Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Scale-space with causal time direction
KTH, Skolan för datavetenskap och kommunikation (CSC), Beräkningsbiologi, CB.ORCID-id: 0000-0002-9081-2170
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
1996 (Engelska)Ingår i: : ECCV'96 (Cambridge, U.K.) published in Springer Lecture Notes in Computer Science, vol 1064, Berlin / Heidelberg: Springer , 1996, Vol. 1064, s. 229-240Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This article presents a theory for multi-scale representation of temporal data. Assuming that a real-time vision system should represent the incoming data at different time scales, an additional causality constraint arises compared to traditional scale-space theory—we can only use what has occurred in the past for computing representations at coarser time scales. Based on a previously developed scale-space theory in terms of noncreation of local maxima with increasing scale, a complete classification is given of the scale-space kernels that satisfy this property of non-creation of structure and respect the time direction as causal. It is shown that the cases of continuous and discrete time are inherently different.

Ort, förlag, år, upplaga, sidor
Berlin / Heidelberg: Springer , 1996. Vol. 1064, s. 229-240
Serie
Lecture Notes in Computer Science ; 1064
Nyckelord [en]
scale-space, time, scale, motion, causality, Poisson kernel, Gaussian kernel, smoothing, visual front-end, multi-scale representation, computer vision, signal processing
Nationell ämneskategori
Data- och informationsvetenskap Datorseende och robotik (autonoma system) Signalbehandling
Identifikatorer
URN: urn:nbn:se:kth:diva-33682DOI: 10.1007/BFb0015539OAI: oai:DiVA.org:kth-33682DiVA, id: diva2:417090
Konferens
4th European Conference on Computer Vision, (Cambridge, England), April 14-18, 1996
Anmärkning

QC 20130405

Tillgänglig från: 2013-04-05 Skapad: 2011-05-15 Senast uppdaterad: 2018-01-12Bibliografiskt granskad
Ingår i avhandling
1. Spatio-Temporal Scale-Space Theory
Öppna denna publikation i ny flik eller fönster >>Spatio-Temporal Scale-Space Theory
2011 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

This thesis addresses two important topics in developing a systematic space-time geometric approach to real-time, low-level motion vision. The first one concerns measuring of image flow, while the second one focuses on how to find low level features.

We argue for studying motion vision in terms of space-time geometry rather than in terms of two (or a few) consecutive image frames. The use of Galilean Geometry and Galilean similarity geometry for this  purpose is motivated and relevant geometrical background is reviewed.

In order to measure the visual signal in a way that respects the geometry of the situation and the causal nature of time, we argue that a time causal Galilean spatio-temporal scale-space is needed. The scale-space axioms are chosen so that they generalize popular axiomatizations of spatial scale-space to spatio-temporal  geometries.

To be able to derive the scale-space, an infinitesimal framework for scale-spaces that respects a more general class of Lie groups (compared to previous theory) is developed and applied.

Perhaps surprisingly, we find that with the chosen axiomatization, a time causal Galilean scale-space is not possible as an evolution process on space and time. However, it is possible on space and memory. We argue that this actually is a more accurate and realistic model of motion vision.

While the derivation of the time causal Galilean spatio-temporal scale-spaces requires some exotic mathematics, the end result is as simple as one possibly could hope for and a natural extension of  spatial scale-spaces. The unique infinitesimally generated scale-space is an ordinary diffusion equation with drift on memory and a diffusion equation on space. The drift is used for velocity  adaption, the "velocity adaption" part of Galilean geometry (the Galilean boost) and the temporal scale-space acts as memory.

Lifting the restriction of infinitesimally generated scale spaces, we arrive at a new family of scale-spaces. These are generated by a family of fractional differential evolution equations that generalize the ordinary diffusion equation. The same type of evolution equations have recently become popular in research in e.g. financial and physical modeling.

The second major topic in this thesis is extraction of features from an image flow. A set of low-level features can be derived by classifying basic Galilean differential invariants. We proceed to derive invariants for two main cases: when the spatio-temporal  gradient cuts the image plane and when it is tangent to the image plane. The former case corresponds to isophote curve motion and the later to creation and disappearance of image structure, a case that is not well captured by the theory of optical flow.

The Galilean differential invariants that are derived are equivalent with curl, divergence, deformation and acceleration. These  invariants are normally calculated in terms of optical flow, but here they are instead calculated directly from the the  spatio-temporal image.

Ort, förlag, år, upplaga, sidor
Stockholm: KTH Royal Institute of Technology, 2011. s. viii, 86
Serie
Trita-CSC-A, ISSN 1653-5723 ; 2011:11
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Identifikatorer
urn:nbn:se:kth:diva-33686 (URN)978-91-7501-024-3 (ISBN)
Disputation
2011-06-10, sal D3, Lindstedtsvägen 5, KTH, Stockholm, 10:00 (Engelska)
Opponent
Handledare
Anmärkning
QC 20110518Tillgänglig från: 2011-05-18 Skapad: 2011-05-15 Senast uppdaterad: 2018-01-12Bibliografiskt granskad

Open Access i DiVA

fulltext(242 kB)293 nedladdningar
Filinformation
Filnamn FULLTEXT02.pdfFilstorlek 242 kBChecksumma SHA-512
5a899a4b7feec96402fa91ec708a31a8605936b442a3112ba98191e1f80c0ee4a2f63e751989be0280584e3da4a3bb23b001a2c7b7c9ae3c80db649499f4c8af
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextAt authors' home page

Personposter BETA

Lindeberg, Tony

Sök vidare i DiVA

Av författaren/redaktören
Lindeberg, TonyFagerström, Daniel
Av organisationen
Beräkningsbiologi, CBDatorseende och robotik, CVAP
Data- och informationsvetenskapDatorseende och robotik (autonoma system)Signalbehandling

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 293 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 302 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf