#? rahul swaminathan (T-Labs) & professor patrick baudisch hci2 hasso-plattner institute determining depth
two subproblems Matching Finding corresponding elements in the two images Reconstruction Establishing 3-D coordinates from the 2-D image correspondences found during matching
a little recap on reconstruction
camera scene lighting graphics light computer
camera scene lighting vision light
computer camera scene lighting light
scene the camera sees a red pixel let’s assume it correctly classifies it as “glass of red wine” screen but, the red wine could be anywhere along this line
computer two cameras scene lighting light
triangulate the location of the actual glass
wine glass screens
two subproblems Matching Finding corresponding elements in the two images Reconstruction: done Establishing 3-D coordinates from the 2-D image correspondences found during matching
two subproblems Matching: harder Finding corresponding elements in the two images Reconstruction: done Establishing 3-D coordinates from the 2-D image correspondences found during matching
matching structured light
scene Could we replace one camera with a projector? two cameras lighting
structured light :: the process of projecting a known pattern of pixels onto a scene
pattern is disturbed when depth changes
patterns used
gray code 1
Could we achieve the same result with less images?
use (cos)-wave pattern instead of b/w 2
pattern needs processing caveat
Turns out to be a not too hard problem: flood-fill algorithm already provides acceptable solution
continues gradient result from both
Microsoft Kinect 3
Anoto pen 4
matching two cameras
computer two cameras scene lighting light
main approaches 1.pixel/area-based 2.feature-based
problems Camera-related problems - Image noise, differing gain, contrast, etc.. Viewpoint-related problems: - Perspective distortions - Occlusions - Specular reflections
camera positioning baseline
More matching heuristics Always valid: (Epipolar line) Uniqueness Minimum/maximum disparity 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
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
Area-based matching Similarity measures for two windows SAD (sum of absolute differences) SSD (sum of squared differences) CC (cross-correlation) …
Correspondence via Correlation Rectified images LeftRight scanline SSD error disparity (Same as max-correlation / max-cosine for normalized image patch)
LeftDisparity Map Images courtesy of Point Grey Research Correspondence Using Correlation
Image Normalization Even when the cameras are identical models, there can be differences in gain and sensitivity. The cameras do not see exactly the same surfaces, so their overall light levels can differ. For these reasons and more, it is a good idea to normalize the pixels in each window:
matching features
problems
Scale change Rotation Occlusion Illumination ……
SIFT :: Scale Invariant Feature Transform; transform image data into scale-invariant coordinates relative to local features
result
combining both
2 angles and one side are known height of the triangle can be computed
wine glass screens
the underlying problem is: compute the intersection of two lines
commonly compute “depth” image
problems
oclusion
end
#11 professor patrick baudisch hci hasso-plattner institute title
:: interactive of the day
#11 professor patrick baudisch hci hasso-plattner institute title
main text is 28 pt Arial, dark gray with highlighted text is good green, and bad orange both in bold face. Include commas etc. in highlighting
36pt text overlay text on 40% black 1 label
1.benefit 1 2.benefit 2 benefits:
:: <text to define it including highlighted text only black text in deck
by Saturday upload storyboards for four tasks to the wiki assignment
E title 2x1min (this is an in-class exercise) in teams of : 1.step 1 2.step 2 Go!