Extending Distance Computation - Propagating Derivatives
2010 (English)In: Proceedings SSBA 2010 / [ed] Cris Luengo and Milan Gavrilovic, Uppsala: Centre for Image Analysis , 2010, 39-42 p.Conference paper (Other academic)
In this paper we present a technique to extend distance computation algorithms that compute global distances from a series of local updates. This includes algorithms such as the fast marching method (FMM) and the chamfering algorithm for weighted distances. In addition to the value of a distance function or distance map, we derive formulas to compute the gradient and higher order partial derivatives of the distance function within the same framework. The approach is based on symbolic differentiation of the update scheme, which makes it general and straight forward to apply to almost any distance computation scheme. The main result is a novel set of ``derivative maps'' that are computed along with the ordinary distance maps. Apart from the theory itself, these maps and this technique may be used to compute skeletons and parameterizations such as Riemannian Normal Coordinates and Gauss Normal Coordinates.
Place, publisher, year, edition, pages
Uppsala: Centre for Image Analysis , 2010. 39-42 p.
, Centre for Image Analysis Report Series, ISSN 1100-6641 ; 34
Computer Vision and Robotics (Autonomous Systems)
Research subject Computerized Image Analysis
IdentifiersURN: urn:nbn:se:uu:diva-142812OAI: oai:DiVA.org:uu-142812DiVA: diva2:388277
Symposium on Image Analysis