are vital for generating maximum income and ensuring the
safety of the consumer. There are several methods to improve the quality and quantity of the
harvest. Controlling pests with the help of pesticides is one of them. Section 9.1 will describe
possible approaches for improving the quality of crop production. Sections 9.2, 9.3 and 9.4 are
dedicated for object recognition, detection of plant water stress and plant diseases
respectively. Section 9.5 and 9.6 describe different approaches to and challenges of using
drones for agricultural purposes. Finally, section 9.7 discusses the advantages and
disadvantages of existing pesticide spraying and multi-UAV systems.
9.1. Sensing Technologies
With the development of electronic and information technologies, using sensing technologies
for crop production has started to play a major role in agricultural science and precision
agriculture. We can categorise sensing systems into broader three groups; remote sensing
imagery, machine vision and thermography [31]. Several sensing systems are described as
follows.
9.1.1. Remote Sensing Imagery
When monitoring the growing condition of a specific crop; its variety, fertilizer usage, pest
control, irrigation and growth stages are some of the important factors that a farmer should
consider. Commercial yield monitors observe the growing conditions of crops [31]. However,
they are only available for grains and cotton [31].
Airborne imagery performs yield mapping. Here, imagery in different growth stages is acquired
for yield estimation. Airborne multispectral and hyperspectral imagery is very useful for yield
management in both within-season and after-season [31].
Using robotics for harvesting via fruit detection algorithms is a superior challenge.
Furthermore, robotic harvesting is utilised for yield estimation too [31].
9.1.2. Machine Vision
Application of machine vision in harvesting is not new. For many years, computer vision
research has been considering application areas such as weed detection for pesticides
spraying, row detection for navigating autonomously in row crop farmlands or greenhouses
and fruit detection to assist harvesting robotic systems [31].
Page 22
22
One of the major challenges of using machine vision in farming is the colour-changing problem
[62] arising due to the variation in natural illumination. Since many agriculture-related
activities are performed in outdoor environments under natural sunlight, colour-changing
problem can be acute. Considering spectral changes in illumination is a solution for addressing
this issue [31].
Furthermore, machine vision uses sensing technologies for detecting water status and
nutrients, yield estimation and automatic fruit detection in food production. However, colour
similarity in fruits to tree canopy is a major challenge in fruit detection [31]. Morphological
image processing and the watershed algorithm [63] contribute to minimise this issue [32].
9.1.3. Thermography
Thermal imaging is used to estimate the number of fruits in orchards [33]. Fruit detection
using thermography is based on the temperature difference between fruits and their
surroundings. This is due to the fact that water volume of fruits is relatively higher than that of
other biomass [31]. To distinguish fruits from the surroundings, image processing algorithms
can use this thermal temperature variation [34].
9.2. Object Recognition
Enhancing human vision is another difficulty computer scientists try to overcome. In
conquering this, the concept of “object recognition” has come to center stage. Object
recognition is the process of identifying a specific object in a digital image or a video.
Distinctive invariant feature extraction from images is such an approach. This method yields a
robust match between different views (or angles) of a given image. Furthermore, features are
invariant from scaling and rotating the image. This approach provides a reliable matching even
when the images are distorted, changed in 3D viewpoint, polluted with noise and undergone
changes in illumination. Also, it has been used for object recognition utilising a fast nearest-
neighbour algorithm and the recognition process produces reliable object identification [37].
9.3. Detection of Plant Water Stress
Due to the lack of natural water resources in the world, there is a higher demand for new tools
and technologies to monitor the availability of water and to minimise water wastage when
consuming water [45].
Using a mobile sensor suite to detect water stress levels of plants is such an invention to
protect fresh water. A team of researchers introduce a suite with an infrared (IR) thermometer
for measuring leaf temperature. They have implemented linear regression models to estimate
the shaded leaf temperature. Furthermore, they have identified that stem water potential is a
key variable in all their reference models. Regression models have been used to categorise
Page 23
23
trees as water stressed or unstressed trees. However, results show that the proposed mobile
sensor suit is well suited for water irrigation management [46].
