lecture21 - Motion Tracking Motion tracking Suppose we have...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Motion Tracking Motion tracking Suppose we have more than two images How to track a point through all of the images? Feature Tracking Choose only the points (“features”) that are easily tracked How to find these features? – In principle, we could estimate motion between each pair of consecutive frames – Given point in first frame, follow arrows to trace out it’s path – Problem: DRIFT » small errors will tend to grow and grow over time—the point will drift way off course – windows where has two large eigenvalues Called the Harris Corner Detector
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Feature Detection Tracking features Feature tracking Compute optical flow for that feature for each consecutive H, I When will this go wrong? Occlusions—feature may disappear – need mechanism for deleting, adding new features Changes in shape, orientation – allow the feature to deform Changes in color Large motions – will pyramid techniques work for feature tracking?
Background image of page 2
3 Handling large motions L-K requires small motion
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 4
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 10

lecture21 - Motion Tracking Motion tracking Suppose we have...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online