Deep learning of volumetric representation for 3D object recognition
文献类型：会议论文
| 作者 | Liu HS(刘洪森); Cong Y(丛杨) ; Tang YD(唐延东)
|
| 出版日期 | 2017 |
| 会议名称 | 32nd Youth Academic Annual Conference of Chinese Association of Automation, YAC 2017 |
| 会议日期 | May 19-21, 2017 |
| 会议地点 | Hefei, China |
| 关键词 | Deep Learning Volumetric Representation Hough Forest and 3D Object Recognition |
| 页码 | 663-668 |
| 通讯作者 | Liu HS(刘洪森) |
| 中文摘要 | Robust 3D object detection and pose estimation is still a big challenging for robot vision. In this paper, we propose a new framework for 3D object detection and pose estimation. Rather than using RGB-D image as the original data, we propose to use volumetric representation with the help of unsupervised deep learning network to extract low dimensional feature from 3D point cloud directly. The volumetric representation can not only eliminate the dense scale sampling for offline model training, but also reduce the distortion by mapping the 3D shape to 2D plane and overcome the dependence on texture information. Depending on the Hough forest, we can achieve multi-object detection and pose estimation simultaneously. In compare with the state-of-the-arts using public datasets, we justify the effectiveness of our proposed method. |
| 收录类别 | EI ; CPCI（ISTP） |
| 产权排序 | 1 |
| 会议录 | Proceedings - 2017 32nd Youth Academic Annual Conference of Chinese Association of Automation, YAC 2017
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | New York |
| 语种 | 英语 |
| ISBN号 | 9781538629017 |
| WOS记录号 | WOS:000425862800126 |
| 源URL | [http://ir.sia.cn/handle/173321/20820]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 作者单位 | State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shenyang, 110016, China |
| 推荐引用方式 GB/T 7714 | Liu HS,Cong Y,Tang YD. Deep learning of volumetric representation for 3D object recognition[C]. 见:32nd Youth Academic Annual Conference of Chinese Association of Automation, YAC 2017. Hefei, China. May 19-21, 2017. |
入库方式： OAI收割
来源：沈阳自动化研究所
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。