9.4. Detection of Plant Diseases
To obtain a higher quantity harvest, farmers should be cautious about plant diseases related to
cultivation. Nowadays, using thermal spectrometry for detecting usual plant diseases are
commonplace [47]. DNA based detection techniques are also popular [48] but they are neither
cost-effective nor time-saving as using thermal spectrometry.
9.5. Drones for Agriculture
Drones or Unmanned Aerial Vehicles (UAVs) have conciliated in a wider range of audience due
to the smaller size and the flexibility rather than other unmanned counterparts. With
technological developments, drones have become an essential ingredient for success in
agriculture.
“Precision agriculture” or “satellite farming” is such a farming management concept based on
observing, measuring and responding to the variety in crops. Using remote sensing
applications and tools, precision agriculture can analyse organic matter in soil [38].
Using drones with remote sensing imagery, machine vision and thermography in nexus to
precision agriculture, is a fruitful approach employed in developed countries. These
approaches can be categorised into basically three groups; usage of drones for monitoring,
irrigation management and detecting diseases in plants. Several instances among them are
described as follows.
9.5.1. Using Drones for Monitoring
9.5.1.1. VIPtero
VIPtero is a UAV developed as a tool for vineyard management. The system contains six rotors
and a multi-spectral camera for capturing images. Also, VIPtero has the capability of flying
autonomously to a predefined location. The captured images are used to identify the
heterogeneity conditions in crops via a generated vigour map [64]. This aerial platform is well
suited for small-scale farmlands [35].
9.5.1.2. Using a Lightweight UAV Spectral Camera
This is a lightweight UAV platform and consists of a Fabry-Perot Interferometer-based (FPI)
spectral camera for collecting spectrometric images in the environment. The speciality of FPI
camera is that its weight is less than 700 g. This approach processes the collected images via
image processing techniques to monitor the agricultural environment. According to the
Page 24
24
obtained results, the researchers have identified that both the performance of the FPI camera
and data processing are at a consistent level [36].
9.5.1.3. A Low-cost Agricultural Remote Sensing System based on an Autonomous UAV
Researchers have developed a helicopter platform equipped with a multi-spectral camera and
it weighs around 14 kg. This UAV system has the capability to capture multi-spectral images
from any desired location without depending on time of capturing images such as daytime and
night. An extended Kalman Filter (EKF) and sensor fusion techniques have been used for the
development of its navigation system. Furthermore, the researchers have implemented an
interface called “ground station” as the communication protocol between the drone pilot and
the UAV for mission planning, flying and real-time flight monitoring. The UAV can navigate
autonomously to the desired location defined by the ground station and collect the images via
the multi-spectral camera. The experimental results indicate that the UAV system is a flexible
and robust platform for precision agriculture [39].
9.5.2. Using Drones for Irrigation Management
9.5.2.1. Assessment of Vineyard Water Status Variability by Thermal and Multispectral
Imagery Using a UAV
This approach is developed to measure the water status of a vineyard. The system is based on a
UAV with two onboard cameras: a multispectral and thermal camera. The researchers have
identified that there is a high correlation between the values obtained from thermal and
multispectral images and the water status of the vineyard. This invention helps to identify the
deficits in water for certain trees and improves the irrigation management of a vineyard [40].
9.5.2.2. High-Resolution UAV Thermal Imagery to Assess the Variability in the Water
Status
High-resolution thermal imagery is a suitable indicator for measuring water status of trees in
commercial orchards. A set of scientists researched more on high resolution airborne thermal
imagery using a UAV equipped with a thermal camera. They have measured the potential of
stem water in five fruit tree species at three times a day. Through this measurement, the
researchers have identified that the difference between canopy and air temperature is
correlated to tree water status. Furthermore, the proposed approach has been identified as a
suitable method in precision irrigation management for commercial orchards [41].
