基于图像分割和可变窗的联合立体匹配

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 317-321.

基于图像分割和可变窗的联合立体匹配

胡汉平^1,2,3, 朱明¹, 吉淑娇^1,2, 郭滨³

1. 中国科学院长春光学精密机械与物理研究所,长春 130033;
2. 中国科学院研究生院,北京100039;
3. 长春理工大学,长春 130022

收稿日期:2012-07-03 发布日期:2013-06-01
作者简介:胡汉平(1980-),男,中国科学院博士研究生.研究方向:计算机视觉、数字图像处理.E-mail:custhhp@163.com
基金资助:
吉林省自然科学基金项目(201215133) .

Joint stereo matching based on image segmentation and variable windows

HU Han-ping^1,2,3, ZHU Ming¹, JI Shu-jiao^1,2, GUO Bin³

1. Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China;
2. Graduate School, Chinese Academy of Sciences, Beijing, 100039, China;
3. Changchun University of Science and Technology, Changchun, 130022, China

Received:2012-07-03 Published:2013-06-01

摘要/Abstract

摘要：

提出一种基于图像分割和可变窗的联合立体匹配算法。首先对参考图像和目标图像进行图像分割,根据视差在同一色彩分割区域平滑的假设,计算出分割区域的匹配代价;然后由窗口内的匹配误差均值、误差方差、偏向误差确定最佳可变窗并求出其匹配代价;最后综合两类匹配代价通过局部优化方法获得稠密视差图。实验结果表明,该算法能够较好的处理低纹理和深度不连续区域,得到较高匹配精度的同时降低了匹配时间。

关键词: 联合立体匹配, 视差, 图像分割, 可变窗, 匹配代价

Abstract:

A stereo matching based on image segmentation and variable windows is presented was proposed.Firstly,the reference and the target image was segmented based on the color information,according to the hypothesis of disparity in the same color segmentation region smooth,the matching cost of segmented regions was calculated,and then the matching cost of the best variable windows was calculated through the average matching errors,error variance and biases error,at last,two categories matching cost were merged and the dense disparity map was abtained through local optimization.Experimental results show that the algorithm can get a good effect on low texture and discontinuous depth region,not only achieves high accuracy but also has shorter matching time.

Key words: joint stereo matching, disparity, image segmentation, variable windows, matching cost

中图分类号:

Q811.9

胡汉平, 朱明, 吉淑娇, 郭滨. 基于图像分割和可变窗的联合立体匹配[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 317-321.

HU Han-ping, ZHU Ming, JI Shu-jiao, GUO Bin. Joint stereo matching based on image segmentation and variable windows[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 317-321.

参考文献

[1] Scharstein D,Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].International Journal of Computer Vision,2002,47:7-42.

[2] Demaeztu L,Villanueva A,Cabeza R.Stereo matching using gradient similarity and locally adaptive support-weight[J].Pattern Recognition Letters,2011,32(13):1643-1651.

[3] De-Maeztu L,Mattoccia S,Villanueva A,et al.Efficient aggregation via iterative block-based adapting support weight[C]//International Conference on 3D (IC3D 2011).Liege,Belgium,2011:7-8.

[4] Hirschmuller H.Innocent J,Garibaldi P.Real-time correlation-based stereo vision with reduced border errors[J].Journal of Computer Vision,2002,47:1-3.

[5] 伍春洪,付国亮.一种基于图像分割及邻域限制与放松的立体匹配方法[J].计算机学报,2011,34(4):755-760.Wu Chun-hong,Fu Guo-liang.Based stereo matching method in image segmentation and neighborhood restrictions and relaxation[J].Chinese Journal of Computers,2011,34(4):755-760.

[6] Mattoccia S.Accurate dense stereo by constraining local consistency on superpixels[C]//20th International Conference on Pattern Recognition (ICPR2010).Istanbul,Turkey,2010:23-26.

[7] Sun J,Zheng N N,Shum H Y.Stereo matching using belief propagation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):787-800.

