International Journal of Computing and Digital Systems,
Год журнала:
2024,
Номер
15(1), С. 661 - 672
Опубликована: Май 8, 2024
Mangrove
preservation
is
crucial
due
to
their
ecological
significance
impact.Monitoring
the
health
of
mangrove
forests
essential
for
strategy,
yet
it
remains
challenging
and
time-intensive,
particularly
in
remote
locations.This
study
aims
create
system
automatically
assess
density,
providing
data
informed
strategies,
such
as
prioritizing
reforestation
low
density
area.Using
drones
with
RGB
cameras
capture
aerial
imagery,
enabling
collection.The
utilizes
YOLO
neural
network
object
detector
detect
objects,
quantity
estimation.Experiment
shows
that
able
tree
accurately
95%
recall,
88.3%
IoU,
22ms
processing
time.The
uses
'tiny'
model
variant
provide
more
efficient
accuracy
compared
computation
resource,
making
suitable
deployment
on
computer
limited
resources.In
comparison
standard
improves
recall
by
4%,
IoU
2%,
but
demands
six
times
time.Then
calculate
covered
area
using
camera
transformation
formula.Finally,
calculates
forest
health,
synchronized
GPS
location.With
resulting
evaluations
become
much
easier,
facilitating
effective
actions,
density.
The
earth's
vegetation
plays
a
pivotal
role
in
the
ecosystem
equilibrium
and
serves
as
an
environmental
health
indicator.
Monitoring
is
essential
for
informed
agriculture,
resource
management,
ecological
understanding,
tracking.
Remote
sensing
data
offers
valuable
insights
into
plant
life,
benefiting
biodiversity,
forestry,
urban
green
systems.
In
this
provides
unbiased
foundation
yield
management
crop
production
prediction.
Vegetation
indices
(VIs)
are
vital
assessing
health,
growth,
physiological
conditions.
They
mitigate
atmospheric
interference
widely
used
agriculture
to
monitor
estimate
yields,
study
dynamics,
including
chlorophyll
content
estimation.
Current
techniques
such
handheld
spectrometers
satellite
imagery
effective
but
limited.
Handheld
require
time-consuming
field
measurements,
restricting
spatial
coverage.
Satellite
methods
face
resolution,
cloud
interference,
cost,
real-time
insight
challenges.
Recent
advancements
computer
vision,
driven
by
machine
learning,
offer
transformative
potential.
Computer
vision
can
process
from
drone
automated
accurate
VI
measurements.
This
integration
opens
avenues
precision
monitoring.
chapter
explores
synergy
between
assessment
delving
technical
aspects,
application,
challenges,
future
opportunities.
It
envisions
promising
through
remote
integration.
Applied Sciences,
Год журнала:
2024,
Номер
14(19), С. 9132 - 9132
Опубликована: Окт. 9, 2024
Despite
technological
growth
and
worldwide
advancements
in
various
fields,
the
agriculture
sector
continues
to
face
numerous
challenges
such
as
desertification,
environmental
pollution,
resource
scarcity,
excessive
use
of
pesticides
inorganic
fertilizers.
These
unsustainable
problems
agricultural
field
can
lead
land
degradation,
threaten
food
security,
affect
economy,
put
human
health
at
risk.
To
mitigate
these
global
issues,
it
is
essential
for
researchers
professionals
promote
smart
by
integrating
modern
technologies
Internet
Things
(IoT),
Unmanned
Aerial
Vehicles
(UAVs),
Wireless
Sensor
Networks
(WSNs),
more.
Among
technologies,
this
paper
focuses
on
UAVs,
particularly
quadcopters,
which
assist
each
phase
cycle
improve
productivity,
quality,
sustainability.
With
their
diverse
capabilities,
quadcopters
have
become
most
widely
used
UAVs
are
frequently
utilized
projects.
explore
different
aspects
quadcopters’
agriculture,
following:
(a)
unique
advantages
over
other
including
an
examination
quadcopter
types
agriculture;
(b)
missions
where
deployed,
with
examples
highlighting
indispensable
role;
(c)
modelling
from
configurations
derivation
mathematical
equations,
create
a
well-modelled
system
that
closely
represents
real-world
conditions;
(d)
must
be
addressed,
along
suggestions
future
research
ensure
sustainable
development.
Although
has
been
discussed
papers,
best
our
knowledge,
none
specifically
examined
popular
among
them,
“quadcopters”,
particular
terms
types,
applications,
techniques.
Therefore,
provides
comprehensive
survey
offers
engineers
valuable
insights
into
evolving
field,
presenting
roadmap
enhancements
developments.
E3S Web of Conferences,
Год журнала:
2025,
Номер
614, С. 03021 - 03021
Опубликована: Янв. 1, 2025
This
article
presents
a
method
for
automated
apple
counting
using
high-resolution
images
obtained
from
unmanned
aerial
vehicles
(UAVs).
The
YOLO11
architecture,
specifically
models
YOLO11n
to
YOLO11x,
was
employed
fruit
detection.
Key
steps
included
creating
orthophotos,
segmenting
data
into
tiles,
training
convolutional
neural
network
(CNN)
with
transfer
learning
and
augmentation,
merging
results.
Images
were
captured
DJI
Mavic
3
Multispectral
drone
20
MP
RGB
camera.