9.5.2.3. Remote Sensing of Almond and Walnut Tree Canopy Temperatures Using an
Inexpensive IR Sensor on a Small UAV
A small UAV is a low-cost substitute for satellite and aircraft-based systems. Furthermore, a
UAV has the capability to perform considerable precise monitoring. In this research, the
Page 25
25
researchers mounted a digital camera and an IR temperature sensor on a UAV. This system
helps to sense temperature of the canopy in almond and walnut trees. The UAV is flown over
the tree canopy while capturing images and recording temperatures. The pixels of every
captured image are categorised into four groups: sunlit leaves, shaded leaves, sunlit soil and
shaded soil. Finally, a linear system of equations is developed for the identification of
temperature for each class. According to the obtained results, the researchers have identified
that there is a correlation between two temperatures: the temperatures estimated from the
linear system and the temperatures of those classes obtained by the immediate UAV flight.
Also, they have identified that the UAV system is faster and provides a higher spatial resolution
than a handheld sensor [42].
9.5.3. Using Drones for Detecting Diseases in Plants
Citrus Research Board [43] who publishes Citrograph magazine, researches on using drones
for citrus management with the aim of identifying citrus diseases [44]. Currently available
techniques for detecting diseases in plants are time-consuming and not beneficial. There are
three main advantages of using UAVs for detecting diseases and stress in plants described as
follows [44].
9.5.3.1. Cost Effectiveness
Collecting images via a satellite or a manned aircraft needs a considerable cost rather than
collecting images via a UAV.
9.5.3.2. Timeliness
Drones are capable of flying over and capturing images of a given area on a shorter notice
when comparing with other unmanned equivalents.
9.5.3.3. High-Resolution Aerial Images
Furthermore, UAVs can capture high-resolution aerial images and take clearer images by flying
in a lower altitude. The reason for the necessity of clearer images is that some plant diseases
only appear in a single branch of the tree and the rest of canopy might be viewed as healthy.
9.5.4. Using Drones for Pest Controlling
Pests are one of the threats that farmers worry about, due to the harm they do to crops.
According to reviews, one can categorise pest controlling drones into two groups: drones
controlling pests without spraying and those controlling pests via spraying pesticides.
Page 26
26
9.5.4.1. Drones Controlling Pests without Spraying Pesticides
9.5.4.1.1. SpyLight
Ninox Robotics from Australia introduced SpyLight, a cost-effective UAV to detect invasive
pests (e.g.: wild dogs, pigs, rabbits, etc.,) via real-time thermal imaging. The average flying time
of SpyLight is three to four hours. Furthermore, this unmanned system can detect a person
slinking through a forest, identify the source of fire and control a flock of sheep. If any problem
happens to the drone, it uses an air balloon to land safely[49].
9.5.4.1.2. BIRD-X
Birds are the reason for incurring billions of damages in every year to agricultural crops. BIRD-
X is a drone and provides a solution to this problem by driving away birds from crops via its
terrifying noise. This drone is easy to maintain and operate. Furthermore, BIRD-X works as a
low-cost substitution for expensive falconers. Also, this UAV can cover a larger area compared
to other drones [50].
9.5.4.2. Drones Controlling Pests via Spraying Pesticides
9.5.4.2.1. Agras MG-1S
This is one of the novel inventions from DJI group [26]. This drone system gives the capability
to the farmer to mark the target areas using a special computer software that he/she wants to
spray pesticides via the drone. Agras MG-1S can fly to those target areas automatically and
spray pesticides. This is a very low-cost and time-saving treatment when compared with
spraying biological treatments and chemical pesticides manually. Furthermore, this can
minimise the damage done to the environment compared to the magnitude of damage done
due to irregularities in manual spraying [51].
9.5.4.2.2. A Pesticide Spraying Drone from Japan
Saga university of Japan has developed an agricultural drone, which can spray pesticides to
crops which contain insects. It flies over the area of crops while scanning the area. If it finds an
area with insects, flies over closer to that area and sprays pesticides. Furthermore, the drone
can fly at night with a bug zapper and entice the bugs to reach the bug zapper [52].
