张晶;王竞雪;

• 1:辽宁工程技术大学测绘与地理科学学院

摘要(Abstract)：

针对传统单一Census变换未充分利用影像信息且精度不高的问题,该文提出了一种结合颜色信息的Census变换半全局立体匹配算法。该算法联合像素点间RGB颜色绝对差值与其Census变换值的匹配代价计算方法,采用八方向半全局视差获取方法获得初始稠密视差图。为进一步提高匹配精度,利用左右一致性交叉检测确定初始视差图中不稳定视差;采用基于均值偏移图像分割的视差优化算法对视差图中不稳定视差进行优化,获得最终视差图。选取4组middlebury立体图片库经典立体像对进行视差获取实验并检测。结果表明,本算法能够获得较高精度且可靠视差图,且在遮挡、视差不连续处的视差精度明显优于单一Census变换立体匹配算法及一些改进半全局立体匹配算法。

关键词(KeyWords)： Census变换;颜色绝对差值;半全局立体匹配;左右一致性检测;mean-shift图像分割

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目（41871379）;; 辽宁省教育厅科学研究一般项目（LJYL010）;; 地球观测与时空信息科学国家测绘地理信息局重点实验室经费资助项目（201801）

作者(Authors): 张晶;王竞雪;

DOI: 10.16251/j.cnki.1009-2307.2019.12.022

参考文献(References)：

• [1]周芳．双目视觉中立体匹配算法的研究与实现[D]．大连：大连理工大学，2013.(ZHOU Fang.Research on stereo matching in binocular vision and its implementation[D].Dalian:Dalian University of Technology,2013.)
• [2]宁晓斐．双目立体视觉中半全局立体匹配算法的研究[D]．沈阳：辽宁大学，2014.(NING Xiaofei.Research on semi-global stereo matching algorithm of binocular stereo vision[D].Shenyang:Liaoning University,2014.)
• [3]郭龙源，罗百通，欧先锋，等．自适应窗口和半全局立体匹配算法研究[J]．成都工业学院学报，2017,20(1):7-11.(GUO Longyuan,LUO Baitong,OU Xianfeng,et al.Adaptive windows and semi-global stereo matching algorithm[J].Journal of Chengdu Technology University,2017,20(1):7-11.)
• [4] SCHARSTEIN D,SZELISKI R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].International Journal of Computer Vision,2002,47(1-3):7-42.
• [5] HIRSCHMULLER H,SCHARSTEIN D.Evaluation of stereo matching costs on images with radiometric differences[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2009,31(9):1582-1599.
• [6]王琼，江晓亮，袁建英，等．基于改进Census变换的区域立体匹配算法[J]．计算机应用研究，2015,32(10):3164-3167.(WANG Qiong,JIANG Xiaoliang,YUAN Jianying,et al.Regional stereo matching algorithm based on improved census transform[J].Application Research of Computers,2015,32(10):3164-3167.)
• [7] FR B,ERNST A.Face detection with the modified Census transform[C]∥IEEE International Conference on Automatic Face and Gesture Recognition.Seoul,South Korea:IEEE Computer Society,2004:91-96.
• [8] KWAK J C,PARK T R,YONG S K,et al.Implementation of improved census transform stereo matching on a multicore processor[M]∥Multimedia and Ubiquitous Engineering.Berlin:Springer,2013:989-995.
• [9]雷磊，郑江滨，宋雪梅．基于改进Census变换的立体匹配算法[J]．计算机应用研究，2013,30(10):3185-3188.(LEI Lei,ZHENG Jiangbin,SONG Xuemei.Improved Census transform for stereo matching[J].Application Research of Computers,2013,30(10):3185-3188.)
• [10]祝世平，闫利那，李政．基于改进Census变换和动态规划的立体匹配算法[J]．光学学报，2016(4):208-216.(ZHU Shiping,YAN Lina,LI Zheng.Stereo matching algorithm based on improved Census transform and dynamic programming[J].Acta Optica Sinica,2016(4):208-216.)
• [11]袁建英，王琼，刘甲甲，等．用改进Census变换实现光照变化鲁棒光流计算[J]．计算机辅助设计与图形学学报，2015,27(9):1725-1733.(YUAN Jianying,WANG Qiong,LIU jiajia,et al.A robust optical flow computation under variational illumination based on improved Census transformation[J].Journal of Computer-Aided Design and Computer Graphics,2015,27(9):1725-1733.)
• [12]周龙，徐贵力，李开宇，等．基于Census变换和改进自适应窗口的立体匹配算法[J]．航空学报，2012,33(5):886-892.(ZHOU Long,XU Guili,LI Kaiyu,et al.Stereo matching algorithm based on Census transform and modified adaptive windows[J].Acta Aeronautia et Astronautica Sinica,2012,33(5):886-892.)
• [13]SUN X,MEI X,JIAO S,et al.Stereo matching with reliable disparity propagation[C]∥International Conference on 3D Imaging,Modeling,Processing,Visualization and Transmission.Hangzhou,China:IEEE,2011:132-139.
• [14]范海瑞，杨帆，潘旭冉，等．一种改进Census变换与梯度融合的立体匹配算法[J]．光学学报，2018,38(2):267-277.(FAN Hairui,YANG Fan,PAN Xuran,et al.Stereo matching algorithm for improved Census transform and gradient fusion[J].Acta Optica Sinica,2018,38(2):267-277.)
• [15]BROX T,BRUHN A,PAPENBERG N,et al.High accuracy optical flow estimation based on a theory for warping[C]∥European Conference on Computer Vision.Berlin:Springer,2004,3024(:10):25-36.
• [16]MEI X,SUN X,ZHOU M C,et al.On building an accurate stereo matching system on graphics hardware[C]∥IEEE International Conference on Computer Vision Workshops.Barcelona,Spain:IEEE,2012:467-474.
• [17]HIRSCHMLLER H.Stereo processing by semiglobal matching and mutual information[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2007,30(2):328-341.
• [18]COMANICIU D,MEER P.Mean shift:A robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
• [19]BAKER S,ROTH S,SCHARSTEIN D,et al.A database and evaluation methodology for optical flow[J].International Journal of Computer Vision,2011,92(1):1-31.