Data
augmentation
including
flipping,
hue
adjustment,
blurring,
Tile
8×8
transformation
increased
the
dataset
11
2,000
51,797
objects
(34,383
apples
17,414
fallen
apples).
YOLO11x
model
achieved
highest
performance
metrics:
mAP@50
=
0.816,
mAP@50-95
0.547,
Precision
0.852,
Recall
0.766,
demonstrating
its
effectiveness
in
complex,
high-density
orchards.
model,
lower
computational
demands,
is
suitable
resource-limited
environments.
maintains
geospatial
alignment
visualizes
distribution
across
orchard.
An
experimentally
determined
correction
coefficient
will
account
fruits
hidden
camera,
enhancing
accuracy
of
yield
estimation.
A
Tkinter
interface
displays
detection
results
summary
each
orchard
section.
Future
work
includes
integrating
multispectral
3D
modeling
enhance
precision.
These
findings
highlight
potential
deep
automate
monitoring
assessment.
Ciência Florestal,
Год журнала:
2025,
Номер
unknown, С. e88522 - e88522
Опубликована: Май 2, 2025
Accurate
and
low-cost
tree
inventories
in
forest
plantations
are
essential
for
an
effective
production
management.
Stimulated
by
recent
advancements
Unmanned
Aerial
Vehicle
(UAV)
imagery
coupled
with
artificial
intelligence,
the
interest
developing
models
capable
of
supporting
decision-making
on
silvicultural
management,
this
study
aimed
to
evaluate
performance
different
vegetation
indices
detecting
Eucaliptus
saligna
individuals
using
improved
deep
learning
model.
The
tree-individual
detection
model
was
created
YOLOv8n
algorithm
UAV
RGB
images
(VI)
generated
from
multispectral
sensor
onboard
UAV.
Nine
VIs
were
selected
training
(65%)
testing
(35%)
models.
proposed
framework
demonstrated
that
MPRI,
PSRI,
NDVI
achieved
F1
score
0.98
a
precision
0.97
E.
individual
trees
six
months
after
planting.
Our
demonstrates
robustness
recommends
application
MPRI
index
due
its
efficient
performance,
cost-effectiveness,
simplicity,
as
it
only
utilizes
regions
visible
spectrum.
Remote Sensing,
Год журнала:
2024,
Номер
16(8), С. 1365 - 1365
Опубликована: Апрель 12, 2024
Remote
sensing
is
a
well-established
tool
for
detecting
forest
disturbances.
The
increased
availability
of
uncrewed
aerial
systems
(drones)
and
advances
in
computer
algorithms
have
prompted
numerous
studies
insects
using
drones.
To
date,
most
used
height
information
from
three-dimensional
(3D)
point
clouds
to
segment
individual
trees
two-dimensional
multispectral
images
identify
tree
damage.
Here,
we
describe
novel
approach
classifying
the
reflectances
assigned
3D
cloud
into
damaged
healthy
classes,
retaining
assessment
vertical
distribution
damage
within
tree.
Drone
were
acquired
27-ha
study
area
Northern
Rocky
Mountains
that
experienced
recent
then
processed
produce
cloud.
Using
data
points
on
(based
depth
maps
images),
random
(RF)
classification
model
was
developed,
which
had
an
overall
accuracy
(OA)
98.6%,
when
applied
across
area,
it
classified
77.0%
with
probabilities
greater
than
75.0%.
Based
segmented
trees,
developed
evaluated
separate
trees.
For
identified
severity
each
based
percentages
red
gray
top-kill
length
continuous
treetop.
Healthy
separated
high
(OA:
93.5%).
remaining
different
severities
moderate
70.1%),
consistent
accuracies
reported
similar
studies.
A
subsequent
algorithm
91.8%).
as
(78.3%),
exhibited
some
amount
(78.9%).
Aggregating
tree-level
metrics
30
m
grid
cells
revealed
several
hot
spots
severe
illustrating
potential
this
methodology
integrate
products
space-based
remote
platforms
such
Landsat.
Our
results
demonstrate
utility
drone-collected
monitoring
structure
diseases.
Applied Sciences,
Год журнала:
2024,
Номер
14(17), С. 7695 - 7695
Опубликована: Авг. 31, 2024
Efficient
diagnosis
of
apple
diseases
and
pests
is
crucial
to
the
healthy
development
industry.
However,
existing
single-source
image-based
classification
methods
have
limitations
due
constraints
input
image
information,
resulting
in
low
accuracy
poor
stability.
Therefore,
a
method
for
disease
pest
areas
based
on
multi-source
fusion
proposed
this
paper.
Firstly,
RGB
images
multispectral
are
obtained
using
drones
construct
an
canopy
dataset.
Secondly,
vegetation
index
selection
saliency
attention
proposed,
which
uses
multi-label
ReliefF
feature
algorithm
obtain
importance
scores
indices,
enabling
automatic
indices.
Finally,
area
model
named
AMMFNet
constructed,
effectively
combines
advantages
images,
performs
data-level
data,
channel
mechanisms
exploit
complementary
aspects
between
data.
The
experimental
results
demonstrated
that
achieves
significant
subset
92.92%,
sample
85.43%,
F1
value
86.21%
dataset,
representing
improvements
8.93%
10.9%
compared
prediction
only
or
images.
also
proved
can
provide
technical
support
coarse-grained
positioning
orchards
has
good
application
potential
planting
