Linear isotropic diffusion equation,
150
Linear scale space (SS), 7, 149
approaches, 173–174
Linear spectral mixture analysis
(LSMA), 67
Line segment detector (LSD), 176–177,
180–181, 183–185, 189, 190
algorithm, 177
data, 45, 69
LST–NDVI relationship, 45–46
LST–vegetation relationship, 68
regression modeling, 69–70
coefficients and variables for urban
morphology, 70
residuals, distribution, 70
Local spatial rotation, 272–273
first-order coefficients, 273
nonzero coefficient, 273
Lolium perenne L., 128
LSD. See Line segment detector (LSD)
LST. See Land surface temperature (LST)
Machine learning approach, 201
Marion County, 233
aggregation scales, potentially link
to, 250–251
data sets, of satellite images, 234
efficiency of fractal measurement, for
detecting scaling properties, 250
fractal analysis
for temporal change
characterization, 248–249
using LULC classes, 242–243
using LULC maps, 239
using raw images, 237–239
using raw red bands classified by LULC
classes, 239–242
using resampled raw red images,
242–248
IKONOS data, 234
information of satellite images, 235–236
Lacunarity analysis, use of, 250
landscape characterization, at multiple
scales by fractal
measurement, 236–237
pixel aggregation levels, 250
sensor’s nominal spatial resolution,
249–250
total area, 233
total population, 233
use of fragmented raw red bands filtered
by LULC types, 249
using traditional ISODATA unsupervised
algorithm, 250
values of the root meansquare error
(RMSE), 234
MAUP. See Modifiable areal unit problem
(MAUP)
Mean-shift algorithm, 185
Mean-shift segmentation, 202
Medium-resolution Landsat imagery, 83
Medium spatial-resolution images, 65
Meteorology, 35
Microwave sensors, 7
Moderate resolution imaging
spectroradiometer (MODIS), 36
data, 39, 42–43, 45
images, 82
provide high temporal resolution, 84
multiple TIR bands, 36
in NASA Aqua mission, 36
Modifiable areal unit problem (MAUP), 68,
69, 109
Modified “scaling ladder,” 162
MODIS. See Moderate-resolution imaging
spectroradiometer (MODIS)
Monte Carlo simulation, 110
MSEG algorithm, 173, 176, 178, 180–181,
183, 185, 188, 191
applied on a scale-space AML
representation, 185
classification accuracy with, 186
edge-constrained, 184–186
standard, 183
without parameter tuning, 185
MSS. See Landsat Multispectral Scanner
(MSS)
Multiplatform sensor systems, 83
Multiple census scales, 69
Multiple-resolution analysis, 109
Multiresolution segmentation, 203
Multiresolution wavelet transform, 269
Multiscale analysis, 143, 146, 173, 273
blob–feature detection, 151–156
census-basedLSTvariations, 69
components, 148
linear scale space, 149–151
INDEX
329
150
Linear scale space (SS), 7, 149
approaches, 173–174
Linear spectral mixture analysis
(LSMA), 67
Line segment detector (LSD), 176–177,
180–181, 183–185, 189, 190
algorithm, 177
data, 45, 69
LST–NDVI relationship, 45–46
LST–vegetation relationship, 68
regression modeling, 69–70
coefficients and variables for urban
morphology, 70
residuals, distribution, 70
Local spatial rotation, 272–273
first-order coefficients, 273
nonzero coefficient, 273
Lolium perenne L., 128
LSD. See Line segment detector (LSD)
LST. See Land surface temperature (LST)
Machine learning approach, 201
Marion County, 233
aggregation scales, potentially link
to, 250–251
data sets, of satellite images, 234
efficiency of fractal measurement, for
detecting scaling properties, 250
fractal analysis
for temporal change
characterization, 248–249
using LULC classes, 242–243
using LULC maps, 239
using raw images, 237–239
using raw red bands classified by LULC
classes, 239–242
using resampled raw red images,
242–248
IKONOS data, 234
information of satellite images, 235–236
Lacunarity analysis, use of, 250
landscape characterization, at multiple
scales by fractal
measurement, 236–237
pixel aggregation levels, 250
sensor’s nominal spatial resolution,
249–250
total area, 233
total population, 233
use of fragmented raw red bands filtered
by LULC types, 249
using traditional ISODATA unsupervised
algorithm, 250
values of the root meansquare error
(RMSE), 234
MAUP. See Modifiable areal unit problem
(MAUP)
Mean-shift algorithm, 185
Mean-shift segmentation, 202
Medium-resolution Landsat imagery, 83
Medium spatial-resolution images, 65
Meteorology, 35
Microwave sensors, 7
Moderate resolution imaging
spectroradiometer (MODIS), 36
data, 39, 42–43, 45
images, 82
provide high temporal resolution, 84
multiple TIR bands, 36
in NASA Aqua mission, 36
Modifiable areal unit problem (MAUP), 68,
69, 109
Modified “scaling ladder,” 162
MODIS. See Moderate-resolution imaging
spectroradiometer (MODIS)
Monte Carlo simulation, 110
MSEG algorithm, 173, 176, 178, 180–181,
183, 185, 188, 191
applied on a scale-space AML
representation, 185
classification accuracy with, 186
edge-constrained, 184–186
standard, 183
without parameter tuning, 185
MSS. See Landsat Multispectral Scanner
(MSS)
Multiplatform sensor systems, 83
Multiple census scales, 69
Multiple-resolution analysis, 109
Multiresolution segmentation, 203
Multiresolution wavelet transform, 269
Multiscale analysis, 143, 146, 173, 273
blob–feature detection, 151–156
census-basedLSTvariations, 69
components, 148
linear scale space, 149–151
INDEX
329