International Journal of Applied Earth Observation and Geoinformation,
Год журнала:
2024,
Номер
130, С. 103870 - 103870
Опубликована: Май 15, 2024
Although
the
photon
point
cloud
data
acquired
from
ICESat-2/ATLAS
can
be
efficiently
employed
in
urban
building
height
extraction,
its
universal
applicability
undulating
terrain
scenarios
is
constrained,
and
there
are
noticeable
issues
of
false
positives
negatives.
This
research
establishes
a
terrain-adaptive
methodological
framework
based
on
to
extract
high-precision,
high-density
across
varied
topographical
conditions.
First,
elevation
buffer
utilized
coarse
denoise
cloud,
involving
removal
majority
noise
photons
scene,
thereby
enhancing
efficiency
subsequent
algorithms.
Second,
signal
extracted
remaining
original
using
Adaptive
Method
Based
Single-Photon
Spatial
Distribution
(SPSD-AM).
approach
demonstrates
high
universality
various
scenes,
while
simultaneously
ensuring
stable
accuracy
extraction.
Subsequently,
ground
fit
curve
Differences
Urban
Signal
Photons
(USPSD-AM),
which
addresses
challenge
potential
mixing
complex
scenarios.
A
precise
then
photons.
In
order
mitigate
such
as
negatives,
post-processing
steps,
including
completion
denoising
photons,
implemented.
Finally,
adopted
accurate
parameters.
The
precision
verification
results
show
that
heights
considerably
consistent
with
reference
heights.
mean
RMSE
MAE
0.273
m
0.202
for
flat
terrains
1.168
0.759
terrains,
respectively.
proposed
method
superior
diverse
scenarios,
providing
robust
theoretical
foundation
large-scale
retrieval
efforts.
International Journal of Applied Earth Observation and Geoinformation,
Год журнала:
2022,
Номер
114, С. 103048 - 103048
Опубликована: Окт. 7, 2022
Horizontal
and
vertical
patterns
of
built-up
land
are
essential
to
analyse
a
range
environmental
change
impacts,
such
as
exposure
natural
hazards,
urban
heat
islands,
trapping
air
pollution,
well
for
decision
making
in
this
context.
However,
while
data
on
horizontal
abundant,
they
relatively
rare
patterns.
Here,
we
present
global
maps
3D
at
1-km2
resolution
the
nominal
year
2015.
These
estimated
using
random
forest
models,
fed
with
wide
spatial
trained
reference
from
all
continents
except
Antarctica.
Independent
testing
indicates
that
R2
values
models
footprint,
height,
volume
equal
0.89,
0.73,
0.84,
respectively.
Our
results
show
buildings
worldwide
6.16-m
high
average,
total
building
is
1645
km3,
which
equivalent
solid
cube
12
km
each
side.
Yet,
find
large
variations
patterns,
both
within
across
world
regions.
In
particular,
floor
space
per
person
exceeds
200
m2
Oceania
North
America,
it
only
29
South
Asia
38
Sub-Saharan
Africa.
provide
novel
insights
into
distribution
offer
new
opportunities
assessments
impacts.
The
height
can
be
downloaded
https://doi.org/10.34894/4QAGYL.
Abstract
Understanding
the
spatiotemporal
dynamics
of
global
3D
urban
expansion
over
time
is
becoming
increasingly
crucial
for
achieving
long-term
development
goals.
In
this
study,
we
generated
a
dataset
annual
(1990–2010)
using
World
Settlement
Footprint
2015
data,
GAIA
and
ALOS
AW3D30
data
with
three-step
technical
framework:
(1)
extracting
constructed
land
to
generate
research
area,
(2)
neighborhood
analysis
calculate
original
normalized
DSM
slope
height
each
pixel
in
study
(3)
correction
areas
greater
than
10°
improve
accuracy
estimated
building
heights.
The
cross-validation
results
indicate
that
our
reliable
United
States(R
2
=
0.821),
Europe(R
0.863),
China(R
0.796),
across
world(R
0.811).
As
know,
first
30-meter
globe,
which
can
give
unique
information
understand
address
implications
urbanization
on
food
security,
biodiversity,
climate
change,
public
well-being
health.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,
Год журнала:
2024,
Номер
17, С. 6514 - 6528
Опубликована: Янв. 1, 2024
Extracting
building
heights
from
single-view
remote
sensing
images
greatly
enhances
the
application
of
data.
While
methods
for
extracting
height
shadow
have
been
widely
studied,
it
remains
a
challenging
task.
The
main
reasons
are
as
follows:
(1)
traditional
method
information
exhibits
low
accuracy.
(2)
use
only
to
extract
results
in
limited
scenarios.
To
solve
above
problems,
this
paper
introduces
side
and
complement
each
other,
proposes
extraction
high-resolution
using
information.
Firstly,
we
propose
RMU-Net
method,
which
utilizes
multi-scale
features
This
aims
address
issues
related
pixel
detail
loss
imprecise
edge
segmentation,
result
significant
scale
differences
within
segmentation
targets.
Additionally,
employ
area
threshold
optimize
results,
specifically
tackle
small
stray
patches
holes,
enhancing
overall
integrity
accuracy
extraction.
Secondly,
that
integrates
based
on
an
enhanced
proportional
coefficient
model.
measuring
lengths
is
improved
by
incorporating
fishing
net
informed
our
analysis
geometric
relationships
among
buildings.
Finally,
establish
dataset
containing
images,
select
multiple
areas
experimental
analysis.
demonstrate
91.03%
90.29%.
average
absolute
error
(MAE)
1.22,
while
root
mean
square
(RMSE)
1.21.
Furthermore,
proposed
method's
validity
scalability
affirmed
through
analyses
applicability
anti-interference
performance
extensive
areas.
