Title: SAR information extraction Primitive features for radar data mining
1SAR information extractionPrimitive features for
radar data mining
M.Quartulli, M.Datcu
2Approaches to vision
- D. Marr 1982 Vision, Freeman NY
- Feature-based
- Bottom-up
- - Building representations out of signals
- D.Ballard 1991 Animate Vision
- In Artificial intelligence 48, pp. 57-86
- Objective-based
- Well-posed localized problem
- Makes use of prior information
3KimV primitive feature extraction
4Approaches for IE
SRTM Baltimore, 25m
XSAR Bern, 30m
RSAT LasVegas, 15m
Intermap Maastricht, 0.5m
5Bayesian model-based IE
- Existing models or explicit assumptions for p(S)
- Hierarchies of models
6Bayesian information extraction
GMRF Space Variant G(.) Likelihood
Despeckled backscatter intensity
Backscatter Intensity texture norm
Backscatter intensity
SRTM Baltimore, 25m
7Bayesian information extraction
GMRF Space Variant Gaussian Likelihood
Clean elevation map
Elevation texture norm
DEM elevation map
SRTM Baltimore, 25m
8Feature fusion for 3D urban characterization
e.g. as a fusion of features derived from
intensity, height
9Feature fusion for 3D characterization
dense urbanized
medium urbanized
light urbanized
forest
agricultural
water
Baltimore, USA
10Building detection from SRTM data
Baltimore, USA
11Building detection from SRTM data
water/shadow
sparse urbanized
building
forest
agricultural
Baltimore, USA
12Feature fusion for building reconstruction
by resolving high-resolution detail
Baltimore, USA
13Feature fusion for building reconstruction
Baltimore, USA
14Feature fusion for building identification
Intermap Munich East, 0.5m
15Urban metric SAR information extraction
- Historical buildings, moving vehicles, open
windows, cars on roofs - What models? How many parameters?
E-SAR Dresden, 0.5m
16Urban metric SAR information extraction
17Marked point processes
S X(s) s in D
X(s) (wi,hi,a,t)
Wx,wy,h,a,t
Wx,wy,h,a,t
18Marked point processes
S X(s) s in D, X(s) (wi,hi,a,t)
Uniformly distributed
19Reconstruction of built-up areasthrough marked
point processes
20Hierarchic geometrical models
A measure of the quality of the
reconstruction p(XD)
21Hierarchic geometrical models
A measure of the quality of the
reconstruction p(XD) 1/Z exp -U(XD)
22Likelihood for metric urban SAR
Objects in spatial relationships Slowly varying
small number of scatterers per resolution cell
(NOT speckle)
Intermap Oberpfaffenhofen, 2m
23Hierarchic geometrical models
The potential U(XD) is decomposed U(XD)
SSij Ul(pkfik) Si Up(xi xj) into interaction
model Up(xixj) intersection
measure(xi,xj) taking into account up to two-term
interactions data model Inverse Gaussian
(slowly varying small number of scatterers)
24Likelihood Ratio scattering/clutter
Intermap Oberpfaffenhofen, 2m
25Geometrical modelling of industrial buildings
Intermap Oberpfaffenhofen, 2m
26Reconstruction of built up areasby stochastic
geometry
Intermap Maastricht, 0.5 m
27Conclusions
- HR InSAR urban Scene Understanding by
- Pixel-based Information Fusion
- Can fuse/aggregate multiple information layers
- Intensity, Coherence, Phase
- Object-Based Scene Understanding
- explicit Scene Modeling
- better use of Sensor Modeling in
geometry/radiometry - results ready for 3d applications