Detecting and Grouping Identical Objects for Region Proposal and Classification

Wim Abbeloos; Sergio Caccamo; Esra Ataer-Cansizoglu; Yuichi Taguchi; Chen Feng; Teng Yok Lee

doi:10.1109/CVPRW.2017.76

Detecting and Grouping Identical Objects for Region Proposal and Classification

Wim Abbeloos, Sergio Caccamo, Esra Ataer-Cansizoglu, Yuichi Taguchi, Chen Feng, Teng Yok Lee

Civil and Urban Engineering

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

Abstract

Often multiple instances of an object occur in the same scene, for example in a warehouse. Unsupervised multi-instance object discovery algorithms are able to detect and identify such objects. We use such an algorithm to provide object proposals to a convolutional neural network (CNN) based classifier. This results in fewer regions to evaluate, compared to traditional region proposal algorithms. Additionally, it enables using the joint probability of multiple instances of an object, resulting in improved classification accuracy. The proposed technique can also split a single class into multiple sub-classes corresponding to the different object types, enabling hierarchical classification.

Original language	English (US)
Title of host publication	Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Publisher	IEEE Computer Society
Pages	501-502
Number of pages	2
ISBN (Electronic)	9781538607336
DOIs	https://doi.org/10.1109/CVPRW.2017.76
State	Published - Aug 22 2017
Event	30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States Duration: Jul 21 2017 → Jul 26 2017

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2017-July
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Other

Other	30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Country/Territory	United States
City	Honolulu
Period	7/21/17 → 7/26/17

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW.2017.76

Cite this

Abbeloos, W., Caccamo, S., Ataer-Cansizoglu, E., Taguchi, Y., Feng, C., & Lee, T. Y. (2017). Detecting and Grouping Identical Objects for Region Proposal and Classification. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 (pp. 501-502). Article 8014810 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2017.76

Detecting and Grouping Identical Objects for Region Proposal and Classification. / Abbeloos, Wim; Caccamo, Sergio; Ataer-Cansizoglu, Esra et al.
Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society, 2017. p. 501-502 8014810 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July).

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

Abbeloos, W, Caccamo, S, Ataer-Cansizoglu, E, Taguchi, Y, Feng, C & Lee, TY 2017, Detecting and Grouping Identical Objects for Region Proposal and Classification. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017., 8014810, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2017-July, IEEE Computer Society, pp. 501-502, 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, Honolulu, United States, 7/21/17. https://doi.org/10.1109/CVPRW.2017.76

Abbeloos W, Caccamo S, Ataer-Cansizoglu E, Taguchi Y, Feng C, Lee TY. Detecting and Grouping Identical Objects for Region Proposal and Classification. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society. 2017. p. 501-502. 8014810. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW.2017.76

Abbeloos, Wim ; Caccamo, Sergio ; Ataer-Cansizoglu, Esra et al. / Detecting and Grouping Identical Objects for Region Proposal and Classification. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society, 2017. pp. 501-502 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

@inproceedings{5dda5d448803483ea40b8de5d56e3be9,

title = "Detecting and Grouping Identical Objects for Region Proposal and Classification",

abstract = "Often multiple instances of an object occur in the same scene, for example in a warehouse. Unsupervised multi-instance object discovery algorithms are able to detect and identify such objects. We use such an algorithm to provide object proposals to a convolutional neural network (CNN) based classifier. This results in fewer regions to evaluate, compared to traditional region proposal algorithms. Additionally, it enables using the joint probability of multiple instances of an object, resulting in improved classification accuracy. The proposed technique can also split a single class into multiple sub-classes corresponding to the different object types, enabling hierarchical classification.",

author = "Wim Abbeloos and Sergio Caccamo and Esra Ataer-Cansizoglu and Yuichi Taguchi and Chen Feng and Lee, {Teng Yok}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 ; Conference date: 21-07-2017 Through 26-07-2017",

year = "2017",

month = aug,

day = "22",

doi = "10.1109/CVPRW.2017.76",

language = "English (US)",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "501--502",

booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017",

}

TY - GEN

T1 - Detecting and Grouping Identical Objects for Region Proposal and Classification

AU - Abbeloos, Wim

AU - Caccamo, Sergio

AU - Ataer-Cansizoglu, Esra

AU - Taguchi, Yuichi

AU - Feng, Chen

AU - Lee, Teng Yok

PY - 2017/8/22

Y1 - 2017/8/22

N2 - Often multiple instances of an object occur in the same scene, for example in a warehouse. Unsupervised multi-instance object discovery algorithms are able to detect and identify such objects. We use such an algorithm to provide object proposals to a convolutional neural network (CNN) based classifier. This results in fewer regions to evaluate, compared to traditional region proposal algorithms. Additionally, it enables using the joint probability of multiple instances of an object, resulting in improved classification accuracy. The proposed technique can also split a single class into multiple sub-classes corresponding to the different object types, enabling hierarchical classification.

AB - Often multiple instances of an object occur in the same scene, for example in a warehouse. Unsupervised multi-instance object discovery algorithms are able to detect and identify such objects. We use such an algorithm to provide object proposals to a convolutional neural network (CNN) based classifier. This results in fewer regions to evaluate, compared to traditional region proposal algorithms. Additionally, it enables using the joint probability of multiple instances of an object, resulting in improved classification accuracy. The proposed technique can also split a single class into multiple sub-classes corresponding to the different object types, enabling hierarchical classification.

UR - http://www.scopus.com/inward/record.url?scp=85030248255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030248255&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2017.76

DO - 10.1109/CVPRW.2017.76

M3 - Conference contribution

AN - SCOPUS:85030248255

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 501

EP - 502

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

PB - IEEE Computer Society

T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

Y2 - 21 July 2017 through 26 July 2017

ER -

Detecting and Grouping Identical Objects for Region Proposal and Classification

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this