Improved feature detection in fused intensity-range images with complex SIFT (CSIFT)

Patrick Erik Bradley; Boris Jutzi

doi:10.3390/rs3092076

Improved feature detection in fused intensity-range images with complex SIFT (CSIFT)

Patrick Erik Bradley, Boris Jutzi

Humanoid Technologies Lab (H2T)

Research output: Contribution to journal › Article › peer-review

8 Scopus citations

Abstract

The real and imaginary parts are proposed as an alternative to the usual Polar representation of complex-valued images. It is proven that the transformation from Polar to Cartesian representation contributes to decreased mutual information, and hence to greater distinctiveness. The Complex Scale-Invariant Feature Transform (CSIFT) detects distinctive features in complex-valued images. An evaluation method for estimating the uniformity of feature distributions in complex-valued images derived from intensity-range images is proposed. In order to experimentally evaluate the proposed methodology on intensity-range images, three different kinds of active sensing systems were used: Range Imaging, Laser Scanning, and Structured Light Projection devices (PMD CamCube 2.0, Z+F IMAGER 5003, Microsoft Kinect).

Original language	English
Pages (from-to)	2076-2088
Number of pages	13
Journal	Remote Sensing
Volume	3
Issue number	9
DOIs	https://doi.org/10.3390/rs3092076
State	Published - Sep 2011
Externally published	Yes

Keywords

Active sensor
Complex-valued image
Image-based registration
Laser scanning
Mutual information
Range imaging
Sift
Structured light projection

Access to Document

10.3390/rs3092076

Cite this

@article{b55c6b957670499080b827c33f58303c,

title = "Improved feature detection in fused intensity-range images with complex SIFT (CSIFT)",

abstract = "The real and imaginary parts are proposed as an alternative to the usual Polar representation of complex-valued images. It is proven that the transformation from Polar to Cartesian representation contributes to decreased mutual information, and hence to greater distinctiveness. The Complex Scale-Invariant Feature Transform (CSIFT) detects distinctive features in complex-valued images. An evaluation method for estimating the uniformity of feature distributions in complex-valued images derived from intensity-range images is proposed. In order to experimentally evaluate the proposed methodology on intensity-range images, three different kinds of active sensing systems were used: Range Imaging, Laser Scanning, and Structured Light Projection devices (PMD CamCube 2.0, Z+F IMAGER 5003, Microsoft Kinect).",

keywords = "Active sensor, Complex-valued image, Image-based registration, Laser scanning, Mutual information, Range imaging, Sift, Structured light projection",

author = "Bradley, {Patrick Erik} and Boris Jutzi",

year = "2011",

month = sep,

doi = "10.3390/rs3092076",

language = "English",

volume = "3",

pages = "2076--2088",

journal = "Remote Sensing",

issn = "2072-4292",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "9",

}

TY - JOUR

T1 - Improved feature detection in fused intensity-range images with complex SIFT (CSIFT)

AU - Bradley, Patrick Erik

AU - Jutzi, Boris

PY - 2011/9

Y1 - 2011/9

N2 - The real and imaginary parts are proposed as an alternative to the usual Polar representation of complex-valued images. It is proven that the transformation from Polar to Cartesian representation contributes to decreased mutual information, and hence to greater distinctiveness. The Complex Scale-Invariant Feature Transform (CSIFT) detects distinctive features in complex-valued images. An evaluation method for estimating the uniformity of feature distributions in complex-valued images derived from intensity-range images is proposed. In order to experimentally evaluate the proposed methodology on intensity-range images, three different kinds of active sensing systems were used: Range Imaging, Laser Scanning, and Structured Light Projection devices (PMD CamCube 2.0, Z+F IMAGER 5003, Microsoft Kinect).

AB - The real and imaginary parts are proposed as an alternative to the usual Polar representation of complex-valued images. It is proven that the transformation from Polar to Cartesian representation contributes to decreased mutual information, and hence to greater distinctiveness. The Complex Scale-Invariant Feature Transform (CSIFT) detects distinctive features in complex-valued images. An evaluation method for estimating the uniformity of feature distributions in complex-valued images derived from intensity-range images is proposed. In order to experimentally evaluate the proposed methodology on intensity-range images, three different kinds of active sensing systems were used: Range Imaging, Laser Scanning, and Structured Light Projection devices (PMD CamCube 2.0, Z+F IMAGER 5003, Microsoft Kinect).

KW - Active sensor

KW - Complex-valued image

KW - Image-based registration

KW - Laser scanning

KW - Mutual information

KW - Range imaging

KW - Sift

KW - Structured light projection

UR - http://www.scopus.com/inward/record.url?scp=80755175259&partnerID=8YFLogxK

U2 - 10.3390/rs3092076

DO - 10.3390/rs3092076

M3 - Article

AN - SCOPUS:80755175259

SN - 2072-4292

VL - 3

SP - 2076

EP - 2088

JO - Remote Sensing

JF - Remote Sensing

IS - 9

ER -

Improved feature detection in fused intensity-range images with complex SIFT (CSIFT)

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this