Object classfication from RGB-D images using depth context kernel descriptors

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Object classfication from RGB-D images using depth context kernel descriptors. / Pan, Hong; Olsen, Søren Ingvor; Zhu, Yaping.

2015 IEEE International Conference on Image Processing (ICIP 2015). IEEE, 2015. s. 512-516.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Pan, H, Olsen, SI & Zhu, Y 2015, Object classfication from RGB-D images using depth context kernel descriptors. i 2015 IEEE International Conference on Image Processing (ICIP 2015). IEEE, s. 512-516, International Conference on Image Processing 2015, Quebec City, Canada, 27/09/2015. https://doi.org/10.1109/ICIP.2015.7350851

APA

Pan, H., Olsen, S. I., & Zhu, Y. (2015). Object classfication from RGB-D images using depth context kernel descriptors. I 2015 IEEE International Conference on Image Processing (ICIP 2015) (s. 512-516). IEEE. https://doi.org/10.1109/ICIP.2015.7350851

Vancouver

Pan H, Olsen SI, Zhu Y. Object classfication from RGB-D images using depth context kernel descriptors. I 2015 IEEE International Conference on Image Processing (ICIP 2015). IEEE. 2015. s. 512-516 https://doi.org/10.1109/ICIP.2015.7350851

Author

Pan, Hong ; Olsen, Søren Ingvor ; Zhu, Yaping. / Object classfication from RGB-D images using depth context kernel descriptors. 2015 IEEE International Conference on Image Processing (ICIP 2015). IEEE, 2015. s. 512-516

Bibtex

@inproceedings{1cc67b48485b452ea0eda1174016bee5,
title = "Object classfication from RGB-D images using depth context kernel descriptors",
abstract = "Context cue is important in object classification. By embedding the depth context cue of image attributes into kernel descriptors, we propose a new set of depth image descriptors called depth context kernel descriptors (DCKD) for RGB-D based object classification. The motivation of DCKD is to use the depth consistency of image attributes defined within a neighboring region to improve the robustness of descriptor matching in the kernel space. Moreover, a novel joint spatial-depth pooling (JSDP) scheme, which further partitions image sub-regions using the depth cue and pools features in both 2D image plane and the depth direction, is developed to take full advantage of the available depth information. By embedding DCKD and JSDP into the standard object classification pipeline, we achieve superior performance to state-of-the-art methods on RGB-D benchmarks for object classification and scene recognition.",
keywords = "Faculty of Science, RGB-D object classification, Context cue,",
author = "Hong Pan and Olsen, {S{\o}ren Ingvor} and Yaping Zhu",
year = "2015",
doi = "10.1109/ICIP.2015.7350851",
language = "English",
pages = "512--516",
booktitle = "2015 IEEE International Conference on Image Processing (ICIP 2015)",
publisher = "IEEE",
note = "null ; Conference date: 27-09-2015 Through 30-09-2015",

}

RIS

TY - GEN

T1 - Object classfication from RGB-D images using depth context kernel descriptors

AU - Pan, Hong

AU - Olsen, Søren Ingvor

AU - Zhu, Yaping

PY - 2015

Y1 - 2015

N2 - Context cue is important in object classification. By embedding the depth context cue of image attributes into kernel descriptors, we propose a new set of depth image descriptors called depth context kernel descriptors (DCKD) for RGB-D based object classification. The motivation of DCKD is to use the depth consistency of image attributes defined within a neighboring region to improve the robustness of descriptor matching in the kernel space. Moreover, a novel joint spatial-depth pooling (JSDP) scheme, which further partitions image sub-regions using the depth cue and pools features in both 2D image plane and the depth direction, is developed to take full advantage of the available depth information. By embedding DCKD and JSDP into the standard object classification pipeline, we achieve superior performance to state-of-the-art methods on RGB-D benchmarks for object classification and scene recognition.

AB - Context cue is important in object classification. By embedding the depth context cue of image attributes into kernel descriptors, we propose a new set of depth image descriptors called depth context kernel descriptors (DCKD) for RGB-D based object classification. The motivation of DCKD is to use the depth consistency of image attributes defined within a neighboring region to improve the robustness of descriptor matching in the kernel space. Moreover, a novel joint spatial-depth pooling (JSDP) scheme, which further partitions image sub-regions using the depth cue and pools features in both 2D image plane and the depth direction, is developed to take full advantage of the available depth information. By embedding DCKD and JSDP into the standard object classification pipeline, we achieve superior performance to state-of-the-art methods on RGB-D benchmarks for object classification and scene recognition.

KW - Faculty of Science

KW - RGB-D object classification, Context cue,

U2 - 10.1109/ICIP.2015.7350851

DO - 10.1109/ICIP.2015.7350851

M3 - Article in proceedings

SP - 512

EP - 516

BT - 2015 IEEE International Conference on Image Processing (ICIP 2015)

PB - IEEE

Y2 - 27 September 2015 through 30 September 2015

ER -

ID: 160890096