Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees

Research output: Chapter in Book/Conference paperConference paper

21 Citations (Scopus)

Abstract

© 2015 IEEE. This paper presents an efficient framework for the categorization of objects in real-world scenes (captured with an RGB-D sensor). The proposed framework uses ensembles of randomized decision trees in a hierarchical cascaded architecture to compute consistent object-class inferences of unseen objects. Specifically, the proposed framework computes object-class probabilities at three levels of an image hierarchy (i.e., pixel-, surfel-, and object-levels) using Random Forest classifiers. Next, these probabilities are fused together to compute a cumulative probabilistic output which is used to infer object categories. This fusion results in an improved object categorization performance compared with the state-of-the-art methods.
Original languageEnglish
Title of host publication2015 IEEE International Conference on Robotics and Automation (ICRA)
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1295-1302
Volume2015-June
ISBN (Print)10504729
DOIs
Publication statusPublished - 2015
Event2015 IEEE International Conference on Robotics and Automation (ICRA) - Seattle, United States
Duration: 26 May 201530 May 2015

Conference

Conference2015 IEEE International Conference on Robotics and Automation (ICRA)
CountryUnited States
CitySeattle
Period26/05/1530/05/15

Fingerprint

Decision trees
Classifiers
Fusion reactions
Pixels
Sensors

Cite this

Asif, U., Bennamoun, M., & Sohel, F. (2015). Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees. In 2015 IEEE International Conference on Robotics and Automation (ICRA) (Vol. 2015-June, pp. 1295-1302). USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICRA.2015.7139358
Asif, Umar ; Bennamoun, Mohammed ; Sohel, Ferdous. / Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees. 2015 IEEE International Conference on Robotics and Automation (ICRA). Vol. 2015-June USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 1295-1302
@inproceedings{8bf8643bc51448bdb29ae670e6311e6a,
title = "Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees",
abstract = "{\circledC} 2015 IEEE. This paper presents an efficient framework for the categorization of objects in real-world scenes (captured with an RGB-D sensor). The proposed framework uses ensembles of randomized decision trees in a hierarchical cascaded architecture to compute consistent object-class inferences of unseen objects. Specifically, the proposed framework computes object-class probabilities at three levels of an image hierarchy (i.e., pixel-, surfel-, and object-levels) using Random Forest classifiers. Next, these probabilities are fused together to compute a cumulative probabilistic output which is used to infer object categories. This fusion results in an improved object categorization performance compared with the state-of-the-art methods.",
author = "Umar Asif and Mohammed Bennamoun and Ferdous Sohel",
year = "2015",
doi = "10.1109/ICRA.2015.7139358",
language = "English",
isbn = "10504729",
volume = "2015-June",
pages = "1295--1302",
booktitle = "2015 IEEE International Conference on Robotics and Automation (ICRA)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Asif, U, Bennamoun, M & Sohel, F 2015, Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees. in 2015 IEEE International Conference on Robotics and Automation (ICRA). vol. 2015-June, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 1295-1302, 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, United States, 26/05/15. https://doi.org/10.1109/ICRA.2015.7139358

Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees. / Asif, Umar; Bennamoun, Mohammed; Sohel, Ferdous.

2015 IEEE International Conference on Robotics and Automation (ICRA). Vol. 2015-June USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 1295-1302.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees

AU - Asif, Umar

AU - Bennamoun, Mohammed

AU - Sohel, Ferdous

PY - 2015

Y1 - 2015

N2 - © 2015 IEEE. This paper presents an efficient framework for the categorization of objects in real-world scenes (captured with an RGB-D sensor). The proposed framework uses ensembles of randomized decision trees in a hierarchical cascaded architecture to compute consistent object-class inferences of unseen objects. Specifically, the proposed framework computes object-class probabilities at three levels of an image hierarchy (i.e., pixel-, surfel-, and object-levels) using Random Forest classifiers. Next, these probabilities are fused together to compute a cumulative probabilistic output which is used to infer object categories. This fusion results in an improved object categorization performance compared with the state-of-the-art methods.

AB - © 2015 IEEE. This paper presents an efficient framework for the categorization of objects in real-world scenes (captured with an RGB-D sensor). The proposed framework uses ensembles of randomized decision trees in a hierarchical cascaded architecture to compute consistent object-class inferences of unseen objects. Specifically, the proposed framework computes object-class probabilities at three levels of an image hierarchy (i.e., pixel-, surfel-, and object-levels) using Random Forest classifiers. Next, these probabilities are fused together to compute a cumulative probabilistic output which is used to infer object categories. This fusion results in an improved object categorization performance compared with the state-of-the-art methods.

U2 - 10.1109/ICRA.2015.7139358

DO - 10.1109/ICRA.2015.7139358

M3 - Conference paper

SN - 10504729

VL - 2015-June

SP - 1295

EP - 1302

BT - 2015 IEEE International Conference on Robotics and Automation (ICRA)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

ER -

Asif U, Bennamoun M, Sohel F. Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees. In 2015 IEEE International Conference on Robotics and Automation (ICRA). Vol. 2015-June. USA: IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 1295-1302 https://doi.org/10.1109/ICRA.2015.7139358