Title: Statistics in the Image Domain for Mobile Robot Environment Modeling
1Statistics in the Image Domain forMobile Robot
Environment Modeling
- L. Abril Torres-Méndez and Gregory Dudek
- Centre for Intelligent Machines
- School of Computer Science
- McGill University
2Our Application
- Automatic generation of 3D maps.
- Robot navigation, localization
- - Ex. For rescue and inspection tasks.
- Robots are commonly equipped with camera(s) and
laser rangefinder. - Would like a full range map of the
- the environment.
- Simple acquisition of data
3Problem Context
- Pure vision-based methods
- Shape-from-X remains challenging, especially in
unconstrained environments. - Laser line scanners are commonplace, but
- Volume scanners remain exotic, costly, slow.
- Incomplete range maps are far easier to obtain
that complete ones. - Proposed solution Combine visual and partial
depth Shape-from-(partial) Shape -
4Problem Statement
From incomplete range data combined with
intensity, perform scene recovery.
5Overview of the Method
- Approximate the composite of intensity and
range data at each point as a Markov process. - Infer complete range maps by estimating joint
statistics of observed range and intensity.
6What knowledge does Intensity provide about
Surfaces?
- Two examples of kind of inferences
Intensity image Range image
7What about Edges?
- Edges often detect depth discontinuities
- Very useful in the reconstruction process!
Intensity Range
edges
8Isophotes in Range Data
- Linear structures from initial range data
- All normals forming same angle with direction to
eye
Intensity Range
9Range synthesis basis
- Range and intensity images are correlated, in
- complicated ways, exhibiting useful
structure. - - Basis of shape from shading shape from
darkness, but they are based - on strong assumptions.
- The variations of pixels in the intensity and
range images are related to the values
elsewhere in the image(s).
Markov Random Fields
10Related Work
- Probabilistic updating has been used for
- image restoration e.g. Geman Geman, TPAMI
1984 as well as - texture synthesis e.g. Efros Leung, ICCV
1999. - Problems Pure extrapolation/interpolation
- is suitable only for textures with a stationary
distribution - can converge to inappropriate dynamic equilibria
11MRFs for Range Synthesis
- States are described as augmented voxels
V(I,R,E). - Zm(x,y)1x,ym mxm lattice over which the
image are described. - I Ix,y, (x,y)? Zm intensity (gray or color)
of the input image - E is a binary matrix (1 if an edge exists and 0
otherwise). - RRx,y, (x,y)? Zm incomplete depth values
- We model V as an MRF. I and R are random
variables.
R
vx,y
I
12Markov Random Field Model
- Definition A stochastic process for which a
voxel value is predicted by its neighborhood in
range and intensity.
Nx,y is a square neighborhood of size nxn
centered at voxel Vx,y.
13Computing the Markov Model
- From observed data, we can explicitly compute
Nx,y
Vx,y
- This can be represented parametrically or via a
table. - To make it efficient, we use the sample data
itself as a table.
14Estimation using the Markov Model
- Fromwhat should an unknown range value be?
- For an unknown range value with a known
- neighborhood, we can select the
maximum - likelihood estimate for Vx,y.
15Interpolate PDF
- In general, we cannot uniquely solve the desired
neighborhood configuration, instead assume
The values in Nu,v are similar to the values in
Nx,y, (x,y) ? (u,v). Similarity measure
Gaussian-weighted SSD (sum of squared
differences). Update schedule is purely
causal and deterministic.
16Order of Reconstruction
- Dramatically reflects the quality of result
- Based on priority values of voxels to be
synthesize - EdgesIsophotes indicate which voxels are
synthesized first
- ? Region to be synthesized (target region)
- ?? The contour of target region
- ? The source region ? ?i ?r
17Priority value computation
Confidence value
Data term value
18Experimental Evaluation
Input data given to our algorithm
Scharstein Szeliskis Data Set Middlebury
College
19Isophotes vs. no Isophotes Constraint
Results without isophotes
Results using isophotes
Synthesized range images
20More examples
Synthesized result. MAR error 5.94 cms.
21More examples
Synthesized result. MAR error 5.44 cms.
22More examples
Synthesized result. MAR error 7.54 cms.
23Adding Surface Normals
- We compute the normals by fitting a plane
- (smooth surface) in windows of mxm pixels.
- Normal vector Eigenvector with the smallest
eigenvalue of the covariance matrix. - Similarity is now computed between surface
- normals instead of range values.
24Adding Surface Normals
25More Experimental Results
Initial range scans
Synthesized range image
26 More Experimental Results
Synthesized range image
27Conclusions
- Works very well -- is this consistent?
- Can be more robust than standard methods (e.g.
shape from shading) due to limited dependence on
a priori reflectance assumptions. - Depends on adequate amount of reliable range as
input. - Depends on statistical consistency of region to
be constructed and region that has been measured.
28Discussion Ongoing Work
- Surface normals are needed when the input range
data do not capture the underlying structure - Data from real robot
- Issues non-uniform scale, registration,
correlation on different type of data - Integration of data from different viewpoints
29Questions ?