research-article

Feature Tracking with Automatic Selection of Spatial Scales

Authors:

Tony LindebergAuthors Info & Claims

Computer Vision and Image Understanding, Volume 71, Issue 3

Pages 385 - 392

https://doi.org/10.1006/cviu.1998.0650

Published: 01 September 1998 Publication History

Abstract

When observing a dynamic world, the size of image structures may vary over time. 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. The integrated tracking algorithm overcomes some of the inherent limitations of exposing fixed-scale tracking methods to image sequences in which the size variations are large. It is also shown how the stability over time of scale descriptors can be used as a part of 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.

References

[1]

L.S. Shapiro, H. Wang, J.M. Brady, A matching and tracking strategy for independently moving objects, Proc. British Machine Vision Conference (1992) 306-315.

[2]

S.M. Smith, J.M. Brady, Asset-2: Real-time motion segmentation and shape tracking, IEEE Trans. Pattern Anal. Mach. Intell., 17 (1995) 814-820.

Digital Library

[3]

Q. Zheng, R. Chellappa, Automatic feature point extraction and tracking in image sequences for arbitrary camera motion, Int. J. Comput. Vision, 15 (1995) 31-76.

Digital Library

[4]

J.J. Koenderink, A.J. van Doorn, Generic neighborhood operators, IEEE Trans. Pattern Anal. Mach. Intell., 14 (1992) 597-605.

Digital Library

[5]

L.M.J. Florack, B.M.ter Haar Romeny, J.J. Koenderink, M.A. Viergever, Scale and the differential structure of images, Image Vision Comput., 10 (1992) 376-388.

Digital Library

[6]

T. Lindeberg, The Kluwer International Series in Engineering and Computer Science, Scale-Space Theory in Computer Vision (1994).

[7]

T. Lindeberg, On scale selection for differential operators, Proc. 8th Scandinavian Conf. on Image Analysis (1993) 857-866.

[8]

A. P. Witkin, Scale-space filtering, Proc. 8th Int. Joint Conf. Art. Intell, Karlsruhe, West Germany, August 1983, 1019, 1022

[9]

J.J. Koenderink, The structure of images, Biological Cybernetics, 50 (1984) 363-370.

[10]

T. Lindeberg, Edge detection and ridge detection with automatic scale selection, Proc. IEEE Comp. Soc. Conf. on Computer Vision and Pattern Recognition, San Francisco, 1996 (1996) 465-470.

Digital Library

[11]

L. Kitchen, A. Rosenfeld, Gray-level corner detection, Pattern Recog. Lett., 1 (1982) 95-102.

Digital Library

[12]

J.J. Koenderink, W. Richards, Two-dimensional curvature operators, J. Opt. Soc. Am., 5 (1988) 1136-1141.

[13]

R. Deriche, G. Giraudon, Accurate corner detection: An analytical study, Proc. 3rd Int. Conf. on Computer Vision, Osaka, Japan, 1990, 66, 70

[14]

J. Blom, Topological and Geometrical Aspects of Image Structure (1992).

[15]

T. Lindeberg, Junction detection with automatic selection of detection scales and localization scales, Proc. 1st International Conference on Image Processing, Austin, Texas, I (1994) 924-928.

[16]

M. A. Förstner, E. Gülch, A fast operator for detection and precise location of distinct points, corners and centers of circular features, Proc. Intercommission Workshop of the Int. Soc. for Photogrammetry and Remote Sensing, Interlaken, Switzerland, 1987.

[17]

L. Bretzner, T. Lindeberg, Feature tracking with automatic selection of spatial scales, Dept. of Numerical Analysis and Computing Science, KTH, Stockholm, Sweden, June 1996

[18]

T. Lindeberg, Scale selection for differential operators, Int. J. Computer Vision (1994).

Cited By

Jansson YLindeberg T(2022)Scale-Invariant Scale-Channel Networks: Deep Networks That Generalise to Previously Unseen ScalesJournal of Mathematical Imaging and Vision10.1007/s10851-022-01082-264:5(506-536)Online publication date: 1-Jun-2022
https://dl.acm.org/doi/10.1007/s10851-022-01082-2
Lindeberg T(2022)Scale-Covariant and Scale-Invariant Gaussian Derivative NetworksJournal of Mathematical Imaging and Vision10.1007/s10851-021-01057-964:3(223-242)Online publication date: 1-Mar-2022
https://dl.acm.org/doi/10.1007/s10851-021-01057-9
Lindeberg T(2020)Provably Scale-Covariant Continuous Hierarchical Networks Based on Scale-Normalized Differential Expressions Coupled in CascadeJournal of Mathematical Imaging and Vision10.1007/s10851-019-00915-x62:1(120-148)Online publication date: 1-Jan-2020
https://dl.acm.org/doi/10.1007/s10851-019-00915-x
Show More Cited By

