epipolar lines

30
Epipolar lines epipolar lines epipolar lines Baseline O O’ epipolar plane =0

Upload: ponce

Post on 22-Feb-2016

23 views

Category:

Documents


0 download

DESCRIPTION

Epipolar lines. epipolar plane. epipolar lines. epipolar lines. Baseline. O’. O. Rectification. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Epipolar  lines

Epipolar lines

epipolar linesepipolar lines

BaselineO O’

epipolar plane

𝑝 ′𝑇 𝐸𝑝=0

Page 2: Epipolar  lines

Rectification

• Rectification: rotation and scaling of each camera’s coordinate frame to make the epipolar lines horizontal and equi-height,by bringing the two image planes to be parallel to the baseline

• Rectification is achieved by applying homography to each of the two images

Page 3: Epipolar  lines

Rectification

BaselineO O’

𝑞 ′𝑇𝐻 𝑙−𝑇 𝐸𝐻𝑟

−1𝑞=0

𝐻 𝑙 𝐻𝑟

Page 4: Epipolar  lines

Cyclopean coordinates• In a rectified stereo rig with baseline of length ,

we place the origin at the midpoint between the camera centers.

• a point is projected to:– Left image: , – Right image: ,

• Cyclopean coordinates:

Page 5: Epipolar  lines

Disparity

• Disparity is inverse proportional to depth• Constant disparity constant depth• Larger baseline, more stable reconstruction of depth

(but more occlusions, correspondence is harder)

(Note that disparity is defined in a rectified rig in a cyclopean coordinate frame)

Page 6: Epipolar  lines

Random dot stereogram

• Depth can be perceived from a random dot pair of images (Julesz)

• Stereo perception is based solely on local information (low level)

Page 7: Epipolar  lines

Moving random dots

Page 8: Epipolar  lines

Compared elements

• Pixel intensities• Pixel color• Small window (e.g. or ), often using

normalized correlation to offset gain• Features and edges (less common)• Mini segments

Page 9: Epipolar  lines

Dynamic programming

• Each pair of epipolar lines is compared independently

• Local cost, sum of unary term and binary term– Unary term: cost of a single match– Binary term: cost of change of disparity (occlusion)

• Analogous to string matching (‘diff’ in Unix)

Page 10: Epipolar  lines

String matching• Swing → String

S t r i n g

S w i n g

Start

End

Page 11: Epipolar  lines

String matching• Cost: #substitutions + #insertions + #deletions

S t r i n g

S w i n g

Page 12: Epipolar  lines
Page 13: Epipolar  lines

Dynamic Programming

• Shortest path in a grid• Diagonals: constant disparity• Moving along the diagonal – pay unary cost

(cost of pixel match)• Move sideways – pay binary cost, i.e. disparity

change (occlusion, right or left)• Cost prefers fronto-parallel planes. Penalty is

paid for tilted planes

Page 14: Epipolar  lines

Dynamic Programming

Start

, Complexity?

Page 15: Epipolar  lines

Probability interpretation: Viterbi algorithm

• Markov chain

• States: discrete set of disparity

• Log probabilities: product sum• Maximum likelihood: minimize sum of negative

logs• Viterbi algorithm: equivalent to shortest path

Page 16: Epipolar  lines

Markov Random Field

• Graph • In our case: graph is

a 4-connected grid

• Minimize energy of the form

• Interpreted as negative log probabilities

Page 17: Epipolar  lines

Iterated Conditional Modes (ICM)

• Initialize states (= disparities) for every pixel• Update repeatedly each pixel by the most likely

disparity given the values assigned to its neighbors:

• Markov blanket: the state of a pixel only depends on the states of its immediate neighbors

• Similar to Gauss-Seidel iterations• Slow convergence to bad local minimum

Page 18: Epipolar  lines

Graph cuts: expansion moves

• Assume is non-negative and is metric:

• We can apply more semi-global moves using minimal s-t cuts

• Converges faster to a better (local) minimum

Page 19: Epipolar  lines

α-Expansion

• Expansion move allows in one shot each pixel to either change its state to α or to maintain its current state

• We apply expansion moves for all possible disparity values and repeat this to convergence

• At convergence energy is within a scale factor from the global optimum:

where

Page 20: Epipolar  lines

α-Expansion (1D example)

Page 21: Epipolar  lines

α-Expansion (1D example)

𝛼

𝛼  

Page 22: Epipolar  lines

α-Expansion (1D example)

𝛼

𝛼  

Page 23: Epipolar  lines

α-Expansion (1D example)

𝐷𝑝(𝛼) 𝐷𝑞 (𝛼)

𝛼

𝛼  

𝑉 𝑝𝑞 (𝛼 ,𝛼 )=0

Page 24: Epipolar  lines

α-Expansion (1D example)

𝛼

𝛼  𝐷𝑝(𝑑𝑝) 𝐷𝑞 (𝑑𝑞)

But what about?

Page 25: Epipolar  lines

α-Expansion (1D example)

𝛼

𝛼  𝐷𝑝(𝑑𝑝) 𝐷𝑞 (𝑑𝑞)

𝑉 𝑝𝑞(𝑑𝑝 ,𝑑𝑞)

Page 26: Epipolar  lines

α-Expansion (1D example)

𝛼

𝛼  𝐷𝑝(𝑑𝑝)

𝑉 𝑝𝑞(𝑑𝑝 ,𝛼)𝐷𝑞 (𝛼)

Page 27: Epipolar  lines

α-Expansion (1D example)

𝛼

𝛼  𝐷𝑞 (𝑑𝑞)

𝑉 𝑝𝑞(𝛼 ,𝑑𝑞)𝐷𝑝(𝛼)

Page 28: Epipolar  lines

α-Expansion (1D example)

𝛼

𝛼  

𝑉 𝑝𝑞(𝛼 ,𝑑𝑞)𝑉 𝑝𝑞(𝑑𝑝 ,𝛼)

𝑉 𝑝𝑞(𝑑𝑝 ,𝑑𝑞)

Such a cut cannot be obtained due to triangle inequality:

Page 29: Epipolar  lines

Common Metrics

• Potts model:

• Truncated :

• Truncated squared difference is not a metric

Page 30: Epipolar  lines

Reconstruction with graph-cuts

Original Result Ground truth