PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
January 1, 2000448 citations

Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions

View Full Paper
TTTinne TuytelaarsLGLuc Van Gool

Key Points

  • To extract affinely invariant local image regions based purely on intensity for reliable wide baseline stereo matching across viewpoint and illumination changes.
  • Extracted local affinely invariant image patches using an intensity-based formulation independent of corner or edge detectors.
  • Integrated distinct invariant region extraction algorithms into an opportunistic matching system across wide baseline stereo images.
  • Generated stable feature correspondences across wide baseline views and fluctuating illumination without reliance on edge or corner features.
  • Increased matching robustness and coverage across diverse image conditions by combining multiple complementary invariant region types.

Abstract

`Invariant regions are image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions are then described by a set of invariant features, which makes it relatively easy to match them between views and under changing illumination. In previous work, we have presented invariant regions that are based on a combination of corners and edges. The application discussed then was image database retrieval. Here, an alternative method for extracting (affinely) invariant regions is given, that does not depend on the presence of edges or corners in the image but is purely intensity-based. Also, we demonstrate the use of such regions for another application, which is wide baseline stereo matching. As a matter of fact, the goal is to build an opportunistic system that exploits several types of invariant regions as it sees fit. This yields more correspondences and a system that can deal with a wider range of images. To increase t...

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Tuytelaars et al. (2000) studied this question.

synapsesocial.com/papers/6a0f3b49a00258d2006cb4c4https://doi.org/10.5244/c.14.38
Ask AI
Helpful
Bookmark
Share
View Full Paper