Index Terms

Feature Tracking with Automatic Selection of Spatial Scales
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Tracking
      2. Computer vision tasks
        Scene understanding
  2. Machine learning
    1. Machine learning algorithms
      1. Feature selection

Recommendations

Indoor feature tracking
Lens Model Selection for a Markerless AR Tracking System
ISMAR '05: Proceedings of the 4th IEEE/ACM International Symposium on Mixed and Augmented Reality

This paper describes a visual markerless real-time tracking system for Augmented Reality applications. The system uses a firewire camera with a fisheye lens mounted at 10 fps. Visual tracking of 3D scene points is performed simultaneously with 3D camera ...
Lens model selection for visual tracking
PR'05: Proceedings of the 27th DAGM conference on Pattern Recognition

A standard approach to generate a camera pose from images of a single moving camera is Structure From Motion (SfM). When aiming on a practical implementation of SfM often a camera is needed that is lightweight and small. This work analyses which is the ...

Comments

Information & Contributors

Information

Published In

cover image Computer Vision and Image Understanding

Computer Vision and Image Understanding Volume 71, Issue 3

Sept. 1998

195 pages

ISSN:1077-3142

Editor:
Avinash C. Kak
Purdue Univ., West Lafayette, Inidiana

Issue’s Table of Contents

Copyright © Academic Press.

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 September 1998

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

22
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 10 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Jansson YLindeberg T(2022)Scale-Invariant Scale-Channel Networks: Deep Networks That Generalise to Previously Unseen ScalesJournal of Mathematical Imaging and Vision10.1007/s10851-022-01082-264:5(506-536)Online publication date: 1-Jun-2022
https://dl.acm.org/doi/10.1007/s10851-022-01082-2
Lindeberg T(2022)Scale-Covariant and Scale-Invariant Gaussian Derivative NetworksJournal of Mathematical Imaging and Vision10.1007/s10851-021-01057-964:3(223-242)Online publication date: 1-Mar-2022
https://dl.acm.org/doi/10.1007/s10851-021-01057-9
Lindeberg T(2020)Provably Scale-Covariant Continuous Hierarchical Networks Based on Scale-Normalized Differential Expressions Coupled in CascadeJournal of Mathematical Imaging and Vision10.1007/s10851-019-00915-x62:1(120-148)Online publication date: 1-Jan-2020
https://dl.acm.org/doi/10.1007/s10851-019-00915-x
Lindeberg T(2017)Temporal Scale Selection in Time-Causal Scale SpaceJournal of Mathematical Imaging and Vision10.1007/s10851-016-0691-358:1(57-101)Online publication date: 1-May-2017
https://dl.acm.org/doi/10.1007/s10851-016-0691-3
Zhang WShui P(2015)Contour-based corner detection via angle difference of principal directions of anisotropic Gaussian directional derivativesPattern Recognition10.1016/j.patcog.2015.03.02148:9(2785-2797)Online publication date: 1-Sep-2015
https://dl.acm.org/doi/10.1016/j.patcog.2015.03.021
Lindeberg T(2015)Image Matching Using Generalized Scale-Space Interest PointsJournal of Mathematical Imaging and Vision10.1007/s10851-014-0541-052:1(3-36)Online publication date: 1-May-2015
https://dl.acm.org/doi/10.1007/s10851-014-0541-0
Lindeberg T(2013)Scale Selection Properties of Generalized Scale-Space Interest Point DetectorsJournal of Mathematical Imaging and Vision10.1007/s10851-012-0378-346:2(177-210)Online publication date: 1-Jun-2013
https://dl.acm.org/doi/10.1007/s10851-012-0378-3
Khan ZGu I(2010)Joint feature correspondences and appearance similarity for robust visual object trackingIEEE Transactions on Information Forensics and Security10.1109/TIFS.2010.20503125:3(591-606)Online publication date: 1-Sep-2010
https://dl.acm.org/doi/10.1109/TIFS.2010.2050312
Khan ZGu IBackhouse A(2009)Joint particle filters and multi-mode anisotropic mean shift for robust tracking of video objects with partitioned areasProceedings of the 16th IEEE international conference on Image processing10.5555/1819298.1819849(4025-4028)Online publication date: 7-Nov-2009
https://dl.acm.org/doi/10.5555/1819298.1819849
Khan ZGu IWang TBackhouse A(2009)Joint anisotropic mean shift and consensus point feature correspondences for object tracking in videoProceedings of the 2009 IEEE international conference on Multimedia and Expo10.5555/1698924.1699237(1270-1273)Online publication date: 28-Jun-2009
https://dl.acm.org/doi/10.5555/1698924.1699237
Show More Cited By

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents