Pixel weighted average strategy for depth sensor data fusion

Frederic Garcia; Bruno Mirbach; Bjorn Ottersten; Frédéric Grandidier; Ángel Cuesta

doi:10.1109/ICIP.2010.5651112

Pixel weighted average strategy for depth sensor data fusion

Frederic Garcia^*, Bruno Mirbach, Bjorn Ottersten, Frédéric Grandidier, Ángel Cuesta

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

78 Citations (Scopus)

Abstract

This paper introduces a new multi-lateral filter to fuse low-resolution depth maps with high-resolution images. The goal is to enhance the resolution of Time-of-Flight sensors and, at the same time, reduce the noise level in depth measurements. Our approach is based on the joint bilateral upsampling, extended by a new factor that considers the low reliability of depth measurements along the low-resolution depth map edges. Our experimental results show better performances than alternative depth enhancing data fusion techniques.

Original language	English
Title of host publication	2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings
Pages	2805-2808
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2010.5651112
Publication status	Published - 2010
Externally published	Yes
Event	2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong, Hong Kong Duration: 26 Sept 2010 → 29 Sept 2010

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880

Conference

Conference	2010 17th IEEE International Conference on Image Processing, ICIP 2010
Country/Territory	Hong Kong
City	Hong Kong
Period	26/09/10 → 29/09/10

Keywords

Active vision
Image resolution
Machine vision
Multisensor systems
Nonlinear filters

Access to Document

10.1109/ICIP.2010.5651112

Cite this

@inproceedings{f8fabe25d2934e04b15fd513ce6abb01,

title = "Pixel weighted average strategy for depth sensor data fusion",

abstract = "This paper introduces a new multi-lateral filter to fuse low-resolution depth maps with high-resolution images. The goal is to enhance the resolution of Time-of-Flight sensors and, at the same time, reduce the noise level in depth measurements. Our approach is based on the joint bilateral upsampling, extended by a new factor that considers the low reliability of depth measurements along the low-resolution depth map edges. Our experimental results show better performances than alternative depth enhancing data fusion techniques.",

keywords = "Active vision, Image resolution, Machine vision, Multisensor systems, Nonlinear filters",

author = "Frederic Garcia and Bruno Mirbach and Bjorn Ottersten and Fr{\'e}d{\'e}ric Grandidier and {\'A}ngel Cuesta",

year = "2010",

doi = "10.1109/ICIP.2010.5651112",

language = "English",

isbn = "9781424479948",

series = "Proceedings - International Conference on Image Processing, ICIP",

pages = "2805--2808",

booktitle = "2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings",

note = "2010 17th IEEE International Conference on Image Processing, ICIP 2010 ; Conference date: 26-09-2010 Through 29-09-2010",

}

Garcia, F, Mirbach, B, Ottersten, B, Grandidier, F & Cuesta, Á 2010, Pixel weighted average strategy for depth sensor data fusion. in 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings., 5651112, Proceedings - International Conference on Image Processing, ICIP, pp. 2805-2808, 2010 17th IEEE International Conference on Image Processing, ICIP 2010, Hong Kong, Hong Kong, 26/09/10. https://doi.org/10.1109/ICIP.2010.5651112

Pixel weighted average strategy for depth sensor data fusion. / Garcia, Frederic; Mirbach, Bruno; Ottersten, Bjorn et al.
2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings. 2010. p. 2805-2808 5651112 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Pixel weighted average strategy for depth sensor data fusion

AU - Garcia, Frederic

AU - Mirbach, Bruno

AU - Ottersten, Bjorn

AU - Grandidier, Frédéric

AU - Cuesta, Ángel

PY - 2010

Y1 - 2010

N2 - This paper introduces a new multi-lateral filter to fuse low-resolution depth maps with high-resolution images. The goal is to enhance the resolution of Time-of-Flight sensors and, at the same time, reduce the noise level in depth measurements. Our approach is based on the joint bilateral upsampling, extended by a new factor that considers the low reliability of depth measurements along the low-resolution depth map edges. Our experimental results show better performances than alternative depth enhancing data fusion techniques.

AB - This paper introduces a new multi-lateral filter to fuse low-resolution depth maps with high-resolution images. The goal is to enhance the resolution of Time-of-Flight sensors and, at the same time, reduce the noise level in depth measurements. Our approach is based on the joint bilateral upsampling, extended by a new factor that considers the low reliability of depth measurements along the low-resolution depth map edges. Our experimental results show better performances than alternative depth enhancing data fusion techniques.

KW - Active vision

KW - Image resolution

KW - Machine vision

KW - Multisensor systems

KW - Nonlinear filters

UR - http://www.scopus.com/inward/record.url?scp=78651112669&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2010.5651112

DO - 10.1109/ICIP.2010.5651112

M3 - Conference contribution

AN - SCOPUS:78651112669

SN - 9781424479948

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 2805

EP - 2808

BT - 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings

T2 - 2010 17th IEEE International Conference on Image Processing, ICIP 2010

Y2 - 26 September 2010 through 29 September 2010

ER -

Pixel weighted average strategy for depth sensor data fusion

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this