Return to search

Robust and Efficient 3D Recognition by Alignment

Alignment is a prevalent approach for recognizing 3D objects in 2D images. A major problem with current implementations is how to robustly handle errors that propagate from uncertainties in the locations of image features. This thesis gives a technique for bounding these errors. The technique makes use of a new solution to the problem of recovering 3D pose from three matching point pairs under weak-perspective projection. Furthermore, the error bounds are used to demonstrate that using line segments for features instead of points significantly reduces the false positive rate, to the extent that alignment can remain reliable even in cluttered scenes.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6799
Date01 September 1992
CreatorsAlter, Tao Daniel
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format113 p., 903052 bytes, 1830006 bytes, application/octet-stream, application/pdf
RelationAITR-1410

Page generated in 0.0017 seconds