lecture32 - CSE486 Penn State Robert Collins Lecture 32...

Info iconThis preview shows pages 1–11. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: CSE486, Penn State Robert Collins Lecture 32: Object Recognition: SIFT Keys CSE486, Penn State Robert Collins Motivation • Want to recognize a known objects from unknown viewpoints. database of models find them in an image CSE486, Penn State Robert Collins Local Feature based Approaches • Represent appearance of object by little intensity/feature patches. • Try to match patches from object to image • Geometrically consistent matches tell you the location and pose of the object CSE486, Penn State Robert Collins Simple Example • Represent object by set of 11x11 intensity templates extracted around Harris corners. harris corners our object “model” CSE486, Penn State Robert Collins Simple Example • Match patches to new image using NCC. CSE486, Penn State Robert Collins Simple Example • Find matches consistent with affine transformation using RANSAC CSE486, Penn State Robert Collins Simple Example • Inlier matches let you solve for location and pose of object in the image. CSE486, Penn State Robert Collins Problem with Simple Example Using NCC to match intensity patches puts restrictions on the amount of overall rotation and scaling allowed between the model and the image appearance. model template matches well no match no match ncc ncc ncc CSE486, Penn State Robert Collins More General : SIFT Keys David G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, 60, 2 (2004), pp. 91-110. CSE486, Penn State Robert Collins SIFT Keys: General Idea • Reliably extract same image points regardless of new magnification and rotation of the image....
View Full Document

{[ snackBarMessage ]}

Page1 / 40

lecture32 - CSE486 Penn State Robert Collins Lecture 32...

This preview shows document pages 1 - 11. Sign up to view the full document.

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