[8] 刘赫伟,汪增福.一种沿区域边界的动态规划立体匹配算法[J].模式识别与人工智能,2010,23(1):38-44.Liu He-wei, Wang Zeng-fu. An along the regional border dynamic programming stereo matching algorithm[J].Pattern Recogntion and Drtificial Intelligence,2010,23(1):38-44.

[9] Wang Z,Zheng Z.A region based stereo matching algorithm using cooperative optimization[C]//CVPR 2008:117-120.

[10] De-Maeztu L,Mattoccia S,Villanueva A,et al.Linear stereo ma tching [C]//International Conference on Computer Vision (ICCV 2011).Barcelona,Spain,2011:6-13.

[11] Comaniciu D,meer P.Mean shift:A robust approach toward feature space analysis[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2002,24( 5):603-619

[12] Velsler O.Fast variable window for stereo correspondence using integral images[C]//IEEE International Conference on Computer Vision and Pattern Recognition,USA.2003:556-561.

[13] Yoon K J,Kweon S.Adaptive support-weight approach for correspondence serarch[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):650-656.

[14] Tombari F,Mattoccia S,Distefano L.Segmentation-based adaptive support for accurate stereo correspondence[C]// IEEE Pacific-Rim Symposium on Image and Video Technology (PSIVT 2007).2007.

相关文章 15

[1]	刘仲民,王阳,李战明,胡文瑾. 基于简单线性迭代聚类和快速最近邻区域合并的图像分割算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1931-1937.
[2]	肖明尧, 李雄飞, 张小利, 张刘. 基于多尺度的区域生长的图像分割算法[J]. 吉林大学学报(工学版), 2017, 47(5): 1591-1597.
[3]	刘仲民, 李战明, 李博皓, 胡文瑾. 基于稀疏矩阵的谱聚类图像分割算法[J]. 吉林大学学报(工学版), 2017, 47(4): 1308-1313.
[4]	许岩岩, 陈辉, 刘家驹, 袁金钊. CELL处理器并行实现立体匹配算法[J]. 吉林大学学报(工学版), 2017, 47(3): 952-958.
[5]	赵夫群, 周明全, 耿国华. 基于GA-Otsu法的图像阈值分割及定量识别[J]. 吉林大学学报(工学版), 2017, 47(3): 959-964.
[6]	肖明尧, 李雄飞. 基于高斯分解的多尺度3D Otsu阈值分割算法[J]. 吉林大学学报(工学版), 2017, 47(1): 255-261.
[7]	王培智, 田地, 龙涛, 李抵非, 邱春玲, 刘敦一. 用于TOF-SIMS的锆石样品图像自动聚焦算法[J]. 吉林大学学报(工学版), 2017, 47(1): 308-315.
[8]	申铉京, 张赫, 陈海鹏, 王玉. 快速递归多阈值分割算法[J]. 吉林大学学报(工学版), 2016, 46(2): 528-534.
[9]	郑欣, 彭真明, 邢艳. 基于活跃度的图像分割算法性能评价新方法[J]. 吉林大学学报(工学版), 2016, 46(1): 311-317.
[10]	李一兵，杨鹏，叶方，刘丹丹. 基于交互势函数和均场参数估计的分层MRF模型的纹理图像分割[J]. 吉林大学学报(工学版), 2015, 45(6): 2075-2079.
[11]	何凯, 朱程涛, 姚静娴. 基于双权重聚合的立体匹配算法[J]. 吉林大学学报(工学版), 2015, 45(4): 1318-1323.
[12]	李雄飞^{1, 2}, 赵浩宇¹, 陈霄³, 赵宏伟^{1, 2}. 基于视觉特征的不规则形状目标分割方法[J]. 吉林大学学报(工学版), 2014, 44(4): 1140-1144.
[13]	张金果,郭海涛,吴君鹏,李依桐. 改进的最小交叉Tsallis熵的小目标声呐图像分割[J]. 吉林大学学报(工学版), 2014, 44(3): 834-839.
[14]	何凯, 穆星, 邹刚. 基于图像分割的三维立体匹配改进算法[J]. 吉林大学学报(工学版), 2014, 44(01): 219-224.
[15]	李晓瑜, 杨马英. 足球机器人视觉图像分割算法[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 260-264.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed