跳到主要导航 跳到搜索 跳到主要内容

Dense optical flow estimation from RGB-D

  • Paderborn University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Optical flow is a key problem in computer vision with tremendous potential applications in many fields, such as action recognition, autonomous navigation and manipulation. In this paper, we propose a dense optical flow estimation approach for objects of interest. In order to improve the accuracy of the optical flow estimation, the intensity and depth data from the RGB-D sensor are used for doing object segmentation. Afterwards, a homography based method assuming the surface to be planar is applied to obtain dense optical flow for each segment. Several experiments have been performed to evaluate the proposed method. The results demonstrate the validity of our approach.

源语言英语
主期刊名Proceedings - 8th International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2018
编辑Jun-Bao Li
出版商Institute of Electrical and Electronics Engineers Inc.
328-333
页数6
ISBN(电子版)9781538682463
DOI
出版状态已出版 - 7月 2018
活动8th International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2018 - Harbin, Heilongjiang, 中国
期限: 19 7月 201821 7月 2018

出版系列

姓名Proceedings - 8th International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2018

会议

会议8th International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2018
国家/地区中国
Harbin, Heilongjiang
时期19/07/1821/07/18

学术指纹

探究 'Dense optical flow estimation from RGB-D' 的科研主题。它们共同构成独一无二的学术指纹。

引用此