Active multi-view object recognition: A unifying view on online feature selection and view planning
详细信息 查看全文
- 作者：Christian Potthast ; potthast@usc.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Andreas Breitenmoser andreas.breitenmoser@usc.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Fei Sha feisha@usc.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Gaurav S. Sukhatme gaurav@usc.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Viewpoint selection ; Feature selection ; Multi-view object recognition ; Information-theory ; Active perception ; Object change detection
- 刊名：Robotics and Autonomous Systems
- 出版年：2016
- 出版时间：October 2016
- 年：2016
- 卷：84
- 期：Complete
- 页码：31-47
- 全文大小：1102 K
文摘
- •
A unified approach to feature and viewpoint selection for multi-view object recognition is proposed.
- •
Online feature selection reduces the dimensionality and with that the computation time.
- •
View planning offers performance advantages whenever multiple views are required due to ambiguous situations or occlusions.
- •
Increased recognition accuracy and reduced computation cost are realized by an information-theoretic action selection framework.