Knowledge Commons of Institute of Automation,CAS
Key Observation Selection for Effective Video Synopsis | |
Zhu, Xiaobin; Liu, Jing![]() ![]() ![]() | |
2012 | |
会议名称 | 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012) |
会议录名称 | International Conference on Pattern Recognition (ICPR) |
页码 | 2528-2531 |
会议日期 | 2012 |
会议地点 | Lake Buena Vista (Orlando), Florida, USA |
摘要 | Millions of video surveillance cameras distribute around the world, and capture tremendous number of video data endlessly. Video browsing by frame is time consuming and inefficient, since needless information is abundant in the raw videos. Video synopsis is an ef- fective way to solve this problem by producing a short video abstraction, while keeping the essential activities of the original video. However, traditional video syn- opsis only eliminates redundancy in spatial and tempo- ral domain, while neglects redundancy in content do- main. However, too many observations will make syn- opsis video confusing and degrade synopsis efficiency. In this paper, we present a novel video synopsis method based on key observation selection. Key observation s- election is conducted for activity to eliminate content redundancy. We have demonstrated the effectiveness of our approach on real surveillance videos. |
关键词 | Effective Video Synopsis Key Observation Selection |
收录类别 | CPCI-T |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/4658 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Wang, Jinqiao |
推荐引用方式 GB/T 7714 | Zhu, Xiaobin,Liu, Jing,Wang, Jinqiao,et al. Key Observation Selection for Effective Video Synopsis[C],2012:2528-2531. |
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 | ||
Key observation sele(1465KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论