
浏览全部资源
扫码关注微信
四川大学 电子信息学院,四川 成都,中国,610065
收稿日期:2010-11-17,
修回日期:2010-12-09,
网络出版日期:2011-04-06,
纸质出版日期:2011-04-06
移动端阅览
范小聪, 李大海, 王琼华, 刘曦, 张映权, 刘效勇. 基于背景重构的视频分割技术及应用[J]. 液晶与显示, 2011,26(2): 229-233
FAN Xiao-cong, LI Da-hai, WANG Qiong-hua, LIU Xi, ZHANG Ying-quan, LIU Xiao-yong. Video Object Segmentation Algorithm Based on Background Reconstruction and Its Application[J]. , 2011,26(2): 229-233
范小聪, 李大海, 王琼华, 刘曦, 张映权, 刘效勇. 基于背景重构的视频分割技术及应用[J]. 液晶与显示, 2011,26(2): 229-233 DOI: 10.3788/YJYXS20112602.0229.
FAN Xiao-cong, LI Da-hai, WANG Qiong-hua, LIU Xi, ZHANG Ying-quan, LIU Xiao-yong. Video Object Segmentation Algorithm Based on Background Reconstruction and Its Application[J]. , 2011,26(2): 229-233 DOI: 10.3788/YJYXS20112602.0229.
针对背景静止的立体视频提出了一种快速的基于背景重构的视频分割算法。先利用帧差法分别确定出左右视频的前景运动区域
再重构出该区域的背景图像
最后
通过视频图像和背景图像的对比来准确地提取运动前景。然后
先匹配左右图像序列的背景图像
并保存它们的匹配结果
再分别对各立体图像对的运动前景进行匹配。采用该方法将立体视频分割可以减少图像数据的传输量和储存空间;同时
视频分割之后再做匹配运算
减少了立体匹配的时间。
A fast video segmentation algorithm based on background reconstruction is proposed for stereo video with static backgrounds. Firstly
the moving foreground areas are found out by the frame difference respectively. And then
the backgrounds shaded by foreground areas are reconstructed. At last
the moving foregrounds could be separated by comparing the backgrounds information with the current frame images and it could achieve the segmentation accurately. After that
two background images reconstructed from the left and right video sequences are matched in the initialization and the parallax image is saved
so that only the foreground parallax images are necessary to be updated. Therefore
the proposed method can improve image compression ratio and reduce storage. Meanwhile
the time for stereo matching is also decreased.
Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV camera and lenses [J]. IEEE Journal of Robotics and Automation, 1987, 3(4): 323-344.[2] 何友兵,李大海,李良玉,等.彩色立体图像匹配算法研究 [J]. 液晶与显示 ,2007, 22(4): 417-422.[3] 张超, 王琼华, 李大海, 等.从平面图生成多视点自由立体显示视差图的研究 [J] .液晶与显示 ,2009, 24(2): 258-261.[4] 张浩,李大海,王琼华,等.自由立体显示拍摄系统中摄像机空间自由度的确定 [J] .液晶与显示 ,2010, 25(2): 287-291.[5] Barnard S T, Fischler M A. Computational stereo [J]. ACM Computing Surveys,1982, 14(4): 552-572.[6] 王世刚,林青,付庆兴,等.基于视差和帧差运动检测的立体视频对象提取与压缩编码 [J] .中国体视学与图像分析 ,2009, 14(1): 67-72.[7] Kim H, Choi S, Sohn K. Real-time depth reconstruction from stereo sequences [J]. Proc. of SPIE, 2005, 6016: 60160E(1-12).[8] Haritaoglu I, Harwood D, Davis L. Real-time surveillance of people and their activities [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830.[9] 李彬,刘冀伟,韩鸿哲,等.基于步态特征的快速身份识别方法 [J]. 计算机工程与应用 ,2004, 22(2): 60-62.[10] 夏侯玉娇,龚声蓉,刘纯平,等.结合Gaussian分布和LK光流法的视频对象分割算法 [J] .微电子学与计算机 ,2009, 26(6): 239-245.[11] 伏思华,张小虎.基于序列图像的运动目标实时检测方法 [J]. 光学技术 ,2004, 30(2): 215-217.[12] 袁静. 动目标的提取分析与研究 .西安:西安电子科技大学,2007.[13] 王军,沙芸,吴裕树.基于背景模型的自动视频分割方法 [J]. 计算机工程与应用 ,2004, 40(9): 60-62.[14] Wang H M, Chang C W, Yang J F. An effective calibration procedure for correction of parallax unmatched image pairs [J]. IET Image Process, 2009, 2(3): 63-74.[15] Gu Z, Su X Y, Liu Y K, et al. Local stereo matching with adaptive support-weight rank transform and disparity calibration [J]. Pattern Recognition Letters, 2008, 29(9):1230-1235.
0
浏览量
33
下载量
2
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621