计算机科学 ›› 2015, Vol. 42 ›› Issue (Z6): 13-15.
郭龙源,孙长银,张国云,吴健辉
GUO Long-yuan, SUN Chang-yin, ZHANG Guo-yun and WU Jian-hui
摘要: 匹配窗口大小和形状是影响区域立体匹配算法效果的关键因素之一。根据相位一致性能反映灰度变化快慢情况和抗干扰能力较强的特点,对图像进行相位一致性检测,再根据监测的值确定像素的特性,然后按不同特性采用不同窗口进行匹配,并结合非参量测度和灰度值构成复合费用函数值,得到最终的视差图。实验结果表明,本算法有较好的匹配效果。
[1] Kanade T,Okutomi M.A stereo matching algorithm with adaptive window:Theory and experiment[J].IEEE transactions on Pattern analysis and Machine Intelligence,1994,6(9):920-932 [2] Veksler O.Stereo matching by compact windows via minimumratio cycle[J].International Journal of Computer Vision,2002,1:556-561 [3] Yoon K J,Kweon I S.Adaptive support weight approach forstereo correspondence search[J].IEEE Transactions on Pattern analysis and Machine Intelligence,2005,28(4):650-656 [4] Kovesi P D.Phase congruency:A low-level image invariant[J].Psychological Research,2000,64(2):136-148 [5] Mei X,Sun X,Zhou M,et al.On building an accurate stereomatching system on graphics hardware[C]∥IEEE International Conference on Computer Vision Workshops(ICCV Workshops).2011:467-474 [6] 段凤增.信号检测理论[M].哈尔滨:哈尔滨工业大学出版社,2002:226-228 |
No related articles found! |
|