Interesting Interest Points: A Comparative Study of Interest Point Performance on a Unique Data Set

Publication: Research - peer-reviewJournal article – Annual report year: 2011

Standard

Interesting Interest Points : A Comparative Study of Interest Point Performance on a Unique Data Set. / Aanæs, Henrik; Dahl, Anders Lindbjerg; Pedersen, Kim Steenstrup.

In: International Journal of Computer Vision, Vol. 97, No. 1, 2012, p. 18-35.

Publication: Research - peer-reviewJournal article – Annual report year: 2011

Harvard

APA

CBE

MLA

Vancouver

Author

Aanæs, Henrik; Dahl, Anders Lindbjerg; Pedersen, Kim Steenstrup / Interesting Interest Points : A Comparative Study of Interest Point Performance on a Unique Data Set.

In: International Journal of Computer Vision, Vol. 97, No. 1, 2012, p. 18-35.

Publication: Research - peer-reviewJournal article – Annual report year: 2011

Bibtex

@article{4f5f030575d14f10a05cf677c9d39160,
title = "Interesting Interest Points: A Comparative Study of Interest Point Performance on a Unique Data Set",
keywords = "Interest point detectors, Performance evaluation, Benchmark data set, Scene matching, Object recognition",
publisher = "Springer New York LLC",
author = "Henrik Aanæs and Dahl, {Anders Lindbjerg} and Pedersen, {Kim Steenstrup}",
year = "2012",
doi = "10.1007/s11263-011-0473-8",
volume = "97",
number = "1",
pages = "18--35",
journal = "International Journal of Computer Vision",
issn = "0920-5691",

}

RIS

TY - JOUR

T1 - Interesting Interest Points

T2 - A Comparative Study of Interest Point Performance on a Unique Data Set

A1 - Aanæs,Henrik

A1 - Dahl,Anders Lindbjerg

A1 - Pedersen,Kim Steenstrup

AU - Aanæs,Henrik

AU - Dahl,Anders Lindbjerg

AU - Pedersen,Kim Steenstrup

PB - Springer New York LLC

PY - 2012

Y1 - 2012

N2 - Not all interest points are equally interesting. The most valuable interest points lead to optimal performance of the computer vision method in which they are employed. But a measure of this kind will be dependent on the chosen vision application. We propose a more general performance measure based on spatial invariance of interest points under changing acquisition parameters by measuring the spatial recall rate. The scope of this paper is to investigate the performance of a number of existing well-established interest point detection methods. Automatic performance evaluation of interest points is hard because the true correspondence is generally unknown. We overcome this by providing an extensive data set with known spatial correspondence. The data is acquired with a camera mounted on a 6-axis industrial robot providing very accurate camera positioning. Furthermore the scene is scanned with a structured light scanner resulting in precise 3D surface information. In total 60 scenes are depicted ranging from model houses, building material, fruit and vegetables, fabric, printed media and more. Each scene is depicted from 119 camera positions and 19 individual LED illuminations are used for each position. The LED illumination provides the option for artificially relighting the scene from a range of light directions. This data set has given us the ability to systematically evaluate the performance of a number of interest point detectors. The highlights of the conclusions are that the fixed scale Harris corner detector performs overall best followed by the Hessian based detectors and the difference of Gaussian (DoG). The methods based on scale space features have an overall better performance than other methods especially when varying the distance to the scene, where especially FAST corner detector, Edge Based Regions (EBR) and Intensity Based Regions (IBR) have a poor performance. The performance of Maximally Stable Extremal Regions (MSER) is moderate. We observe a relatively large decline in performance with both changes in viewpoint and light direction. Some of our observations support previous findings while others contradict these findings.

AB - Not all interest points are equally interesting. The most valuable interest points lead to optimal performance of the computer vision method in which they are employed. But a measure of this kind will be dependent on the chosen vision application. We propose a more general performance measure based on spatial invariance of interest points under changing acquisition parameters by measuring the spatial recall rate. The scope of this paper is to investigate the performance of a number of existing well-established interest point detection methods. Automatic performance evaluation of interest points is hard because the true correspondence is generally unknown. We overcome this by providing an extensive data set with known spatial correspondence. The data is acquired with a camera mounted on a 6-axis industrial robot providing very accurate camera positioning. Furthermore the scene is scanned with a structured light scanner resulting in precise 3D surface information. In total 60 scenes are depicted ranging from model houses, building material, fruit and vegetables, fabric, printed media and more. Each scene is depicted from 119 camera positions and 19 individual LED illuminations are used for each position. The LED illumination provides the option for artificially relighting the scene from a range of light directions. This data set has given us the ability to systematically evaluate the performance of a number of interest point detectors. The highlights of the conclusions are that the fixed scale Harris corner detector performs overall best followed by the Hessian based detectors and the difference of Gaussian (DoG). The methods based on scale space features have an overall better performance than other methods especially when varying the distance to the scene, where especially FAST corner detector, Edge Based Regions (EBR) and Intensity Based Regions (IBR) have a poor performance. The performance of Maximally Stable Extremal Regions (MSER) is moderate. We observe a relatively large decline in performance with both changes in viewpoint and light direction. Some of our observations support previous findings while others contradict these findings.

KW - Interest point detectors

KW - Performance evaluation

KW - Benchmark data set

KW - Scene matching

KW - Object recognition

U2 - 10.1007/s11263-011-0473-8

DO - 10.1007/s11263-011-0473-8

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1

VL - 97

SP - 18

EP - 35

ER -