9.5.4.2.3. Drones of Eagle Brother Group
Eagle Brother in China is a popular agricultural drone producer in the world. It introduced
several agricultural drone categories and different drone formations [53].
Page 27
27
9.5.4.2.4. DJI Agras MG-1S
DJI Agras MG-1S is a production of DroneAG, a company in United Kingdom for spraying
pesticides to crops. In this product, the farmer carries a device around the boundary of the area
that he/she wants to spray pesticides. The device marks the boundary of that area. Afterwards,
the drone is flown over that marked area and sprayed pesticides. This drone consists of four
batteries and each battery can support for 10 to 15 minutes flying time. Also, this drone system
contains a multi-charger for battery recharging [54].
9.5.4.2.5. Multi-Drone System from Austria
A group of researchers in Klagenfurt, Austria have introduced a multi-drone system, which can
carry cameras and fly autonomously. The aims of developing this multi-drone system are for
aerial photography and carrying objects from one location to another. Here, the researchers
have used only three drones. The desired boundary is marked manually by the user using a
computer software. Then the user marks the locations in the boundary that he/she wants to
capture the images of, via integer linear programming. Afterwards, the system identifies the
shortest flight routes for each drone and then drones take off. Captured images are placed as
UAV’s metadata storage. They are then used to develop the terrain [55].
9.6. Challenges of Using Drones in Agriculture
When using sensor technologies with drones, it is sometimes hard to find cost-effective and
lightweight sensors. Furthermore, some vital sensors work better at night, but drone flights
may sometimes not be possible during this time of the day due to government regulations [44].
Inferior quality of captured images is another difficulty drone researchers face. Drones should
fly very close to target object(s) to capture clearer images while avoiding obstacles during the
flight [44].
9.7. Discussion
Advantages and disadvantages of available pesticides and multi-UAV systems are as follows.
Page 28
28
Drone Advantages Disadvantages
1 SpyLight
Cost-effective Detect invasive pests via real-time
thermal imaging Average flying time is around three
to four hours
Uses an air balloon for landing in a dangerous situations
Cannot control pests
2 BIRD-X
Works as a predator Easy to maintain and operate Cost-effective than hiring falconers Can cover a larger area Combination of sight and sound
Cannot control pests
3 Agras MG-1S
The farmer can decide pesticides spraying areas
Cost-effective and time-saving method
Minimises the damage to the environment
Cannot avoid unsafe areas (dams, ponds, wastelands, streams, etc.)
4
A Pesticide Sprayer Drone from Japan
Identifies the areas with insects in crops
Works as a bug zapper at night
Cannot avoid unsafe areas (dams, ponds, wastelands, streams, etc.)
5
Drones of Eagle Brother Group
Sprays pesticides in a given area under the supervision of the drone pilot
Cannot avoid unsafe areas (dams, ponds, wastelands, streams, etc.)
Pesticides refilling and battery recharging are manual tasks
6 DJI Agras MG-1S
The farmer can mark any area as he/she desired, using a device
The drone can spray pesticides with a minimum human intervention
The flying time of the drone is relatively higher, due to the four batteries
Cannot avoid unsafe areas (dams, ponds, wastelands, streams, etc)
Pesticides refilling and battery recharging are manual tasks
7
Multi-Drone System from Austria
This can perform a given task more speedily due to the multi-drone platform
Can identify the shortest paths for accessing given locations
Can capture the images of a selected area and develop the terrain
Battery recharging is a manual task
Table 9.7: Advantages and the Disadvantages of Available Pesticides Systems and Multi-UAV Systems
Page 29
29
10. References
[1] “WHO | Pesticides,” WHO, 2017. [Online]. Available:
http://www.who.int/topics/pesticides/en/. [Accessed: 01-Apr-2018].
[2] J. Pretty and Z. Bharucha, “Integrated Pest Management for Sustainable Intensification of
Agriculture in Asia and Africa,” Insects, vol. 6, no. 1, pp. 152–182, Mar. 2015.
