中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
机构
采集方式
_filter
_filter
_filter
筛选

浏览/检索结果: 共4条,第1-4条 帮助

条数/页: 排序方式:
Interaction semantic segmentation network via progressive supervised learning 期刊论文  OAI收割
MACHINE VISION AND APPLICATIONS, 2024, 卷号: 35, 期号: 2
作者:  
Zhao, Ruini;  Xie, Meilin;  Feng, Xubin;  Guo, Min;  Su, Xiuqin
  |  收藏  |  浏览/下载:21/0  |  提交时间:2024/03/15
Unsupervised Transformer Boundary Autoencoder Network for Hyperspectral Image Change Detection 期刊论文  OAI收割
REMOTE SENSING, 2023, 卷号: 15, 期号: 7
作者:  
Liu, Song;  Li, Haiwei;  Wang, Feifei;  Chen, Junyu;  Zhang, Geng
  |  收藏  |  浏览/下载:29/0  |  提交时间:2023/05/06
视频中的人体跟踪和行为识别方法研究 学位论文  OAI收割
工学博士, 中国科学院自动化研究所: 中国科学院研究生院, 2012
作者:  
王恒
收藏  |  浏览/下载:98/0  |  提交时间:2015/09/02
Partial occlusion detection of object boundary (EI CONFERENCE) 会议论文  OAI收割
2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009, May 5, 2009 - May 7, 2009, Singapore, Singapore
作者:  
Zhang J.;  Zhang K.;  Zhang K.;  Zhang K.;  Zhang K.
收藏  |  浏览/下载:35/0  |  提交时间:2013/03/25
Partial occlusion is a difficult problem in computer vision since whether the object is changed or occluded is ambiguous  especially when distinguishing it only from the object boundary. In this paper  we proposed a novel idea to solve this problem by taking shape matching as a morphing processing. A mass-spring model is constructed from the point set which is sampled from a template (or reference) object boundary by moving it to a target object which is deformed and/or occluded. From the morphing processing  sufficient information can be obtained and an accurate detection of occlusion is performed. By using of the proposed method  the application scope of occlusion detection is expanded while other method cannot be performed which need color  texture  or motion information. The experiments performed on synthetic and real world images proved the satisfactory performance of the proposed method. 2009 IEEE.