0% found this document useful (0 votes)
296 views27 pages

Computer Vision and Image Processing - Fundamentals and Applications

Stereo vision uses images from two or more viewpoints to analyze a 3D scene. The two main subproblems are matching and reconstruction. Matching, which is the most difficult part, involves finding correspondences between points or features in the images. There are two main approaches to matching: area-based methods provide dense reconstruction by matching pixels between windows, while feature-based methods provide sparser reconstruction by matching edges, lines or corners. Reconstruction uses the matches to infer 3D information about the scene.

Uploaded by

Dikshant Buwa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
296 views27 pages

Computer Vision and Image Processing - Fundamentals and Applications

Stereo vision uses images from two or more viewpoints to analyze a 3D scene. The two main subproblems are matching and reconstruction. Matching, which is the most difficult part, involves finding correspondences between points or features in the images. There are two main approaches to matching: area-based methods provide dense reconstruction by matching pixels between windows, while feature-based methods provide sparser reconstruction by matching edges, lines or corners. Reconstruction uses the matches to infer 3D information about the scene.

Uploaded by

Dikshant Buwa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 27

Computer Vision and Image Processing

– Fundamentals and Applications

Image Formation in a Stereo Vision Setup

n
ya
hu
.B
.K
M
Course Instructor: Dr. M.K. Bhuyan
Professor

Department of Electronics and Electrical Engineering,


Indian Institute of Technology Guwahati, India.
Goal: disparity map
• Disparity:
• The horizontal displacement between corresponding
points
• Closely related to scene depth

n
ya
hu
.B
.K
M
The matching problem
• Which image entities should be matched?
• Two main approaches
• Pixel/area-based (lower-level)
• Feature-based (higher-level)

n
ya
hu
.B
.K
M
Matching challenges
• Scene elements do not always look the same in the two images
• Camera-related problems
• Image noise, differing gain, contrast, etc..
• Viewpoint-related problems:

n
ya
hu
• Perspective distortions

.B
.K
M
• Occlusions
• Specular reflections
More matching heuristics
• Always valid:
• (Epipolar line)
• Uniqueness
• Minimum/maximum disparity

n
ya
hu
.B
.K
M
• Sometimes valid:
• Ordering
• Local continuity (smoothness)
Area-based matching
• Finding pixel-to-pixel correspondences
• For each pixel in the left image, search for the most similar pixel in the right
image
• Using neighbourhood windows

n
ya
hu
.B
.K
M
Intensity-based Methods
• Match image sub-windows between the two images
(e.g., using correlation).
left right

n
ya
hu
.B
.K
M
• How to choose the window size W?
– Too small a window may not capture enough image structure, and may
be too noise sensitive (i.e., less distinctive, many false matches).
– Too large a window makes matching less sensitive to noise (desired)
but also harder to match
Area-based matching
• Similarity measures for two windows
• SAD (sum of absolute differences)
• SSD (sum of squared differences)
• CC (cross-correlation)

n
ya
hu
.B
• …

.K
M
M
.K
.B
hu
ya
n
Feature-based matching
• Matching features:
• Edge points
• lines
• corners

n
ya
hu
.B
• …

.K
M
• Sparse reconstruction sets
• Best if scene type is known a priori
M
.K
.B
hu
ya
n
Intensity-based vs feature-based approaches

• Intensity-based methods
– Provide a dense disparity map.
– Need textured images to work well.
– Sensitive to illumination changes.

n
ya
hu
.B
.K
M
• Feature-based methods:
– Faster than correlation-based methods.
– Provide sparse disparity maps.
– Relatively insensitive to illumination changes.
Three or more viewpoints
• More matching information
• Additional epipolar constraints
• More confident matches

n
ya
hu
.B
.K
M
M
.K
.B
hu
ya
n
Summary
Summary
• Stereo vision:
• A method for 3-D analysis of a scene using images from two or more
viewpoints
• Two subproblems:

n
ya
hu
.B
• Matching

.K
M
• Reconstruction
• Most difficult part: Matching
• Two main approaches:
• Area based: Dense reconstruction
• Feature based: Sparse reconstruction
Image Reconstruction from a Series of

n
ya
hu
Projections

.B
.K
M
M
.K
.B
hu
ya
n
M
.K
.B
hu
ya
n
M
.K
.B
hu
ya
n
Radon Transform

n
ya
hu
.B
.K
M
⚫ A linear transform
f(x,y) → g(s,)
– Line integral or “ray-sum”
– Along a line inclined at angle 
from y-axis and s away from origin

⚫ Fix  to get a 1-D signal g(s)


M
.K
.B
hu
ya
n
M
.K
.B
hu
ya
n
M
.K
.B
hu
ya
n
Representation in Polar Coordinates

n
ya
hu
.B
.K
M
Example of Radon Transform

n
ya
hu
.B
.K
M
Full circle in RT

n
ya
hu
.B
.K
M
Thin stick in RT

n
ya
hu
.B
.K
M

You might also like