[3] K. B. Jayasekara, D. M. Dissanayake, R. Sivakanesan, A. Ranasinghe, R. H. Karunarathna, and
G. W. G. Priyantha Kumara, “Epidemiology of chronic kidney disease, with special emphasis
on chronic kidney disease of uncertain etiology, in the north central region of Sri Lanka.,” J.
Epidemiol., vol. 25, no. 4, pp. 275–80, 2015.
[4] N. R. Hill, S. T. Fatoba, J. L. Oke, J. A. Hirst, C. A. O’Callaghan, D. S. Lasserson, and F. D. R.
Hobbs, “Global Prevalence of Chronic Kidney Disease - A Systematic Review and Meta-
Analysis.,” PLoS One, vol. 11, no. 7, p. e0158765, 2016.
[5] “How to fly your DIY Raspberry Pi drone | TechRadar.” [Online]. Available:
https://www.techradar.com/how-to/how-to-fly-your-diy-raspberry-pi-drone. [Accessed:
01-Apr-2018].
[6] M. C. R. Alavanja, J. A. Hoppin, and F. Kamel, “Health Effects of Chronic Pesticide Exposure:
Cancer and Neurotoxicity,” Annu. Rev. Public Health, vol. 25, no. 1, pp. 155–197, Apr. 2004.
[7] M. G. Weisskopf, F. Moisan, C. Tzourio, P. J. Rathouz, and A. Elbaz, “Pesticide Exposure and
Depression Among Agricultural Workers in France,” Am. J. Epidemiol., vol. 178, no. 7, pp.
1051–1058, Oct. 2013.
[8] R. K. Kole, H. Banerjee, and A. Bhattacharyya, “Monitoring of market fish samples for
endosulfan and hexachlorocyclohexane residues in and around Calcutta.,” Bull. Environ.
Contam. Toxicol., vol. 67, no. 4, pp. 554–9, Oct. 2001.
[9] “The Quality of Our Nation’s Waters.” [Online]. Available:
https://pubs.usgs.gov/circ/circ1225/. [Accessed: 01-Apr-2018].
[10] “Pesticides in Selected Small Streams in the Puget Sound Basin, 1987-1995.” [Online].
Available: https://wa.water.usgs.gov/pubs/fs/fs067/psfs.html. [Accessed: 01-Apr-2018].
[11] “Source Water Protection Practices Bulletin Managing Septic Systems to Prevent
Contamination of Drinking Water,” United States Environ. Prot. Agency, vol. i, no. 4606, p.
July, 2001.
[12] M. W. Aktar, D. Sengupta, and A. Chowdhury, “Impact of pesticides use in agriculture:
their benefits and hazards.,” Interdiscip. Toxicol., vol. 2, no. 1, pp. 1–12, Mar. 2009.
[13] D. W. Knipe, “Pesticide exposure in Sri Lanka.,” Int. J. Epidemiol., vol. 45, no. 2, pp. 327–
32, 2016.
[14] “Pesticide exposure of users and agricultural workers | Anses - Agence nationale de
sécurité sanitaire de l’alimentation, de l’environnement et du travail.” [Online]. Available:
https://www.anses.fr/en/content/pesticide-exposure-users-and-agricultural-workers.
[Accessed: 01-Apr-2018].
[15] “Impact of Pesticide Use on Health in Developing Countries: Part IV: Environmental
concerns and alternatives to manufactured pesticides in agriculture and public health:
Alternative methods for pest management in developing countries.” [Online]. Available:
Page 30
30
http://collections.infocollections.org/ukedu/en/d/Jid22ie/6.6.html. [Accessed: 01-Apr-
2018].
[16] O. N. Nesheim and F. M. Fishel, “Proper Disposal of Pesticide Waste.”
[17] A. Ryan, M. Zennaro, A. Howell, R. Sengupta, and J. K. Hedrick, “An overview of emerging
results in cooperative UAV control,” in 2004 43rd IEEE Conference on Decision and Control
(CDC) (IEEE Cat. No.04CH37601), 2004, p. 602–607 Vol.1.
