Change search
ReferencesLink to record
Permanent link

Direct link
Feature tracking with automatic selection of spatial scales
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.ORCID iD: 0000-0002-9081-2170
1998 (English)Report (Other academic)
Abstract [en]

When observing a dynamic world, the size of image structures may vary over nada. This article emphasizes the need for including explicit mechanisms for automatic scale selection in feature tracking algorithms in order to: (i) adapt the local scale of processing to the local image structure, and (ii) adapt to the size variations that may occur over time.

The problems of corner detection and blob detection are treated in detail, and a combined framework for feature tracking is presented in which the image features at every time moment are detected at locally determined and automatically selected nadaes. A useful property of the scale selection method is that the scale levels selected in the feature detection step reflect the spatial extent of the image structures. Thereby, the integrated tracking algorithm has the ability to adapt to spatial as well as temporal size variations, and can in this way overcome some of the inherent limitations of exposing fixed-scale tracking methods to image sequences in which the size variations are large.

In the composed tracking procedure, the scale information is used for two additional major purposes: (i) for defining local regions of interest for searching for matching candidates as well as setting the window size for correlation when evaluating matching candidates, and (ii) stability over time of the scale and significance descriptors produced by the scale selection procedure are used for formulating a multi-cue similarity measure for matching.

Experiments on real-world sequences are presented showing the performance of the algorithm when applied to (individual) tracking of corners and blobs. Specifically, comparisons with fixed-scale tracking methods are included as well as illustrations of the increase in performance obtained by using multiple cues in the feature matching step.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 1998. Vol. 71, 40 p.385-392 p.
, Trita-NA. P, 96:21
Keyword [en]
feature, tracking, motion, blob, corner, scale, scale-space, scale selection, similarity, multi-scale representation, computer vision
National Category
Computer Vision and Robotics (Autonomous Systems) Computer Science
URN: urn:nbn:se:kth:diva-40148OAI: diva2:466293
QC 20111215Available from: 2011-12-15 Created: 2011-09-13 Last updated: 2011-12-15Bibliographically approved

Open Access in DiVA

fulltext(575 kB)190 downloads
File information
File name FULLTEXT01.pdfFile size 575 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Search in DiVA

By author/editor
Bretzner, LarsLindeberg, Tony
By organisation
Numerical Analysis and Computer Science, NADA
Computer Vision and Robotics (Autonomous Systems)Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 190 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 139 hits
ReferencesLink to record
Permanent link

Direct link