热门
Flow Mosaicking: Real-time Pedestrian Counting without Scene-specific Learning
文献类型：会议论文
| 作者 | Cong Y(丛杨) ; Gong HF(龚海峰); Zhu SC(朱松纯); Tang YD(唐延东)
|
| 出版日期 | 2009 |
| 会议名称 | IEEE-Computer-Society Conference on Computer Vision and Pattern Recognition Workshops |
| 会议日期 | June 20-25, 2009 |
| 会议地点 | Miami Beach, FL |
| 页码 | 1093-1100 |
| 中文摘要 | In this paper, we present a novel algorithm based on flow velocity field estimation to count the number of pedestrians across a detection line or inside a specified region. We regard pedestrians across the line as fluid flow, and design a novel model to estimate the flow velocity field. By integrating over time, the dynamic mosaics are constructed to count the number of pixels and edges passed through the line. Consequentially, the number of pedestrians can be estimated by quadratic regression, with the number of weighted pixels and edges as input. The regressors are learned off line from several camera tilt angles, and have taken the calibration information into account. We use tilt-angle-specific learning to ensure direct deployment and avoid overfitting while the commonly used scene-specific learning scheme needs on-site annotation and always trends to overfitting. Experiments on a variety of videos verified that the proposed method can give accurate estimation under different camera setup in real-time. |
| 收录类别 | EI ; CPCI（ISTP） |
| 产权排序 | 1 |
| 会议主办者 | IEEE Comp Soc |
| 会议录 | CVPR: 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-4
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | NEW YORK |
| 语种 | 英语 |
| ISSN号 | 1063-6919 |
| ISBN号 | 978-1-4244-3992-8 |
| WOS记录号 | WOS:000279038000140 |
| 源URL | [http://ir.sia.cn/handle/173321/8717]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 推荐引用方式 GB/T 7714 | Cong Y,Gong HF,Zhu SC,et al. Flow Mosaicking: Real-time Pedestrian Counting without Scene-specific Learning[C]. 见:IEEE-Computer-Society Conference on Computer Vision and Pattern Recognition Workshops. Miami Beach, FL. June 20-25, 2009. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
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。