Efficient keypoint detection and description via polynomial regression of scale space

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Keypoint detection and description using approximate continuous scale space are more efficient techniques than typical discretized scale space for achieving more robust feature matching. However, this state-of-the-art method requires high computational complexity to approximately reconstruct, or decompress, the value at an arbitrary point in scale space. Specifically, it has O(M2) computational complexity where M is an approximation order. This paper presents an efficient scale space approach that provides decompression operation with O(M) complexity without a loss of accuracy. As a result of the fact that the proposed method has much fewer variables to be solved, the least-square solution can be obtained through normal equation. This is easier to solve than the existing method which employs Karhunen-Loeve expansion and generalized eigenvalue problem. Experiments revealed that the proposed method performs as expected from the theoretical analysis.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1357-1361
Number of pages5
Volume2016-May
ISBN (Electronic)9781479999880
DOIs
Publication statusPublished - 2016 May 18
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
Duration: 2016 Mar 202016 Mar 25

Other

Other41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
CountryChina
CityShanghai
Period16/3/2016/3/25

Fingerprint

Computational complexity
Polynomials
Experiments

Keywords

  • Compressed scale space
  • Feature extraction
  • Image filtering
  • Scale space
  • Spectral SIFT

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Okutani, R., Sugimoto, K., & Kamata, S. (2016). Efficient keypoint detection and description via polynomial regression of scale space. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (Vol. 2016-May, pp. 1357-1361). [7471898] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7471898

Efficient keypoint detection and description via polynomial regression of scale space. / Okutani, Ryo; Sugimoto, Kenjiro; Kamata, Seiichiro.

2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. p. 1357-1361 7471898.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Okutani, R, Sugimoto, K & Kamata, S 2016, Efficient keypoint detection and description via polynomial regression of scale space. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. vol. 2016-May, 7471898, Institute of Electrical and Electronics Engineers Inc., pp. 1357-1361, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 16/3/20. https://doi.org/10.1109/ICASSP.2016.7471898
Okutani R, Sugimoto K, Kamata S. Efficient keypoint detection and description via polynomial regression of scale space. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1357-1361. 7471898 https://doi.org/10.1109/ICASSP.2016.7471898
Okutani, Ryo ; Sugimoto, Kenjiro ; Kamata, Seiichiro. / Efficient keypoint detection and description via polynomial regression of scale space. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1357-1361
@inproceedings{f55a4b4c8e74435e8db6172642ffb9a4,
title = "Efficient keypoint detection and description via polynomial regression of scale space",
abstract = "Keypoint detection and description using approximate continuous scale space are more efficient techniques than typical discretized scale space for achieving more robust feature matching. However, this state-of-the-art method requires high computational complexity to approximately reconstruct, or decompress, the value at an arbitrary point in scale space. Specifically, it has O(M2) computational complexity where M is an approximation order. This paper presents an efficient scale space approach that provides decompression operation with O(M) complexity without a loss of accuracy. As a result of the fact that the proposed method has much fewer variables to be solved, the least-square solution can be obtained through normal equation. This is easier to solve than the existing method which employs Karhunen-Loeve expansion and generalized eigenvalue problem. Experiments revealed that the proposed method performs as expected from the theoretical analysis.",
keywords = "Compressed scale space, Feature extraction, Image filtering, Scale space, Spectral SIFT",
author = "Ryo Okutani and Kenjiro Sugimoto and Seiichiro Kamata",
year = "2016",
month = "5",
day = "18",
doi = "10.1109/ICASSP.2016.7471898",
language = "English",
volume = "2016-May",
pages = "1357--1361",
booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Efficient keypoint detection and description via polynomial regression of scale space

AU - Okutani, Ryo

AU - Sugimoto, Kenjiro

AU - Kamata, Seiichiro

PY - 2016/5/18

Y1 - 2016/5/18

N2 - Keypoint detection and description using approximate continuous scale space are more efficient techniques than typical discretized scale space for achieving more robust feature matching. However, this state-of-the-art method requires high computational complexity to approximately reconstruct, or decompress, the value at an arbitrary point in scale space. Specifically, it has O(M2) computational complexity where M is an approximation order. This paper presents an efficient scale space approach that provides decompression operation with O(M) complexity without a loss of accuracy. As a result of the fact that the proposed method has much fewer variables to be solved, the least-square solution can be obtained through normal equation. This is easier to solve than the existing method which employs Karhunen-Loeve expansion and generalized eigenvalue problem. Experiments revealed that the proposed method performs as expected from the theoretical analysis.

AB - Keypoint detection and description using approximate continuous scale space are more efficient techniques than typical discretized scale space for achieving more robust feature matching. However, this state-of-the-art method requires high computational complexity to approximately reconstruct, or decompress, the value at an arbitrary point in scale space. Specifically, it has O(M2) computational complexity where M is an approximation order. This paper presents an efficient scale space approach that provides decompression operation with O(M) complexity without a loss of accuracy. As a result of the fact that the proposed method has much fewer variables to be solved, the least-square solution can be obtained through normal equation. This is easier to solve than the existing method which employs Karhunen-Loeve expansion and generalized eigenvalue problem. Experiments revealed that the proposed method performs as expected from the theoretical analysis.

KW - Compressed scale space

KW - Feature extraction

KW - Image filtering

KW - Scale space

KW - Spectral SIFT

UR - http://www.scopus.com/inward/record.url?scp=84973311830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973311830&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7471898

DO - 10.1109/ICASSP.2016.7471898

M3 - Conference contribution

AN - SCOPUS:84973311830

VL - 2016-May

SP - 1357

EP - 1361

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -