计算机科学 ›› 2015, Vol. 42 ›› Issue (Z11): 199-202.
盛家川,杨巍
SHENG Jia-chuan and YANG Wei
摘要: 为了能够从视频序列中快速准确地检测运动目标,在混合高斯背景差分法的基础上引入Grabcut算法,提出了一种新的运动目标检测G-GMM(Grabcut-Gaussian Mixture Model)算法。首先通过混合高斯模型背景差分法提取运动目标初始二值轮廓,构建其最小的外接矩形;然后初始化矩形内图像信息,寻找潜在前景区域;最后采用迭代算法实现最优化分割,得到准确的运动目标轮廓。实验结果表明,在静止摄像机户外视频监控系统中,提出算法具有较高的准确性和鲁棒性,对刚性和非刚性两类目标都具有较好的检测结果。
[1] Khare M,Srivastava R K,Khare A.Moving object segmentation in Daubechies complex wavelet domain[J].Signal Image and Video Processing,2015,9(3):635-650 [2] 文嘉俊,徐勇,战荫伟.基于AdaBoost和帧间特征的人数统计[J].中国图象图形学报,2014,16(9):1729-1735 [3] 刘赏,董林芳.人群运动方向异常检测算法[J].计算机科学,2013,40(11A):337-340 [4] Trulls E,Tsogkas S,Kokkinos I,et al.Segmentation-aware deformable part models[C]∥IEEE International Conference on Computer Vision and Pattern Recognition(CVPR).2014:168-175 [5] 张欢,安国成,张凤军,等.多颜色空间融合的人体检测算法研究[J].中国图象图形学报,2011,16(10):1944-1950 [6] Ramirez-Quintana J A,Chacon-Murguia M I.Self-adaptiveSUM-CNN neural system for dynamic object detection in normal and complex scenarios[J].Pattern Recognition,2015,48(4):1137-1149 [7] Stauffer C,Grimson W E L.Adaptive background mixture mo-dels for real time tracking[C]∥IEEE International Conference on Computer Vision and Pattern Recognition(CVPR).1999:246-252 [8] Stauffer C,Grimson W E L.Learning patterns of activity using real-time tracking[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2000,22(8):747-757 [9] 程全,马军勇.基于改进高斯混合模型的运动目标检测方法[J].计算机科学,2014,41(7):318-321 [10] Zhao Qin-pei,Ville H,Ismo K.Random swap EM algorithm for Gaussian Mixture Models[J].Pattern Recognition Letters,2012,33(16):2120-2126 [11] Nazre B,Rama R.Detection and inpainting of facial wrinklesusing texture orientation fields and markov random field mode-ling[J].IEEE Transactions on Image Processing,2014,23(9):3773-3788 [12] 周良芬,何建农.基于GrabCut改进的图像分割算法[J].计算机应用,2013,33(1):49-52 [13] Tao Wen-bing,Li Kun-qian,Sun Kun.SaCoseg:object coseg-mentation by shape conformability[J].IEEE Transactions on Image Processing,2015,24(3):943-955 [14] 周爱民,张青富,张桂戌.一种基于混合高斯模型的多目标进化算法[J].软件学报,2014,25(5):913-928 [15] Zhu H,Ding M,Li Y.Gibbs phenomenon for fractional Fourier series[J].IET Signal Processing,2011,5(8):728-738 [16] Chen Ning,Ding Fei.Flame object segmentation by an improved frame difference method[C]∥Third International Conference on Digital Manufacturing and Automation(ICDMA).2012:422-425 [17] Barnich O,Droogenbroeck M V.Vibe:a powerful random technique to estimate the background in video sequences[C]∥IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).2009:945-948 [18] Mofaddel M A,Abd-Elhafiez W M.Fast and accurate approa-ches for image and moving object segmentation[C]∥International Conference on Computer Engineering & Systems(ICCES).2011:252-259 |
No related articles found! |
|