Bayesian viewpoint-dependent robust classification under model and localization uncertainty

Yuri Feldman; Vadim Indelman

doi:10.1109/ICRA.2018.8461127

Bayesian viewpoint-dependent robust classification under model and localization uncertainty

Aerospace Engineering

Technion - Israel Institute of Technology

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

Abstract

We propose an algorithm for robust visual classification of an object of interest observed from multiple views using a black-box Bayesian classifier which provides a measure of uncertainty, in the presence of significant ambiguity and classifier noise, and of localization error. The fusion of classifier outputs takes into account viewpoint dependency and spatial correlation among observations, as well as pose uncertainty when these observations are taken and a measure of confidence provided by the classifier itself. Our experiments confirm an improvement in robustness over state-of-the-art.

Original language	English GB
Title of host publication	2018 IEEE International Conference on Robotics and Automation, ICRA 2018
Pages	3221-3228
Number of pages	8
ISBN (Electronic)	9781538630815
DOIs	https://doi.org/10.1109/ICRA.2018.8461127
State	Published - 10 Sep 2018
Event	2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, Australia Duration: 21 May 2018 → 25 May 2018

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation

Conference

Conference	2018 IEEE International Conference on Robotics and Automation, ICRA 2018
Country/Territory	Australia
City	Brisbane
Period	21/05/18 → 25/05/18

ASJC Scopus subject areas

Software
Control and Systems Engineering
Artificial Intelligence
Electrical and Electronic Engineering

Access to Document

10.1109/ICRA.2018.8461127

Cite this

@inproceedings{2bc837b22e5540829eba0e6f9e93e6b7,

title = "Bayesian viewpoint-dependent robust classification under model and localization uncertainty",

abstract = "We propose an algorithm for robust visual classification of an object of interest observed from multiple views using a black-box Bayesian classifier which provides a measure of uncertainty, in the presence of significant ambiguity and classifier noise, and of localization error. The fusion of classifier outputs takes into account viewpoint dependency and spatial correlation among observations, as well as pose uncertainty when these observations are taken and a measure of confidence provided by the classifier itself. Our experiments confirm an improvement in robustness over state-of-the-art.",

author = "Yuri Feldman and Vadim Indelman",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Robotics and Automation, ICRA 2018 ; Conference date: 21-05-2018 Through 25-05-2018",

year = "2018",

month = sep,

day = "10",

doi = "10.1109/ICRA.2018.8461127",

language = "الإنجليزيّة",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

pages = "3221--3228",

booktitle = "2018 IEEE International Conference on Robotics and Automation, ICRA 2018",

}

Feldman, Y & Indelman, V 2018, Bayesian viewpoint-dependent robust classification under model and localization uncertainty. in 2018 IEEE International Conference on Robotics and Automation, ICRA 2018., 8461127, Proceedings - IEEE International Conference on Robotics and Automation, pp. 3221-3228, 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, 21/05/18. https://doi.org/10.1109/ICRA.2018.8461127

Bayesian viewpoint-dependent robust classification under model and localization uncertainty. / Feldman, Yuri ; Indelman, Vadim.
2018 IEEE International Conference on Robotics and Automation, ICRA 2018. 2018. p. 3221-3228 8461127 (Proceedings - IEEE International Conference on Robotics and Automation).

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

TY - GEN

T1 - Bayesian viewpoint-dependent robust classification under model and localization uncertainty

AU - Feldman, Yuri

AU - Indelman, Vadim

PY - 2018/9/10

Y1 - 2018/9/10

N2 - We propose an algorithm for robust visual classification of an object of interest observed from multiple views using a black-box Bayesian classifier which provides a measure of uncertainty, in the presence of significant ambiguity and classifier noise, and of localization error. The fusion of classifier outputs takes into account viewpoint dependency and spatial correlation among observations, as well as pose uncertainty when these observations are taken and a measure of confidence provided by the classifier itself. Our experiments confirm an improvement in robustness over state-of-the-art.

AB - We propose an algorithm for robust visual classification of an object of interest observed from multiple views using a black-box Bayesian classifier which provides a measure of uncertainty, in the presence of significant ambiguity and classifier noise, and of localization error. The fusion of classifier outputs takes into account viewpoint dependency and spatial correlation among observations, as well as pose uncertainty when these observations are taken and a measure of confidence provided by the classifier itself. Our experiments confirm an improvement in robustness over state-of-the-art.

UR - https://www.scopus.com/pages/publications/85048745916

U2 - 10.1109/ICRA.2018.8461127

DO - 10.1109/ICRA.2018.8461127

M3 - منشور من مؤتمر

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 3221

EP - 3228

BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018

T2 - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018

Y2 - 21 May 2018 through 25 May 2018

ER -

Bayesian viewpoint-dependent robust classification under model and localization uncertainty

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this