首页 > 论文 > 光学学报 > 39卷 > 3期(pp:315001--1)

基于图像分割的稠密立体匹配算法

Dense Stereo Matching Algorithm Based on Image Segmentation

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出一种基于图像分割的稠密立体匹配算法,该算法将灰度-梯度算法与零均值归一化互相关(ZNCC)算法相结合生成匹配代价,利用SLIC(Simple Liner Iterative Cluster)算法对图像进行分割,基于视差图和超像素更新了匹配代价。在视差后处理阶段,基于左右一致性检验(LRC)、孔洞填充和十字交叉自适应窗口加权中值滤波的方法减小视差图的误匹配率。利用Middlebury数据集的4组图像进行测试,测试结果表明,平均误匹配率为4.99%。

Abstract

A dense stereo matching algorithm is proposed based on image segmentation. This algorithm combines the gray-gradient algorithm and the zero-mean normalized cross-correlation (ZNCC) algorithm to generate matching cost. The SLIC (Simple Liner Iterative Cluster) algorithm is used for image segmentation. A method based disparity map and superpixels is proposed to update the matching cost. At the disparity post-processing stage, the LRC (Left Right Check), hole filling and cross adaptive window weighted median filtering methods are used to reduce the error matching rate of the disparity map. The performance evaluation experiments on four Middlebury stereo pairs demonstrate that the proposed algorithm achieves an average error matching rate of 4.99%.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN911.73

DOI:10.3788/aos201939.0315001

所属栏目:机器视觉

基金项目:国家自然科学基金(U1713216)

收稿日期:2018-09-13

修改稿日期:2018-10-10

网络出版日期:2018-10-21

作者单位    点击查看

马瑞浩:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016东北大学信息科学与工程学院, 辽宁 沈阳 110819中国科学院光电信息处理重点实验室, 辽宁 沈阳 110016
朱枫:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016中国科学院光电信息处理重点实验室, 辽宁 沈阳 110016
吴清潇:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016中国科学院光电信息处理重点实验室, 辽宁 沈阳 110016
鲁荣荣:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016中国科学院光电信息处理重点实验室, 辽宁 沈阳 110016
魏景阳:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016中国科学院光电信息处理重点实验室, 辽宁 沈阳 110016

联系人作者:朱枫(fzhu@sia.cn)

【1】Fan H R, Yang F, Pan X R, et al. Stereo matching algorithm for improved Census transform and gradient fusion[J]. Acta Optica Sinica, 2018, 38(2): 0215006.
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): 0215006.

【2】Scharstein D, Szeliski R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002, 47(1/2/3): 7-42.

【3】Taniai T, Matsushita Y, Sato Y, et al. Continuous 3D label stereo matching using local expansion moves[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(11): 2725-2739.

【4】Li J J, Ma L, Wang A X, et al. Stereo matching algorithm based on improved patchmatch and slice sampling particle belief propagation[J]. Journal of Northeastern University(Natural Science), 2016, 37(5): 609-613.
李晶皎, 马利, 王爱侠, 等. 基于改进Patchmatch及切片采样粒子置信度传播的立体匹配算法[J]. 东北大学学报(自然科学版), 2016, 37(5): 609-613.

【5】Zhu S P, Li Z. A stereo matching algorithm using improved gradient and adaptive window[J]. Acta Optica Sinica, 2015, 35(1): 0110003.
祝世平, 李政. 基于改进梯度和自适应窗口的立体匹配算法[J]. 光学学报, 2015, 35(1): 0110003.

【6】Zhu S P, Yan L N, Li Z. Stereo matching algorithm based on improved Census transform and dynamic programming[J]. Acta Optica Sinica, 2016, 36(4): 0415001.
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, 36(4): 0415001.

【7】Liang Z F, Feng Y L, Guo Y L, et al. Learning deep correspondence through prior and posterior feature constancy[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2403-2411.

【8】Xiao J P, Tian H, Zou W T, et al. Stereo matching based on convolutional neural network[J]. Acta Optica Sinica. 2018, 38(8): 0815017.
肖进胜, 田红, 邹文涛, 等. 基于深度卷积神经网络的双目立体视觉匹配算法[J]. 光学学报, 2018, 38(8): 0815017.

【9】Mayer N, Ilg E, Husser P, et al. A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2016: 4040-4048.

【10】Pang J H, Sun W X, Ren J S, et al. Cascade residual learning: a two-stage convolutional neural network for stereo matching[C]. IEEE International Conference on Computer Vision Workshops, 2017: 878-886.

【11】Rhemann C, Hosni A, Bleyer M, et al. Fast cost-volume filtering for visual correspondence and beyond[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(2): 504-511.

【12】Yang Q X. A non-local cost aggregation method for stereo matching[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2012: 1402-1409.

【13】Zhang K, Fang Y Q, Min D B, et al. Cross-scale cost aggregation for stereo matching[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2014: 1590-1597.

【14】Liu Y, Li Q W, Huo G Y, et al. Local binary description combined with superpixel segmentation refinement for stereo matching[J]. Acta Optica Sinica, 2018, 38(6): 0615003.
刘艳, 李庆武, 霍冠英, 等. 结合局部二进制表示和超像素分割求精的立体匹配[J]. 光学学报, 2018, 38(6): 0615003.

【15】Gong W B, Gu G H, Qian W X, et al. Stereo matching algorithm based on image segmentation and adaptive support weight[J]. Acta Optica Sinica, 2015, 35(s2): s210002.
龚文彪, 顾国华, 钱惟贤, 等. 基于图像分割和自适应支撑权重的立体匹配算法[J]. 光学学报, 2015, 35(s2): s210002.

【16】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.

【17】Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar-based image inpainting[J]. IEEE Transactions on Image Processing, 2004, 13(9): 1200-1212.

【18】Guo H, Ono N, Sagayama S. A structure-synthesis image inpainting algorithm based on morphological erosion operation[C]. Congress on Image and Signal Processing, 2008: 530-535.

【19】Jiao A S M, Tsang P W M, Poon T C. Restoration of digital off-axis Fresnel hologram by exemplar and search based image inpainting with enhanced computing speed[J]. Computer Physics Communications, 2015, 193: 30-37.

【20】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, 2011: 467-474.

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

【22】Scharstein D, Szeliski R. Middlebury stereo vision page[EB/OL]. (2017-11-15)[2018-12-03]. http://vision.middlebury.edu/stereo/.

引用该论文

Ma Ruihao,Zhu Feng,Wu Qingxiao,Lu Rongrong,Wei Jingyang. Dense Stereo Matching Algorithm Based on Image Segmentation[J]. Acta Optica Sinica, 2019, 39(3): 0315001

马瑞浩,朱枫,吴清潇,鲁荣荣,魏景阳. 基于图像分割的稠密立体匹配算法[J]. 光学学报, 2019, 39(3): 0315001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF