A Wavelet-based Approach to Image Feature Stability Assessment

Antonio Robles-Kelly, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

3 Citations (Scopus)

Abstract

In this paper, we present a novel method for assessing image-feature stability. The method hinges on applying the discrete wavelet transform to the image features under study throughout a number of video frames in an image sequence. For purposes of stability assessment, we recover the imagefeature vectors for each video frame and then track them trough a series of consecutive frames in the image sequence. We apply the discrete wavelet transform to the time series constructed from the pairwise Euclidean distances for each of the image features under study and use the wavelet transform coefficients to assess their stability. We then recover the stable features by clustering together those time series which exhibit largely constant low-pass wavelet coefficients. We present results of the stability analysis for Harris corners, Maximally Stable Extremal Regions, and Scale Invariant Feature Transform regions extracted from two real-world video sequences. We also elaborate on the applications of our method to indexing, retrieval, and compression of stable image feature vectors
Original languageEnglish
Title of host publication2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06)
Subtitle of host publicationBeyond patches workshop
EditorsRiad I Hammoud, James W Davis
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-8
Number of pages8
ISBN (Print)9780769525976
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event2006 Conference on Computer Vision and Pattern Recognition Workshop, CVPRW'06 - New York City, New York, United States
Duration: 17 Jun 200622 Jun 2006

Workshop

Workshop2006 Conference on Computer Vision and Pattern Recognition Workshop, CVPRW'06
Abbreviated titleCVPRW
CountryUnited States
CityNew York
Period17/06/0622/06/06

Fingerprint

Discrete wavelet transforms
Time series
Hinges
Wavelet transforms
Mathematical transformations

Cite this

Robles-Kelly, A., & Goecke, R. (2006). A Wavelet-based Approach to Image Feature Stability Assessment. In R. I. Hammoud, & J. W. Davis (Eds.), 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06): Beyond patches workshop (pp. 1-8). United States: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CVPRW.2006.22
Robles-Kelly, Antonio ; Goecke, Roland. / A Wavelet-based Approach to Image Feature Stability Assessment. 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06): Beyond patches workshop. editor / Riad I Hammoud ; James W Davis. United States : IEEE, Institute of Electrical and Electronics Engineers, 2006. pp. 1-8
@inproceedings{5e64eb31af0b4e259dfc33ea33ed6ff5,
title = "A Wavelet-based Approach to Image Feature Stability Assessment",
abstract = "In this paper, we present a novel method for assessing image-feature stability. The method hinges on applying the discrete wavelet transform to the image features under study throughout a number of video frames in an image sequence. For purposes of stability assessment, we recover the imagefeature vectors for each video frame and then track them trough a series of consecutive frames in the image sequence. We apply the discrete wavelet transform to the time series constructed from the pairwise Euclidean distances for each of the image features under study and use the wavelet transform coefficients to assess their stability. We then recover the stable features by clustering together those time series which exhibit largely constant low-pass wavelet coefficients. We present results of the stability analysis for Harris corners, Maximally Stable Extremal Regions, and Scale Invariant Feature Transform regions extracted from two real-world video sequences. We also elaborate on the applications of our method to indexing, retrieval, and compression of stable image feature vectors",
author = "Antonio Robles-Kelly and Roland Goecke",
year = "2006",
doi = "10.1109/CVPRW.2006.22",
language = "English",
isbn = "9780769525976",
pages = "1--8",
editor = "Hammoud, {Riad I} and Davis, {James W}",
booktitle = "2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Robles-Kelly, A & Goecke, R 2006, A Wavelet-based Approach to Image Feature Stability Assessment. in RI Hammoud & JW Davis (eds), 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06): Beyond patches workshop. IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 1-8, 2006 Conference on Computer Vision and Pattern Recognition Workshop, CVPRW'06, New York, United States, 17/06/06. https://doi.org/10.1109/CVPRW.2006.22

A Wavelet-based Approach to Image Feature Stability Assessment. / Robles-Kelly, Antonio; Goecke, Roland.

2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06): Beyond patches workshop. ed. / Riad I Hammoud; James W Davis. United States : IEEE, Institute of Electrical and Electronics Engineers, 2006. p. 1-8.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A Wavelet-based Approach to Image Feature Stability Assessment

AU - Robles-Kelly, Antonio

AU - Goecke, Roland

PY - 2006

Y1 - 2006

N2 - In this paper, we present a novel method for assessing image-feature stability. The method hinges on applying the discrete wavelet transform to the image features under study throughout a number of video frames in an image sequence. For purposes of stability assessment, we recover the imagefeature vectors for each video frame and then track them trough a series of consecutive frames in the image sequence. We apply the discrete wavelet transform to the time series constructed from the pairwise Euclidean distances for each of the image features under study and use the wavelet transform coefficients to assess their stability. We then recover the stable features by clustering together those time series which exhibit largely constant low-pass wavelet coefficients. We present results of the stability analysis for Harris corners, Maximally Stable Extremal Regions, and Scale Invariant Feature Transform regions extracted from two real-world video sequences. We also elaborate on the applications of our method to indexing, retrieval, and compression of stable image feature vectors

AB - In this paper, we present a novel method for assessing image-feature stability. The method hinges on applying the discrete wavelet transform to the image features under study throughout a number of video frames in an image sequence. For purposes of stability assessment, we recover the imagefeature vectors for each video frame and then track them trough a series of consecutive frames in the image sequence. We apply the discrete wavelet transform to the time series constructed from the pairwise Euclidean distances for each of the image features under study and use the wavelet transform coefficients to assess their stability. We then recover the stable features by clustering together those time series which exhibit largely constant low-pass wavelet coefficients. We present results of the stability analysis for Harris corners, Maximally Stable Extremal Regions, and Scale Invariant Feature Transform regions extracted from two real-world video sequences. We also elaborate on the applications of our method to indexing, retrieval, and compression of stable image feature vectors

U2 - 10.1109/CVPRW.2006.22

DO - 10.1109/CVPRW.2006.22

M3 - Conference contribution

SN - 9780769525976

SP - 1

EP - 8

BT - 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06)

A2 - Hammoud, Riad I

A2 - Davis, James W

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

ER -

Robles-Kelly A, Goecke R. A Wavelet-based Approach to Image Feature Stability Assessment. In Hammoud RI, Davis JW, editors, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06): Beyond patches workshop. United States: IEEE, Institute of Electrical and Electronics Engineers. 2006. p. 1-8 https://doi.org/10.1109/CVPRW.2006.22