iScience,
Journal Year:
2023,
Volume and Issue:
26(3), P. 106132 - 106132
Published: Feb. 3, 2023
The
proliferation
of
street
view
images
(SVIs)
and
the
constant
advancements
in
deep
learning
techniques
have
enabled
urban
analysts
to
extract
evaluate
perceptions
from
large-scale
streetscapes.
However,
many
existing
analytical
frameworks
been
found
lack
interpretability
due
their
end-to-end
structure
"black-box"
nature,
thereby
limiting
value
as
a
planning
support
tool.
In
this
context,
we
propose
five-step
machine
framework
for
extracting
neighborhood-level
panoramic
SVIs,
specifically
emphasizing
feature
result
interpretability.
By
utilizing
MIT
Place
Pulse
data,
developed
can
systematically
six
dimensions
given
panoramas,
including
wealth,
boredom,
depression,
beauty,
safety,
liveliness.
practical
utility
is
demonstrated
through
its
deployment
Inner
London,
where
it
was
used
visualize
at
Output
Area
(OA)
level
verify
against
real-world
crime
rate.
Computers Environment and Urban Systems,
Journal Year:
2022,
Volume and Issue:
95, P. 101809 - 101809
Published: May 4, 2022
Characterising
and
analysing
urban
morphology
is
a
continuous
task
in
data
science,
environmental
analyses,
many
other
domains.
As
the
availability
quality
of
on
them
have
been
increasing,
buildings
gained
more
attention.
However,
tools
facilitating
large-scale
studies,
together
with
an
interdisciplinary
consensus
metrics,
remain
scarce
often
inadequate.
We
present
Global
Building
Morphology
Indicators
(GBMI)
—
three-pronged
contribution
addressing
such
shortcomings:
(i)
comprehensive
list
hundreds
building
form
multi-scale
measures
derived
through
systematic
literature
review;
(ii)
methodology
tool
for
computation
these
metrics
database
suited
big
comparative
release
code
freely
open-source;
(iii)
we
carry
out
computations
using
high
performance
computing,
generating
public
repository
quantifying
selected
areas
around
world,
demonstrate
their
value
novel
analyses
comparing
morphological
parameters
across
cities.
GBMI
introduces
formalised,
structured,
modular,
extensible
method
to
compute,
manage,
disseminate
indicators
at
large
scale
resolution,
while
precomputed
dataset
facilitates
studies.
The
theory
implementation
traverse
multiple
scales:
level,
both
individual
contextual
ones
based
encircling
by
buffers,
aggregations
several
hierarchical
administrative
levels
grids.
Our
open
dataset,
comprising
billions
records
growing
scope
worldwide,
most
instance
parametrising
stock,
supporting
studies
analytics
range
disciplines.
International Journal of Applied Earth Observation and Geoinformation,
Journal Year:
2022,
Volume and Issue:
112, P. 102859 - 102859
Published: June 17, 2022
3D
building
models
are
an
established
instance
of
geospatial
information
in
the
built
environment,
but
their
acquisition
remains
complex
and
topical.
Approaches
to
reconstruct
often
require
existing
(e.g.
footprints)
data
such
as
point
clouds,
which
scarce
laborious
acquire,
limiting
expansion.
In
parallel,
street
view
imagery
(SVI)
has
been
gaining
currency,
driven
by
rapid
expansion
coverage
advances
computer
vision
(CV),
it
not
used
much
for
generating
city
models.
Traditional
approaches
that
can
use
SVI
reconstruction
multiple
images,
while
practice,
only
few
street-level
images
provide
unobstructed
a
building.
We
develop
from
single
image
using
image-to-mesh
techniques
modified
CV
domain.
regard
three
scenarios:
(1)
standalone
single-view
reconstruction;
(2)
aided
top
delineating
footprint;
(3)
refinement
models,
i.e.
we
examine
enhance
level
detail
block
(LoD1)
common.
The
results
suggest
trained
supporting
able
overall
geometry
building,
first
scenario
may
derive
approximate
mass
useful
infer
urban
form
cities.
evaluate
demonstrating
usefulness
volume
estimation,
with
mean
errors
less
than
10%
last
two
scenarios.
As
is
now
available
most
countries
worldwide,
including
many
regions
do
have
footprint
and/or
data,
our
method
rapidly
cost-effectively
without
requiring
any
information.
Obtaining
hitherto
did
any,
enable
number
analyses
locally
time.
