department of engineering science dtam: dense tracking and mapping in real-time newcombe, lovegrove...
TRANSCRIPT
DEPARTMENT OF ENGINEERING SCIENCE
DTAM: Dense Tracking and Mapping in Real-Time
Newcombe, Lovegrove & Davison ICCV11
Amaury DameActive Vision Lab
Oxford Robotics Research [email protected]
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 2
Introduction
Input :
• Single hand held RGB camera
Objective :
• Dense mapping• Dense tracking
Input image
3D dense map
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 3
System overview
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 4
Depth map estimationPrinciple:
• S depth hypothesis are considered for each pixel of the reference image I
r
• Each corresponding 3D point is projected onto a bundle of images I
m
• Keep the depth hypothesis that best respects the color consistency from the reference to the bundle of images
Formulation:
• : pixel position and depth hypothesis
• : number of valid reprojection of the pixel in the bundle
• : photometric error between reference and current image
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 5
Depth map estimation
Reprojection of depth hypotheses on one image of
bundle
Example reference image pixel
Depth hypotheses
Rep
roje
ctio
n in
im
age
bund
leP
hoto
err
or
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 6
Depth map filtering approach
Problem:
• Uniform regions in reference image do not give discriminative enough photometric error
Idea:• Assume that depth is smooth on uniform regions
• Use total variational approach where depth map is the functional to optimize:
– photometric error defines the data term
– the smoothness constraint defines the regularization.
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 7
Depth map filtering approach
Formulation:
• First term : regularization constraint, g is defined so that it is 0 for image gradients and 1 for uniform regions. So that gradient on depth map is penalized for uniform regions
• Second term : data term defined by the photometric error.
• Huber norm: differentiable replacement to L1 norm that better preserve discontinuities compared to L2.
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 8
Total variational optimisationIm
age
den
oisi
ngL2 norm L1 norm
Reg
ular
isat
ion
eff
ect
QU(f1)=1QU(f2)=0.1QU(f3)=0.01
TV(f1)=1TV(f2)=1TV(f3)=1
[Pock08]
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 9
Depth map filtering approach
Formulation :
• Problem : optimizing this equation directly requires linearising of cost volume. Expensive and cost volume has many local minima.
Approximation :
• Introduce as an auxiliary variable, can be optimized with heuristic search
• Second terms brings original and auxiliary variable together
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 10
Total variational optimisation
Classical approaches: • Time Marching Scheme: steepest descent method
• Linearization of the Euler-Lagrange Equation
Problem: optimization badly conditioned as (uniform regions)
Reformulation of regularization with primal dual method• Dual variable p is introduced to compute the TV norm:
• Indeed:
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 11
Increasing solution accuracy ?
Reminder:
Approach: • Q well modeled, perform Newton step on Q to
update estimation a
• Equivalent to using Epsilon ?
Before
After one iteration
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 12
Dense tracking
Inputs: • 3D texture model of the scene
• Pose at previous frame
Tracking as a registration problem• First inter-frame rotation estimation : the previous image is aligned
on the current image to estimate a coarse inter-frame rotation
• Estimated pose is used to project the 3D model into 2.5D image
• The 2.5D image is registered with the current frame to find the current pose.
Two template matching problems
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 13
SSD optimisation
Problem: Align template image T(x) with input image I(x).
Hypothesis: Know a coarse approximation of the template position (p
0).
Formulation: find the transformation that best maps the pixels of
the templates into the ones of the current image minimizing:
are the displacement parameters to be optimized.
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 14
SSD optimisation
Problem: minimize
The current estimation of p is iteratively updated to reach the minimum of the function.
Formulations: • Direct additional
• Direct compositional
• Inverse
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 15
SSD optimisation
Example: Direct additive method
• Minimize :
• First order Taylor expansion:
• Solution:
with:
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 16
SSD robustified
Problem: In case of occlusion, the occluded pixels cause the optimum of the function to be changed. The occluded pixels have to be ignored from the optimization
Reminder:
Method :• Only the pixels with a difference
lower than a threshold are selected.
• Threshold is iteratively updated to get more selective as the optimization reaches the optimum.
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 17
Template matching
Applications to DTAM:• First rotation estimation:the template is the previous image that is matched with current image. Warp is defined on
the space of all rotations. The initial estimate of p is identity.
• Full pose estimationtemplate is 2.5D, warp is defined by full 3D motion estimation, that is .
The initial pose is given by the pose estimated at the previous frame and the inter frame rotation estimation.
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 18
Conclusion
• First live full dense reconstruction system...
• Limitation from the smoothness assumption on depth...
28.02.2013Amaury DameActive Vision LabOxford Robotics Research Group
Slide 19
Important references
• [Pock Thesis08] Fast total variation for Computer Vision• [Baker IJCV04] Lucas-Kanade 20 years on: A unifying framework