CASIA OpenIR  > 智能感知与计算研究中心
Learning the three factors of a non-overlapping multi-camera network topology
Xiaotang Chen; Kaiqi Huang; Tieniu Tan
2012
会议名称Chinese Conference on Pattern Recognition
会议录名称2012 5th Chinese Conference on Pattern Recognition
页码104–112
会议日期2012
会议地点China
摘要In this paper, we propose an unsupervised approach for learning the three factors of the topology of a non-overlapping multi-camera network, which are nodes, links, and transition time distributions. It is a cross-correlation based method. Different from previous methods, the proposed method can deal with large amounts of data without considering the size of time window. The connectivity between nodes is estimated based on the N-neighbor accumulated cross-correlations, as well as the transition time distribution for each link. Furthermore, integrated with similarity cues, the proposed method can be extended into weighted cross-correlation models for better performance. Experimental results both on simulated and real-life datasets demonstrate the effectiveness of the proposed method.
关键词Topology Recovering   transition Time Distribution   camera Network 
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12687
专题智能感知与计算研究中心
通讯作者Kaiqi Huang
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Xiaotang Chen,Kaiqi Huang,Tieniu Tan. Learning the three factors of a non-overlapping multi-camera network topology[C],2012:104–112.
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
CCPR2012-Learning th(433KB)会议论文 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
[Xiaotang Chen]的文章
[Kaiqi Huang]的文章
[Tieniu Tan]的文章
百度学术
百度学术中相似的文章
[Xiaotang Chen]的文章
[Kaiqi Huang]的文章
[Tieniu Tan]的文章
必应学术
必应学术中相似的文章
[Xiaotang Chen]的文章
[Kaiqi Huang]的文章
[Tieniu Tan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: CCPR2012-Learning the Three Factors of a Non-overlapping Multi-camera Network Topology.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。