Download presentation
Presentation is loading. Please wait.
1
The Brightness Constraint
Brightness Constancy Equation: Linearizing (assuming small (u,v)): Where: ) , ( y x J I t - = Each pixel provides 1 equation in 2 unknowns (u,v). Insufficient info. Another constraint: Global Motion Model Constraint
2
Global Motion Models 2D Models: Affine Quadratic
Homography (Planar projective transform) 3D Models: Rotation, Translation, 1/Depth Instantaneous camera motion models Plane+Parallax
3
Example: Affine Motion
Substituting into the B.C. Equation: Each pixel provides 1 linear constraint in 6 global unknowns Least Square Minimization (over all pixels): (minimum 6 pixels necessary) Every pixel contributes Confidence-weighted regression
4
Example: Affine Motion
Differentiating w.r.t. a1 , …, a6 and equating to zero 6 linear equations in 6 unknowns:
5
Coarse-to-Fine Estimation
Parameter propagation: Pyramid of image J Pyramid of image I image I image J Jw warp refine + u=10 pixels u=5 pixels u=2.5 pixels u=1.25 pixels ==> small u and v ... image J image I
6
Other 2D Motion Models Quadratic – instantaneous approximation to planar motion Projective – exact planar motion (Homography H)
7
Panoramic Mosaic Image
Alignment accuracy (between a pair of frames): error < 0.1 pixel Original video clip Generated Mosaic image
8
Video Removal Original Original Outliers Synthesized
9
Video Enhancement ORIGINAL ENHANCED
10
Direct Methods: Methods for motion and/or shape estimation, which recover the unknown parameters directly from measurable image quantities at each pixel in the image. Minimization step: Direct methods: Error measure based on dense measurable image quantities (Confidence-weighted regression; Exploits all available information) Feature-based methods: Error measure based on distances of a sparse set of distinct feature matches.
11
Benefits of Direct Methods
High subpixel accuracy. Do not need distinct features. Locking property.
12
Limitations Limited search range (up to ~10% of the image size).
Brightness constancy assumption.
13
Video Indexing and Editing
14
Ex#4: Image Alignment (2D Translation)
Differentiating w.r.t. a1 and a2 and equating to zero 2 linear equations in 2 unknowns:
15
Camera induced motion =
The 2D/3D Dichotomy Camera motion + Scene structure Independent motions Camera induced motion = + Independent motions = Image motion = 2D techniques 3D techniques Do not model “3D scenes” Singularities in “2D scenes”
16
The Plane+Parallax Decomposition
Original Sequence Plane-Stabilized Sequence The residual parallax lies on a radial (epipolar) field: epipole
17
Benefits of the P+P Decomposition
Eliminates effects of rotation Eliminates changes in camera parameters / zoom 1. Reduces the search space: Camera parameters: Need to estimate only epipole. (gauge ambiguity: unknown scale of epipole) Image displacements: Constrained to lie on radial lines (1-D search problem) A result of aligning an existing structure in the image.
18
Benefits of the P+P Decomposition
2. Scene-Centered Representation: Translation or pure rotation ??? Focus on relevant portion of info Remove global component which dilutes information !
19
Benefits of the P+P Decomposition
2. Scene-Centered Representation: Shape = Fluctuations relative to a planar surface in the scene STAB_RUG SEQ
20
Benefits of the P+P Decomposition
2. Scene-Centered Representation: Shape = Fluctuations relative to a planar surface in the scene Height vs. Depth (e.g., obstacle avoidance) Appropriate units for shape A compact representation - fewer bits, progressive encoding total distance [ ] camera center scene global (100) component local [-3..+3] component
21
Benefits of the P+P Decomposition
3. Stratified 2D-3D Representation: Start with 2D estimation (homography). 3D info builds on top of 2D info. Avoids a-priori model selection.
22
Dense 3D Reconstruction (Plane+Parallax)
Epipolar geometry in this case reduces to estimating the epipoles. Everything else is captured by the homography. Original sequence Plane-aligned sequence Recovered shape
23
Dense 3D Reconstruction (Plane+Parallax)
Original sequence Plane-aligned sequence Recovered shape
24
Dense 3D Reconstruction (Plane+Parallax)
Original sequence Plane-aligned sequence Epipolar geometry in this case reduces to estimating the epipoles. Everything else is captured by the homography. Recovered shape
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.