期刊文献+

基于两级时空随机取样的背景建模算法

Background Modeling Algorithm Based on Two-level Temporal-spatial Random Sampling
下载PDF
导出
摘要 目的为从发射场室外和航天器舱内等场景的监控视频中提取运动目标,本文提出两级时空随机取样背景建模算法。方法提出了一种全新的背景建模算法,算法通过时间和空间上随机取样的方式进行背景更新,并且通过负反馈的方式实时调整参数。在前景决策上采用基于像素点和基于区域分布两级决策方式进行,充分利用了连续图像序列时间和空间上的一致性和随机性。结果在真实场景和Change Detection数据库上的测试表明本方法提取的前景稳定、清晰,召回率等指标上得到更好的结果。结论通过本文提出的方法,可直接从监控视频中提取较清晰的运动前景,在发射场和未来飞行器监控系统中将有较好的应用前景。 Objective To propose a two-level temporal-spatial random sampling background modeling method al- gorithm for extracting moving objects from the surveillance videos of spacecraft and launching site. Method A novel background modeling algorithm was presented. In our algorithm, the background was updated through random temporal-spatial sampling. Parameters were dynamically adjusted according to the negative feedback information. The foreground decision was performed in a two-level decision manner based on pixels and region- al distribution, making full use of the temporal-spatial consistency and randomness of continuous image se- quence. Results The approach was evaluated on the real surveillance video and the database provided for the Change Detection Challenge. Experiments showed that compared with other modeling methods, better perform- ances could be achieved using the proposed algorithm. Conclusion With the background modeling algorithm, clear foreground directly extracted from the surveillance videos can be used for early-warning and action recog- nition from the surveillance videos of the spacecraft and launching site.
出处 《航天医学与医学工程》 CAS CSCD 北大核心 2014年第2期107-112,共6页 Space Medicine & Medical Engineering
基金 国家高技术研究发展计划(863计划)资助(2012AA011004) 国家自然科学基金资助(61071135) 国家科技支撑计划项目(2013BAK02B04)
关键词 时空随机采样 背景建模 前景检测 两级决策 temporal-spatial random sampling background modeling foreground detection two-leveldecision
  • 相关文献

参考文献9

  • 1Zivkovic Z. Improved adaptive gaussian mixture model forback- ground subtraction [ C ]. In Pattern Recognition, 2004. ICPR2004. Proceedings of the 17th International Conference, 2004:28-31.
  • 2Elgammal A, Harwood D, Davis L. Non-parametricmodel for- backgroundsubtraetion[ C]. Proceedings of the 6th European- Conference on Computer Vision, Dublin, Ireland, 2000 : 751- 767.
  • 3Kim K, Chalidabhongse TH, Harwood D, et al. Real-time fore- ground-backgroundsegmentation using codebook model[ J]. Re- al Timelmaging,2005,11 (3) : 172-185.
  • 4Barnich OM. Van Droogenbroeck. ViBe: A universal back- ground subtraction algorithmfor video sequences[J]. ImagePro- cessing, IEEE Transactions on, 2011,20(6) :1709-1724.
  • 5Hofmann M,Tiefenbacher P, Rigoll G. Background segmenta- tion with feedback : Thepixel-based adaptive segmenter [ C ]. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on, 2012:38-43.
  • 62012 CVPR Workshop: Motion and Change Detection Chal- lenge, http ://www. change detection, net.
  • 7Li L, Huang W, Gui YH, et al. Statistical modeling of com- plex backgrounds for foreground object detection [ J ]. Image Processing, IEEE Transactions on, 2004,13 ( 11 ) : 1459-1472.
  • 8Haines TSF, Xiang T. Background Subtraction with Dirichlet Processes[ C]. Proceedings of the 12th EuropeanConference on Computer Vision, Florence, Italy ,2012:99-113.
  • 9ADIV G. Determining three-dimensional motion and structure from optical flow generated by several moving objects [ J ]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1985, 7(4) :384-401.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部