[18] M. A. Kovacina, D. Palmer, Guang Yang, and R. Vaidyanathan, “Multi-agent control
algorithms for chemical cloud detection and mapping using unmanned air vehicles,” in
IEEE/RSJ International Conference on Intelligent Robots and System, vol. 3, pp. 2782–2788.
[19] D. Cole, A. Goktogan, P. Thompson, and S. Sukkarieh, “Mapping and Tracking,” IEEE
Robot. Autom. Mag., vol. 16, no. 2, pp. 22–34, Jun. 2009.
[20] S. Hayat, E. Yanmaz, and R. Muzaffar, “Survey on Unmanned Aerial Vehicle Networks for
Civil Applications: A Communications Viewpoint,” IEEE Commun. Surv. Tutorials, vol. 18, no.
4, pp. 2624–2661, 2016.
[21] M. Erdelj, E. Natalizio, K. R. Chowdhury, and I. F. Akyildiz, “Help from the Sky:
Leveraging UAVs for Disaster Management,” IEEE Pervasive Comput., vol. 16, no. 1, pp. 24–
32, Jan. 2017.
[22] “Six Ways Drones Are Revolutionizing Agriculture - MIT Technology Review.” [Online].
Available: https://www.technologyreview.com/s/601935/six-ways-drones-are-
revolutionizing-agriculture/. [Accessed: 01-Apr-2018].
[23] “Drone Farming Is Revolutionizing Agriculture.” [Online]. Available:
https://www.wetalkuav.com/drone-farming-revolutionizing-agriculture/. [Accessed: 01-
Apr-2018].
[24] “List of Agricultural Drone Prices | World Agriculture.” [Online]. Available:
http://www.agrotechnomarket.com/2017/03/list-of-agricultural-drone-prices.html.
[Accessed: 01-Apr-2018].
[25] “WHO | Acute pesticide poisoning: a proposed classification tool.” [Online]. Available:
http://www.who.int/bulletin/volumes/86/3/07-041814-table-T1.html. [Accessed: 01-
Apr-2018].
[26] “DJI - The Future Of Possible.” [Online]. Available: https://www.dji.com/. [Accessed: 01-
Apr-2018].
[27] E. Yanmaz, S. Yahyanejad, B. Rinner, H. Hellwagner, and C. Bettstetter, “Drone networks:
Communications, coordination, and sensing,” Ad Hoc Networks, vol. 68, pp. 1–15, Jan. 2018.
[28] D. T. Cole, P. Thompson, A. H. Göktoğan, and S. Sukkarieh, “System Development and
Demonstration of a Cooperative UAV Team for Mapping and Tracking,” Int. J. Rob. Res., vol.
29, no. 11, pp. 1371–1399, Sep. 2010.
[29] S. Rathinam, M. Zennaro, T. Mak, and R. Sengupta, “An architecture for UAV team
control,” IFAC Proc. Vol., vol. 37, no. 8, pp. 573–578, Jul. 2004.
[30] A. Ollero, S. Lacroix, L. Merino, J. Gancet, J. Wiklund, V. Remuss, I. Veiga Perez, L. G.
Gutierrez, D. X. Viegas, M. A. Gonzalez Benitez, A. Mallet, R. Alami, R. Chatila, G. Hommel, F. J.
Colmenero Lechuga, B. C. Arrue, J. Ferruz, J. Ramiro Martinez-de Dios, and F. Caballero,
“Multiple eyes in the skies - Architecture and perception issues in the comets unmanned air
vehicles project,” IEEE Robot. Autom. Mag., vol. 12, no. 2, pp. 46–57, Jun. 2005.
Page 31
31
[31] W. S. Lee, V. Alchanatis, C. Yang, M. Hirafuji, D. Moshou, and C. Li, “Sensing technologies
for precision specialty crop production,” Comput. Electron. Agric., vol. 74, no. 1, pp. 2–33,
2010.
