计算机科学 ›› 2016, Vol. 43 ›› Issue (2): 302-306.doi: 10.11896/j.issn.1002-137X.2016.02.063
孙焘,陈康睿
SUN Tao and CHEN Kang-rui
摘要： 视频图像分割是图像处理领域的一个热门问题。在传统分割算法的基础上,提出了一种新的无监督的视频分割算法。该算法采用超像素对运动前景进行表示,定义联接权概念来描述超像素属于同一物体的可能性,并利用当前帧的静态特征与前后帧的关联特征进行联接权计算。为优化超像素间匹配关系的搜索,算法引入了超像素颜色特征匹配约束与运动关联性匹配约束的机制。分别在简单场景和复杂场景进行了视频分割实验,简单场景下,算法保证了较高的召回率与稳定的准确率；复杂场景下,算法完成了人群中单个人的切分。大量实验结果表明,该算法能够实现视频图像的分割,并且能有效解决过分割问题。
| [1] Vicente S,Rother C,Kolmogorov V.Object cosegmentation[C]∥2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2011:2217-2224 [2] Lee Y J,Kim J,Grauman K.Key-segments for video object segmentation[C]∥2011 IEEE International Conference on Computer Vision (ICCV).IEEE,2011:1995-2002 [3] Liu Y.A video object segmentation algorithm based on region selection[J].Science Technology and Engineering,2014,4(6):211-217(in Chinese) 刘毅.一种基于区域选择的视频对象分割算法[J].科学技术与工程,2014,14(6):211-217 [4] Trichet R,Nevatia R.Video segmentation and feature co-occurrences for activity classification[C]∥2014 IEEE Winter Conference on Applications of Computer Vision (WACV).IEEE,2014:385-392 [5] Sun D,Roth S,Black M J.Secrets of optical flow estimation and their principles[C]∥2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2010:2432-2439 [6] Kim K,Chalidabhongse T H,Harwood D,et al.Real-time foreground-background segmentation using codebook model[J].Real-time imaging,2005,11(3):172-185 [7] Zivkovic Z.Improved adaptive Gaussian mixture model for background subtraction[C]∥Proceedings of the 17th International Conference on Pattern Recognition,2004(ICPR 2004).IEEE,2004,2:28-31 [8] Barnich O,Van Droogenbroeck M.ViBe:A universal back-ground subtraction algorithm for video sequences[J].IEEE Transactions on Image Processing,2011,20(6):1709-1724 [9] Achanta R,Shaji A,Smith K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282 [10] http://www.sfu.ca/~ibajic/datasets.html [11] Chen Y M,Bajic I V,Saeedi P.Moving region segmentationfrom compressed video using global motion estimation and Markov random fields[J].IEEE Transactions on Multimedia,2011,13(3):421-431 [12] Zeng W,Du J,Gao W,et al.Robust moving object segmentation on H.264/AVC compressed video using the block-based MRF model[J].Real-Time Imaging,2005,11(4):290-299 [13] http://sida.rdg.ac.uk/pub |
| No related articles found! |
|
||
首页