一种高精度视频目标检测与分割新方法

赵文哲; 秦世引

一种高精度视频目标检测与分割新方法

北京航空航天大学自动化科学与电气工程学院, 北京 100191

基金项目: 国家高技术研究发展(863)计划资助项目(2008AA12A200); 国际科技合作资助项目(2007DFA11530); 国家自然科学基金资助项目(60875072)

详细信息

作者简介:
赵文哲(1979-),女,内蒙古赤峰人,博士生,zwz@asee.buaa.edu.cn.

中图分类号: TP 391.41
计量
- 文章访问数: 3203
- HTML全文浏览量: 155
- PDF下载量: 1480
- 被引次数: 0
出版历程
- 收稿日期: 2010-05-10
- 网络出版日期: 2010-12-30

Novel approach to video object detection and precise segmentation

School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 根据动态视频场景与多目标检测的应用需求,提出了一种变分光流场与mean shift图像分割相结合的高精度运动目标检测与分割新方法.依据动态场景多运动目标检测的约束条件提出变分光流场优化计算模型,并给出其数值解法.在此基础上提出结合mean shift的高精度运动目标检测与分割算法,此方法对摄像机运动和静止情况都适合,能够进行同一场景中多个运动目标的高精度检测,并且不需要事先的学习和人工干预,具有通用性.
- 机器视觉 /
- 运动分析 /
- 目标检测 /
- 运动分割 /
- 变分光流场 /
- 均值平移
Abstract: Taking into account multiple objects detection in dynamic video scene, a method based on variational optimization of optical flow and mean shift was proposed. A variational optimization model for optical flow field was built according to constraints of multiple objects detection in dynamic video scene. The proper numerical solution was then given by this kind of optimizing calculus of variation. With the optical flow optimized solution, a high precise segmentation method was proposed. This approach can be used in the situations of both motion camera and stationary one. Meanwhile it can also be used to detect several targets in dynamic scenes simultaneously without learning in advance and manual intervention so as to be implemented automatically. A lot of experiment results validate the effectiveness of the proposed method.
- machine vision /
- motion analysis /
- target detection /
- motion segmentation /
- variational optical flow field /
- mean shift

HTML全文

参考文献(1)

[1] Yilmaz A,Javed O,Shah M.Object tracking:a survey [J].ACM Computing Survey,2006:38(4):Article 13 [2] Stauffer C,Grimson W L.Learning patterns of activity using real-time tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-767 [3] 赵文哲,秦世引.视频运动目标检测方法的对比分析[J].科技导报,2009,27(10):64-70 Zhao Wenzhe,Qin Shiyin.Comparative study on detection methods for video motion targets [J].Science & Technology Review,2009,27(10):64-70 (in Chinese) [4] Viola P,Jones M,Snow D.Detecting pedestrians using patterns of motion and appearance[J].International Journal of Computer Vision,2005,63(2):153-161 [5] Horn B K,Schunck B G.Determining optical flow[J].Artificial Intelligence,1981,17:185-203 [6] Kim S,Han J,Kim J.An efficient scheme for motion estimation using multireference frames in H264/AVC[J].IEEE Transaction on Multimedia,2006,8(3):457-466 [7] Babu V R,Ramakrishnan K R.Video object segmentation-a compressed domain approach[J].IEEE Transactions on Circuit and Systems for Video Technology,2004,14(4):462-474 [8] Ewerth R,Schwalb M,Tessmann P,et al.Segmenting moving objects in MPEG videos in the presence of camera motion //Cucchiara Rita.14^th International Conference on Image Analysis and Processing.Washington DC:IEEE Computer Society Press,2007:819-824 [9] Brox T,Malik J.Large displacement optical flow:descriptor matching in variational motion estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(3):402-415. [10] Barron J L,Fleet D J,Beauchemin S S.Performance of optical flowtechniques[J].International Journal of Computer Vision,1994,12(1):43-77 [11] Galvin B,McCane B,Novins K,et al.Recovering motion fields:An analysis of eight optical flow algorithms //John N Carter.British Machine Vision Conference.London:British Library,1998:195-204 [12] Bruhn A.Variational optic flow computation,accurate modelling and efficient numerics .Saarbr ucken:Department of Mathematics and Computer Science,Saarland University,2006 [13] Brox T,Bruhn A,Papenberg N,et al.High accuracy optical flow estimation based on a theory for warping [J].International Journal of Computer Vision,2006,67(2):141-158 [14] Sand P,Teller S.Particle video:long-range motion estimation using point trajectories [J].International Journal of Computer Vision,2008,80(1):72-91 [15] Zhao Wenzhe,Qin Shiyin.A new method for target detection based on analysis of motion vector field in dynamic video scene //Liu Jianguo.Proceedings of the SPIE.Bellingham:SPIE Press,2009:74951C-74951C-7 [16] 邹谋炎.反卷积和信号复原[M].北京:国防工业出版社,2001:249-250 Zou Mouyan.Deconvolution and signal recovery[M].Beijing:National defense industry Press,2001:249-250 (in Chinese)

施引文献

资源附件(0)

访问统计