3D Attention-Driven Depth Acquisition for Object Identification
文献类型：期刊论文
| 作者 | Kai Xu; Yifei Shi; Lintao Zheng; Junyu Zhang; Min Liu; Hui Huang; Hao Su; Daniel Cohen-Or; Baoquan Chen |
| 刊名 | ACM TRANSACTIONS ON GRAPHICS
 |
| 出版日期 | 2016 |
| 英文摘要 | We address the problem of autonomously exploring unknown objectsinascenebyconsecutivedepthacquisitions. Thegoalistoreconstructthescenewhileonlineidentifyingtheobjectsfromamong a large collection of 3D shapes. Fine-grained shape identification demands a meticulous series of observations attending to varying viewsandpartsoftheobjectofinterest. Inspiredbytherecentsuccessofattention-basedmodelsfor2Drecognition,wedevelopa3D Attention Model that selects the best views to scan from, as well as themostinformativeregionsineachviewtofocuson,toachieveefficientobjectrecognition. Theregion-levelattentionleadstofocusdrivenfeatureswhicharequiterobustagainstobjectocclusion. The attention model, trained with the 3D shape collection, encodes the temporal dependencies among consecutive views with deep recurrent networks. This facilitates order-aware view planning accounting for robot movement cost. In achieving instance identification, the shape collection is organized into a hierarchy, associated with pre-trainedhierarchicalclassifiers. Theeffectivenessofourmethod isdemonstratedonanautonomousrobot(PR)thatexploresascene and identifies the objects to construct a 3D scene model. |
| 收录类别 | SCI |
| 原文出处 | http://dl.acm.org/citation.cfm?id=2980224 |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/10172]  |
| 专题 | 深圳先进技术研究院_数字所 |
| 作者单位 | ACM TRANSACTIONS ON GRAPHICS |
| 推荐引用方式 GB/T 7714 | Kai Xu,Yifei Shi,Lintao Zheng,et al. 3D Attention-Driven Depth Acquisition for Object Identification[J]. ACM TRANSACTIONS ON GRAPHICS,2016. |
| APA | Kai Xu.,Yifei Shi.,Lintao Zheng.,Junyu Zhang.,Min Liu.,...&Baoquan Chen.(2016).3D Attention-Driven Depth Acquisition for Object Identification.ACM TRANSACTIONS ON GRAPHICS. |
| MLA | Kai Xu,et al."3D Attention-Driven Depth Acquisition for Object Identification".ACM TRANSACTIONS ON GRAPHICS (2016). |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。