[32] O. Safren, V. Alchanatis, V. Ostrovsky, and O. Levi, “Detection of Green Apples in
Hyperspectral Images of Apple-Tree Foliage Using Machine Vision,” Trans. ASABE, vol. 50,
no. 6, pp. 2303–2313, 2007.
[33] J. Wachs, H. Stern, T. Burks, and V. Alchanatis, “Multi-modal Registration Using a
Combined Similarity Measure.”
[34] D. M. Bulanon, T. F. Burks, and V. Alchanatis, “Study on temporal variation in citrus
canopy using thermal imaging for citrus fruit detection,” Biosyst. Eng., vol. 101, no. 2, pp.
161–171, Oct. 2008.
[35] J. Primicerio, S. F. Di Gennaro, E. Fiorillo, L. Genesio, E. Lugato, A. Matese, and F. P.
Vaccari, “A flexible unmanned aerial vehicle for precision agriculture,” Precis. Agric., vol. 13,
no. 4, pp. 517–523, Aug. 2012.
[36] E. Honkavaara, H. Saari, J. Kaivosoja, I. Pölönen, T. Hakala, P. Litkey, J. Mäkynen, and L.
Pesonen, “Processing and assessment of spectrometric, stereoscopic imagery collected
using a lightweight UAV spectral camera for precision agriculture,” Remote Sens., vol. 5, no.
10, pp. 5006–5039, 2013.
[37] S. Keypoints and D. G. Lowe, “Distinctive Image Features from,” Int. J. Comput. Vis., vol.
60, no. 2, pp. 91–110, 2004.
[38] D. J. Mulla, “Twenty five years of remote sensing in precision agriculture: Key advances
and remaining knowledge gaps,” Biosyst. Eng., vol. 114, no. 4, pp. 358–371, 2013.
[39] H. Xiang and L. Tian, “Development of a low-cost agricultural remote sensing system
based on an autonomous unmanned aerial vehicle (UAV),” Biosyst. Eng., vol. 108, no. 2, pp.
174–190, Feb. 2011.
[40] J. Baluja, M. P. Diago, P. Balda, R. Zorer, F. Meggio, F. Morales, and J. Tardaguila,
“Assessment of vineyard water status variability by thermal and multispectral imagery
using an unmanned aerial vehicle (UAV),” Irrig. Sci., vol. 30, no. 6, pp. 511–522, 2012.
[41] V. Gonzalez-Dugo, P. Zarco-Tejada, E. Nicolás, P. A. Nortes, J. J. Alarcón, D. S. Intrigliolo,
and E. Fereres, “Using high resolution UAV thermal imagery to assess the variability in the
water status of five fruit tree species within a commercial orchard,” Precis. Agric., vol. 14,
no. 6, pp. 660–678, Dec. 2013.
[42] K. E. Crawford and K. Ethan, Remote sensing of almond and walnut tree canopy
temperatures using an inexpensive infrared sensor on a small unmanned aerial vehicle. 2014.
[43] “Citrus Research Board.” [Online]. Available: http://citrusresearch.org/. [Accessed: 01-
Apr-2018].
[44] C. Magazine, “Detecting disease,” Br. Med. J., vol. 1, no. 5066, pp. 329–330, 1958.
[45] M. C. Anderson, R. G. Allen, A. Morse, and W. P. Kustas, “Use of Landsat thermal imagery
in monitoring evapotranspiration and managing water resources,” Remote Sens. Environ.,
vol. 122, pp. 50–65, Jul. 2012.
[46] D. Slaughter, “Detection of Plant Water Stress Using Leaf Temperature and
Microclimatic Measurements in Almond, Walnut, and Grape Crops,” Trans. ASABE, no.
January, pp. 297–304, 2014.
