Learning to discover objects in RGB-D images using correlation clustering

Michael Firman, Diego Thomas, Simon Julier, Akihiro Sugimoto

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

7 引用 (Scopus)

抜粋

We introduce a method to discover objects from RGB-D image collections which does not require a user to specify the number of objects expected to be found. We propose a probabilistic formulation to find pairwise similarity between image segments, using a classifier trained on labelled pairs from the recently released RGB-D Object Dataset. We then use a correlation clustering solver to both find the optimal clustering of all the segments in the collection and to recover the number of clusters. Unlike traditional supervised learning methods, our training data need not be of the same class or category as the objects we expect to discover. We show that this parameter-free supervised clustering method has superior performance to traditional clustering methods.

元の言語英語
ホスト出版物のタイトルIROS 2013
ホスト出版物のサブタイトルNew Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems
ページ1107-1112
ページ数6
DOI
出版物ステータス出版済み - 12 1 2013
外部発表Yes
イベント2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013 - Tokyo, 日本
継続期間: 11 3 201311 8 2013

出版物シリーズ

名前IEEE International Conference on Intelligent Robots and Systems
ISSN(印刷物)2153-0858
ISSN(電子版)2153-0866

その他

その他2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013
日本
Tokyo
期間11/3/1311/8/13

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

フィンガープリント Learning to discover objects in RGB-D images using correlation clustering' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Firman, M., Thomas, D., Julier, S., & Sugimoto, A. (2013). Learning to discover objects in RGB-D images using correlation clustering. : IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 1107-1112). [6696488] (IEEE International Conference on Intelligent Robots and Systems). https://doi.org/10.1109/IROS.2013.6696488