Horticulturae,
Journal Year:
2024,
Volume and Issue:
10(8), P. 852 - 852
Published: Aug. 12, 2024
Pitaya
fruit
is
a
significant
agricultural
commodity
in
southern
China.
The
traditional
method
of
determining
the
ripeness
pitaya
by
humans
inefficient,
it
therefore
utmost
importance
to
utilize
precision
agriculture
and
smart
farming
technologies
order
accurately
identify
fruit.
In
achieve
rapid
recognition
targets
natural
environments,
we
focus
on
maturity
as
research
object.
During
growth
process,
undergoes
changes
its
shape
color,
with
each
stage
exhibiting
characteristics.
Therefore,
divided
into
four
stages
according
different
levels,
namely
Bud,
Immature,
Semi-mature
Mature,
have
designed
lightweight
detection
classification
network
for
recognizing
based
YOLOv8n
algorithm,
GSE-YOLO
(GhostConv
SPPELAN-EMA-YOLO).
specific
methods
include
replacing
convolutional
layer
backbone
model,
incorporating
attention
mechanisms,
modifying
loss
function,
implementing
data
augmentation.
Our
improved
model
achieved
accuracy
85.2%,
recall
rate
87.3%,
an
F1
score
86.23,
mAP50
90.9%,
addressing
issue
false
or
missed
intricate
environments.
experimental
results
demonstrate
that
our
enhanced
has
attained
commendable
level
discerning
ripeness,
which
positive
impact
advancement
technologies.
Horticulturae,
Journal Year:
2024,
Volume and Issue:
10(9), P. 1006 - 1006
Published: Sept. 22, 2024
The
accurate
identification
of
tomato
maturity
and
picking
positions
is
essential
for
efficient
picking.
Current
deep-learning
models
face
challenges
such
as
large
parameter
sizes,
single-task
limitations,
insufficient
precision.
This
study
proposes
MTS-YOLO,
a
lightweight
model
detecting
fruit
bunch
stem
positions.
We
reconstruct
the
YOLOv8
neck
network
propose
high-
low-level
interactive
screening
path
aggregation
(HLIS-PAN),
which
achieves
excellent
multi-scale
feature
extraction
through
alternating
fusion
information
while
reducing
number
parameters.
Furthermore,
utilize
DySample
upsampling,
bypassing
complex
kernel
computations
with
point
sampling.
Moreover,
context
anchor
attention
(CAA)
introduced
to
enhance
model’s
ability
recognize
elongated
targets
bunches
stems.
Experimental
results
indicate
that
MTS-YOLO
an
F1-score
88.7%
[email protected]
92.0%.
Compared
mainstream
models,
not
only
enhances
accuracy
but
also
optimizes
size,
effectively
computational
costs
inference
time.
precisely
identifies
foreground
need
be
harvested
ignoring
background
objects,
contributing
improved
efficiency.
provides
technical
solution
intelligent
agricultural
Horticulturae,
Journal Year:
2024,
Volume and Issue:
10(8), P. 852 - 852
Published: Aug. 12, 2024
Pitaya
fruit
is
a
significant
agricultural
commodity
in
southern
China.
The
traditional
method
of
determining
the
ripeness
pitaya
by
humans
inefficient,
it
therefore
utmost
importance
to
utilize
precision
agriculture
and
smart
farming
technologies
order
accurately
identify
fruit.
In
achieve
rapid
recognition
targets
natural
environments,
we
focus
on
maturity
as
research
object.
During
growth
process,
undergoes
changes
its
shape
color,
with
each
stage
exhibiting
characteristics.
Therefore,
divided
into
four
stages
according
different
levels,
namely
Bud,
Immature,
Semi-mature
Mature,
have
designed
lightweight
detection
classification
network
for
recognizing
based
YOLOv8n
algorithm,
GSE-YOLO
(GhostConv
SPPELAN-EMA-YOLO).
specific
methods
include
replacing
convolutional
layer
backbone
model,
incorporating
attention
mechanisms,
modifying
loss
function,
implementing
data
augmentation.
Our
improved
model
achieved
accuracy
85.2%,
recall
rate
87.3%,
an
F1
score
86.23,
mAP50
90.9%,
addressing
issue
false
or
missed
intricate
environments.
experimental
results
demonstrate
that
our
enhanced
has
attained
commendable
level
discerning
ripeness,
which
positive
impact
advancement
technologies.
