Refereed conference paper presented and published in conference proceedings
香港中文大学研究人员 ( 现职)
| 颜庆义教授 (电子工程学系) |
全文
| 没有全文档案提供 |
引用次数
Web of Sciencehttp://aims.cuhk.edu.hk/converis/portal/Publication/0WOS source URL
其它资讯
摘要In this paper, we address the problem of dense depth map generation from two successive image frames in a video. We first recover the camera motion from the observable normal flow pattern using our previously proposed apparent flow constraints. Once the camera motion is estimated, sparse depth data can be directly recovered from the flow pattern. We utilize a hierarchical approach to generate an initial dense depth map from the sparse depth data. This depth map is further enhanced through the refinement of the associated optical flow field in a variational framework. Experimental results show that the proposed method can provide high-quality depth maps. We also have a faster computational time than the conventional optical flow approach.
着者Hui TW, Ngan KN
会议名称IEEE International Conference on Image Processing (ICIP)
会议开始日27.1http://aims.cuhk.edu.hk/converis/portal/Publication/0.2http://aims.cuhk.edu.hk/converis/portal/Publication/014
会议完结日3http://aims.cuhk.edu.hk/converis/portal/Publication/0.1http://aims.cuhk.edu.hk/converis/portal/Publication/0.2http://aims.cuhk.edu.hk/converis/portal/Publication/014
会议地点Paris
会议国家法国
详细描述organized by IEEE,
出版年份2http://aims.cuhk.edu.hk/converis/portal/Publication/014
月份1
日期1
出版社IEEE
页次3837 - 3841
电子国际标準书号978-1-4799-5751-4
国际标準期刊号1522-488http://aims.cuhk.edu.hk/converis/portal/Publication/0
语言英式英语
关键词Camera motion; depth map; normal flow; optical flow
Web of Science 学科类别Computer Science; Computer Science, Theory & Methods; Engineering; Engineering, Electrical & Electronic; Imaging Science & Photographic Technology
