Active multi-view object recognition A unifying view on online feature selection and view planning.pdfVIP
- 1、有哪些信誉好的足球投注网站(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
- 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
- 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
- 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
Active multi-view object recognition A unifying view on online feature selection and view planning.pdf
Robotics and Autonomous Systems 84 (2016) 31–47
Contents lists available at ScienceDirect
Robotics and Autonomous Systems
journal homepage: /locate/robot
Active multi-view object recognition: A unifying view on online feature selection and view planning
Christian Potthast ?, Andreas Breitenmoser, Fei Sha, Gaurav S. Sukhatme
University of Southern California, Department of Computer Science, Los Angeles, CA 90089, USA
highlights
? 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.
article info
Article history: Received 26 May 2015 Received in revised form 14 January 2016 Accepted 27 June 2016 Available online 4 July 2016
Keywords: Viewpoint selection Feature selection Multi-view object recognition Information-theory Active perception Object change detection
abstract
Many robots are limited in their operating capabilities, both computational and energy-wise. A strong desire exists to keep computation cost and energy consumption to a minimum when executing tasks like object recognition with a mobile robot. Adaptive action selection is a paradigm, offering great flexibility in trading off the cost of acquiring information against making robust and reliable inference under uncertainty. In this paper, we study active multi-view object recognition and describe an informationtheoretic framework that combines and unifies two common techniques: online feature selection for reducing computational costs and view planning for resolving ambiguities and occlusions. Our algorithm adaptively chooses between the two strategies of either selecting only the features that are most informative to th
您可能关注的文档
- A FEM-based study on the influence of skewness and kurtosis surface texture parameters in human dental occlusal contact.pdf
- A field measurement method for large objects based on a multi-view stereo vision system.pdf
- A finite element approach for the line-to-line contact interaction of thin beams with arbitrary orientation.pdf
- A finite element framework for modeling internal frictional contact in three-dimensional fractured media using unstructured tetrahedral meshes.pdf
- A fixed-bandwidth view of the pre-asymptotic inference for kernel smoothing with time series data.pdf
- A flexible architecture for multi-view 3DTV based on uncalibrated cameras.pdf
- A generalized form of context-dependent psychophysiological interactions (gPPI) A comparison to standard approaches.pdf
- A generic contact detection framework for cylindrical particles in discrete element modelling.pdf
- A genomic view of short tandem repeats.pdf
- A genomic view of the peopling of the Americas.pdf
- Activity of a melimine derived peptide Mel4 against Stenotrophomonas, Delftia, Elizabethkingia, Burkholderia and biocompatibility as a contact lens coating.pdf
- Adaptive early termination mode decision for 3D-HEVC using inter-view and spatio-temporal correlations.pdf
- Adaptive multi-view feature selection for human motion retrieval.pdf
- Adaptive multi-view selection for semi-supervised emotion recognition of posts in online student community.pdf
- Adhesive and adhesiveless contact mechanics of elastic layers on slightly wavy rigid substrates.pdf
- Adhesive Contact Algorithm for MPM and its Application to the Simulation of Cone Penetration in Clay.pdf
- Adhesive contact between a rigid spherical indenter and an elastic multi-layer coated substrate.pdf
- Adhesive contact between dissimilar cylinders subject to a temperature difference.pdf
- Adhesive contact of a power-law graded elastic half-space with a randomly rough rigid surface.pdf
- Adjust your view! Wing-mirror settings influence distance estimations and lane-change decisions.pdf
文档评论(0)