| 遗失目标的实时检测算法 |
| |
| 引用本文： | 吴明军,彭先蓉. 遗失目标的实时检测算法[J]. 光电工程, 2009, 36(7). DOI: 10.3969/j.issn.1003-501X.2009.07.007 |
| |
| 作者姓名： | 吴明军 彭先蓉 |
| |
| 作者单位： | 中国科学院光电技术研究所,成都,610209;中国科学院研究生院,北京,100039;中国科学院光电技术研究所,成都,610209 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | 针对视频安全监控问题,提出一种实时的遗失目标检测算法.首先,帧间差分用于获取像素级运动特性,并构造双重背景用于检测双重前景.而后,将像素级特性及双重前景综合以维持双重背景的更新.最后,通过累加证据图像来处理实际应用中的虚警和遮挡问题并证实遗失目标.在不同视频序列下的实验表明该算法能够有效地从嘈杂的场景中检测出遗失目标.此外,对于352x288的序列而言,该算法的运行速度达到约54帧/s,能够满足实时的监控任务需求.
|
| 关 键 词： | 视频监控 遗失目标检测 背景更新 证据图像 实时处理 |
A Real-time Method for Detecting Abandoned Object |
| |
| WU Ming-jun,PENG Xian-rong. A Real-time Method for Detecting Abandoned Object[J]. Opto-Electronic Engineering, 2009, 36(7). DOI: 10.3969/j.issn.1003-501X.2009.07.007 |
| |
| Authors: | WU Ming-jun PENG Xian-rong |
| |
| Affiliation: | WU Ming-jun1,2,PENG Xian-rong1(1.Institute of Optics and Electronics,Chinese Academy of Sciences,Chengdu 610209,China,2.Graduate School of Chinese Academy of Sciences,Beijing 100039,China) |
| |
| Abstract: | To solve the problem of video-based security surveillance,a real-time method for abandoned object detection is proposed.First,frame-to-frame difference is used to obtain the pixel-wise properties of motion,and two backgrounds are constructed to detect dual foregrounds.Then,the pixel-wise properties and both foregrounds are integrated to maintain the dual backgrounds.Since the false alarms and occlusions necessarily occur and degrade the detection performance in practical applications,an evidence image is ag... |
| |
| Keywords: | video surveillance abandoned object detection background update evidence image real-time processing |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
