Linear feature extraction by least squares template matching constrained by internal shape forces

Armin Gruen; Peggy Agouris

doi:10.1117/12.182860

17 August 1994 Linear feature extraction by least squares template matching constrained by internal shape forces

Armin Gruen, Peggy Agouris

Proceedings Volume 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision; (1994) https://doi.org/10.1117/12.182860
Event: Spatial Information from Digital Photogrammetry and Computer Vision: ISPRS Commission III Symposium, 1994, Munich, Germany

Abstract

This paper deals with monoscopic object extraction from digital imagery by least squares template matching. We present a globally enforced least squares template matching method, constrained by internal shape forces, for automatic precise geometric identification and registration of object outlines. This is a highly localized operation, and as such, it can be affected by gaps in the edge representation, occlusions, radiometric noise, and other artifacts. To bypass this problem, the method is extended to an object-wise global level by being performed simultaneously for the complete outline of a single object. The template matching least squares solutions for different edge segments along the outline of an object are tied together by using a geometric coherence condition which expresses the a priori acceptable shape behavior of this object. Finally, we discuss the use of the presented technique within a semi-automated monoplotting strategy for GIS object extraction.

Citation Download Citation

Armin Gruen and Peggy Agouris "Linear feature extraction by least squares template matching constrained by internal shape forces", Proc. SPIE 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision, (17 August 1994); https://doi.org/10.1117/12.182860

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available