计算机科学 ›› 2015, Vol. 42 ›› Issue (5): 286-288.doi: 10.11896/j.issn.1002-137X.2015.05.058
范文超,李晓宇,魏 凯,陈兴林
FAN Wen-chao, LI Xiao-yu, WEI Kai and CHEN Xing-lin
摘要： 运动目标检测是实现目标跟踪、视频监控的基础。针对基于高斯混合模型的运动目标检测算法的不足,提出了一种基于分块思想和高斯模型个数自适应的改进高斯混合算法。利用对视频图像分块的思想,在提高目标检测效率的同时,实现对视频的滤波处理；并利用高斯混合模型中高斯分布个数自适应操作来降低算法复杂度,提高运动目标检测的速度。实验结果表明:该算法比传统高斯混合模型运动目标检测算法具有更快的检测速度和更好的检测效果,并降低了检测噪声,能有效地检测运动目标,适用于运动目标的实时检测。
| [1] 夏永泉,李卫丽,甘勇,等.智能视频监控中的运动目标检测技术研究[J].通信技术,2009(6):185-187 [2] Zhong Y,Jain A K,Dubuisson-Jolly M P.Object tracking using deformable templates[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(5):544-549 [3] 万缨,韩毅,卢汉清.运动目标检测算法的探讨[J].计算机仿真,2006,23(10):221-226 [4] Wang L,Wang L,Wen M,et al.Background subtraction using incremental subspace learning[C]∥IEEE International Confe-rence on Image Processing,2007(ICIP 2007).IEEE,2007,5:45-48 [5] 刘贵喜,邵明礼,刘先红,等.真实场景下视频运动目标自动提取方法[J].光学学报,2006,26(8):1150-1155 [6] 王勇,谭毅华,田金文.基于阴影消除和混合高斯模型的视频分割算法[J].光电工程,2008,35(3):21-25 [7] 李明,赵勋杰.改进的基于高斯混合模型的运动目标检测算法[J].计算机工程与应用,2011,47(8):204-206 [8] 王永忠,梁彦,潘泉,等.基于自适应混合高斯模型的时空背景建模[J].自动化学报,2009(4):371-378 [9] Blanding W R,Wille P K,Bar-Shalom Y.Multiple targets tracking using maximum likelihood probabilistic data association[C]∥IEEE Aerospace Conference Proceedings,2007 IEEE Aerospace Conference Digest.2007:416-445 [10] Lei B,Xu L Q.Real-time outdoor video surveillance with robust foreground extraction and object tracking via multi-state transition management[J].Pattern Recognition Letters,2006,27(15):1816-1825 [11] Martel-Brisson N,Zaccarin A.Moving cast shadow detectionfrom a Gaussian mixture shadow model[C]∥Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2005:643-648 [12] Xue J S G,Song L.Dynamic background subtraction based onspatial extended center-symmetric local binary pattern[C]∥IEEE International Conference on Multimedia and Expo.2010:1050-1054 [13] Socolinsky D A.Design and deployment of visible-thermal biometric surveillance systems[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2007(CVPR’07).2007:1-2 |
| No related articles found! |
|
||
首页