CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Fast depth extraction from a single image
He, Lei1; Dong, Qiulei1; Wang, Guanghui2
2016-11-14
发表期刊INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS
卷号13期号:1页码:1-10
文章类型Article
摘要Predicting depth from a single image is an important problem for understanding the 3-D geometry of a scene. Recently, the nonparametric depth sampling (Depth Transfer) has shown great potential in solving this problem, and its two key components are a Scale Invariant Feature Transform (SIFT) flow-based depth warping between the input image and its retrieved similar images and a pixel-wise depth fusion from all warped depth maps. In addition to the inherent heavy computational load in the SIFT flow computation even under a coarse-to-fine scheme, the fusion reliability is also low due to the low discriminativeness of pixel-wise description nature. This article aims at solving these two problems. First, a novel sparse SIFT flow algorithm is proposed to reduce the complexity from subquadratic to sublinear. Then, a reweighting technique is introduced where the variance of the SIFT flow descriptor is computed at every pixel and used for reweighting the data term in the conditional Markov random fields. Our proposed depth transfer method is tested on the Make3D Range Image Data and NYU Depth Dataset V2. It is shown that, with comparable depth estimation accuracy, our method is 2-3 times faster than the Depth Transfer.
关键词Depth Extraction Single Image Sparse Sift Flow
WOS标题词Science & Technology ; Technology
DOI10.1177/1729881416663370
收录类别SCI
语种英语
项目资助者Strategic Priority Research Program of the Chinese Academy of Sciences(XDB02070002) ; National Natural Science Foundation of China(61421004 ; 61333015 ; 61573351 ; 61283282)
WOS研究方向Robotics
WOS类目Robotics
WOS记录号WOS:000394814200001
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/12442
专题模式识别国家重点实验室_机器人视觉
通讯作者Dong, Qiulei
作者单位1.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
2.Univ Kansas, Dept Elect Engn & Comp Sci, Lawrence, KS 66045 USA
推荐引用方式
GB/T 7714
He, Lei,Dong, Qiulei,Wang, Guanghui. Fast depth extraction from a single image[J]. INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,2016,13(1):1-10.
APA He, Lei,Dong, Qiulei,&Wang, Guanghui.(2016).Fast depth extraction from a single image.INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,13(1),1-10.
MLA He, Lei,et al."Fast depth extraction from a single image".INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 13.1(2016):1-10.
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
Fast depth extractio(2922KB)期刊论文作者接受稿开放获取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
[He, Lei]的文章
[Dong, Qiulei]的文章
[Wang, Guanghui]的文章
百度学术
百度学术中相似的文章
[He, Lei]的文章
[Dong, Qiulei]的文章
[Wang, Guanghui]的文章
必应学术
必应学术中相似的文章
[He, Lei]的文章
[Dong, Qiulei]的文章
[Wang, Guanghui]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Fast depth extraction from a single image.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。