Page 32
32
[47] W. H. K. Cheung, A. Pasamontes, D. J. Peirano, W. Zhao, E. E. Grafton-Cardwell, T. Kapaun,
R. K. Yokomi, J. Simmons, M. Doll, O. Fiehn, A. M. Dandekar, and C. E. Davis, “Volatile organic
compound (VOC) profiling of citrus tristeza virus infection in sweet orange citrus varietals
using thermal desorption gas chromatography time of flight mass spectrometry (TD-
GC/TOF-MS),” Metabolomics, vol. 11, no. 6, pp. 1514–1525, Dec. 2015.
[48] A. A. Aksenov, A. Pasamontes, D. J. Peirano, W. Zhao, A. M. Dandekar, O. Fiehn, R. Ehsani,
and C. E. Davis, “Detection of Huanglongbing Disease Using Differential Mobility
Spectrometry,” Anal. Chem., vol. 86, no. 5, pp. 2481–2488, Mar. 2014.
[49] “Ninox Robotics.” [Online]. Available: https://ninox-robotics.com/#introduction.
[Accessed: 01-Apr-2018].
[50] “Bird Control Drone | Professional drones for permanent bird control.” [Online].
Available: https://bird-x.com/bird-products/drones/. [Accessed: 01-Apr-2018].
[51] “Suppressing Agricultural Pests with Drones.” [Online]. Available:
https://enterprise.dji.com/news/detail/suppressing-agricultural-pests-with-drones.
[Accessed: 01-Apr-2018].
[52] “This Drone Sprays Pesticides Around Crops | Popular Science.” [Online]. Available:
https://www.popsci.com/agri-drone-is-precision-pesticide-machine. [Accessed: 01-Apr-
2018].
[53] “Shenzhen Eagle Brother UAV Innovation Co., Ltd. - Agricultural UAV,Agricultural
spraying drone.” [Online]. Available: https://ebuav.en.alibaba.com/. [Accessed: 01-Apr-
2018].
[54] “Drone Spraying Systems and Services from Drone AG.” [Online]. Available:
https://droneag.farm/drone-spraying/. [Accessed: 01-Apr-2018].
[55] “Communications and Path Planning of Drones.” [Online]. Available:
https://bettstetter.com/research/uav/. [Accessed: 01-Apr-2018].
[56] J. R. Jensen and J. Gao, REMOTE SENSING Remote Sensing of the Environment: An Earth
Resource Perspective. Upper Saddle River, NJ: Pearson Prentice Hall, 2007.
[57] “CS 201 - Computer Science I - Spring 2004 Project 4.” [Online]. Available:
http://www.cs.loyola.edu/~lawrie/CS201/S04/projects/P4/proj4.html. [Accessed: 01-
Apr-2018].
[58] “Raspberry Pi - Teach, Learn, and Make with Raspberry Pi.” [Online]. Available:
https://www.raspberrypi.org/. [Accessed: 10-Apr-2018].
[59] “Arduino.” [Online]. Available: https://www.arduino.cc/. [Accessed: 10-Apr-2018].
[60] “Full / Solid cone spray nozzles | ICS Industrial Services - Manufacturers of Spray
Nozzles.” [Online]. Available: http://www.icspray.co.uk/spray-nozzles/solid-cone/.
[Accessed: 10-Apr-2018].
[61] “Trillium Technologies.” [Online]. Available: http://trillium.tech/#secondary-2-ISS-
page. [Accessed: 10-Apr-2018].
[62] P. M. Granitto, P. F. Verdes, and H. A. Ceccatto, “Large-scale investigation of weed seed
identification by machine vision,” Comput. Electron. Agric., vol. 47, no. 1, pp. 15–24, Apr.
2005.
[63] “The Watershed Transform: Strategies for Image Segmentation - MATLAB &
Simulink.” [Online]. Available:
Page 33
33
https://www.mathworks.com/company/newsletters/articles/the-watershed-transform-
strategies-for-image-segmentation.html. [Accessed: 29-Apr-2018].
[64] “VIGOR MAPPING – CROP MAP.” [Online]. Available:
http://www.agroprecision.cl/en/services-view/vigor-mapping-crop-map/. [Accessed: 29-
Apr-2018].