SIA OpenIR  > 空间自动化技术研究室
An Occlusion-Aware Framework for Real-Time 3D Pose Tracking
Fu ML(付明亮)1,2; Leng YQ(冷雨泉)3; Luo HT(骆海涛)1; Zhou WJ(周维佳)1
作者部门空间自动化技术研究室
关键词Pose Tracking Occlusion Handling Online Rendering Motion Compensation
发表期刊Sensors (Switzerland)
ISSN1424-8220
2018
卷号18期号:8页码:1-20
收录类别SCI ; EI
EI收录号20183505743776
WOS记录号WOS:000445712400334
产权排序1
资助机构National Science Foundation of China
摘要

Random forest-based methods for 3D temporal tracking over an image sequence have gained increasing prominence in recent years. They do not require object’s texture and only use the raw depth images and previous pose as input, which makes them especially suitable for textureless objects. These methods learn a built-in occlusion handling from predetermined occlusion patterns, which are not always able to model the real case. Besides, the input of random forest is mixed with more and more outliers as the occlusion deepens. In this paper, we propose an occlusion-aware framework capable of real-time and robust 3D pose tracking from RGB-D images. To this end, the proposed framework is anchored in the random forest-based learning strategy, referred to as RFtracker. We aim to enhance its performance from two aspects: integrated local refinement of random forest on one side, and online rendering based occlusion handling on the other. In order to eliminate the inconsistency between learning and prediction of RFtracker, a local refinement step is embedded to guide random forest towards the optimal regression. Furthermore, we present an online rendering-based occlusion handling to improve the robustness against dynamic occlusion. Meanwhile, a lightweight convolutional neural network-based motion-compensated (CMC) module is designed to cope with fast motion and inevitable physical delay caused by imaging frequency and data transmission. Finally, experiments show that our proposed framework can cope better with heavily-occluded scenes than RFtracker and preserve the real-time performance.

语种英语
WOS类目Chemistry, Analytical ; Electrochemistry ; Instruments & Instrumentation
关键词[WOS]OBJECT TRACKING ; LIBRARY
WOS研究方向Chemistry ; Electrochemistry ; Instruments & Instrumentation
资助项目National Science Foundation of China[51505470]
引用统计
文献类型期刊论文
条目标识符http://ir.sia.cn/handle/173321/22395
专题空间自动化技术研究室
通讯作者Fu ML(付明亮)
作者单位1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.University of Chinese Academy of Sciences, Beijing 100049, China
3.Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China
推荐引用方式
GB/T 7714
Fu ML,Leng YQ,Luo HT,et al. An Occlusion-Aware Framework for Real-Time 3D Pose Tracking[J]. Sensors (Switzerland),2018,18(8):1-20.
APA Fu ML,Leng YQ,Luo HT,&Zhou WJ.(2018).An Occlusion-Aware Framework for Real-Time 3D Pose Tracking.Sensors (Switzerland),18(8),1-20.
MLA Fu ML,et al."An Occlusion-Aware Framework for Real-Time 3D Pose Tracking".Sensors (Switzerland) 18.8(2018):1-20.
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
An Occlusion-Aware F(4208KB)期刊论文出版稿开放获取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
[Fu ML(付明亮)]的文章
[Leng YQ(冷雨泉)]的文章
[Luo HT(骆海涛)]的文章
百度学术
百度学术中相似的文章
[Fu ML(付明亮)]的文章
[Leng YQ(冷雨泉)]的文章
[Luo HT(骆海涛)]的文章
必应学术
必应学术中相似的文章
[Fu ML(付明亮)]的文章
[Leng YQ(冷雨泉)]的文章
[Luo HT(骆海涛)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: An Occlusion-Aware Framework for Real-Time 3D Pose Tracking.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。