SIA OpenIR  > 机器人学研究室
Deep learning of directional truncated signed distance function for robust 3D object recognition
Liu HS(刘洪森); Cong Y(丛杨); Wang S(王帅); Fan BJ(范保杰); Tian DY(田冬英); Tang YD(唐延东)
作者部门机器人学研究室
会议名称2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017
会议日期September 24-28, 2017
会议地点Vancouver, Canada
会议主办者AIRA; Amazon; Bosch; Clearpath; et al.; Guangdong University of Technology
会议录名称IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems
出版者IEEE
出版地New York
2017
页码5934-5940
收录类别EI ; CPCI(ISTP)
EI收录号20180704807049
WOS记录号WOS:000426978205082
产权排序1
ISSN号2153-0858
ISBN号978-1-5386-2682-5
摘要In this paper, we develop a novel 3D object recognition algorithm to perform detection and pose estimation jointly. We focus on analyzing the advantages of the 3D point cloud relative to the RGB-D image and try to eliminate the unpredictability of output values that inevitably occurs in regression tasks. To achieve this, we first adopt the Truncated Signed Distance Function (TSDF) to encode the point cloud and extract low compact discriminative feature via unsupervised deep learning network. This approach can not only eliminate the dense scale sampling for offline model training but also reduce the distortion by mapping the 3D shape to the 2D plane and overcome the dependence on color cues. Then, we train a Hough forests to achieve multi-object detection and 6-DoF pose estimation simultaneously. In addition, we propose a robust multilevel verification strategy that effectively reduces the unpredictability of output values which occurs in the hough regression module. Experiments on public datasets demonstrate that our approach provides effective results comparable to the state-of-the-arts.
语种英语
引用统计
文献类型会议论文
条目标识符http://ir.sia.cn/handle/173321/21344
专题机器人学研究室
通讯作者Cong Y(丛杨)
作者单位1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China
2.University of Chinese Academy of Sciences, China
推荐引用方式
GB/T 7714
Liu HS,Cong Y,Wang S,et al. Deep learning of directional truncated signed distance function for robust 3D object recognition[C]//AIRA; Amazon; Bosch; Clearpath; et al.; Guangdong University of Technology. New York:IEEE,2017:5934-5940.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Deep learning of dir(1189KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Liu HS(刘洪森)]的文章
[Cong Y(丛杨)]的文章
[Wang S(王帅)]的文章
百度学术
百度学术中相似的文章
[Liu HS(刘洪森)]的文章
[Cong Y(丛杨)]的文章
[Wang S(王帅)]的文章
必应学术
必应学术中相似的文章
[Liu HS(刘洪森)]的文章
[Cong Y(丛杨)]的文章
[Wang S(王帅)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Deep learning of directional truncated signed distance function for robust 3D object recognition.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。