基于图像分割的立体匹配算法

doi:10.11772/j.issn.1001-9081.2019101771

计算机应用 ›› 2020, Vol. 40 ›› Issue (5): 1415-1420.DOI: 10.11772/j.issn.1001-9081.2019101771

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于图像分割的立体匹配算法

张一飞, 李新福, 田学东

河北大学网络空间安全与计算机学院，河北保定 071000

收稿日期:2019-10-18 修回日期:2019-12-10 出版日期:2020-05-10 发布日期:2020-05-15
通讯作者: 李新福(1970—)
作者简介:张一飞(1994—)，男，河北石家庄人，硕士研究生，主要研究方向：智能图文处理；李新福(1970—)，男，河北保定人，教授，博士，主要研究方向：智能图文处理；田学东(1963—)，男，天津人，教授，博士，CCF会员，主要研究方向：模式识别、信息检索。
基金资助:
河北省教育厅高等学校科学技术研究重点项目(ZD2017209)。

Stereo matching algorithm based on image segmentation

ZHANG Yifei, LI Xinfu, TIAN Xuedong

School of Cyber Security and Computer, Hebei University, Baoding Hebei 071000, China

Received:2019-10-18 Revised:2019-12-10 Online:2020-05-10 Published:2020-05-15
Contact: LI Xinfu, born in 1970, Ph. D.，professor. His research interests include intelligent image and text processing.
About author:ZHANG Yifei，born in 1994，M. S. candidate. His research interests include intelligent image and text processing.LI Xinfu, born in 1970, Ph. D.，professor. His research interests include intelligent image and text processing.TIAN Xuedong，born in 1963，Ph. D.，professor. His research interests include pattern recognition, information retrieval.
Supported by:
This work is partially supported by the Key Science and Technology Research Project in Colleges and Universities of Hebei Provincial Department of Education (ZD2017209)．

摘要/Abstract

摘要：

针对在立体匹配中弱纹理及纯色区域匹配不准确和图像分割算法耗时较多的问题，提出一种融合图像分割的立体匹配算法。首先，将初始图像进行高斯滤波和Sobel平滑的处理，获取图像的边缘特征图；然后，将原图的红、绿、蓝三个通道值采用最大类间方差法进行二分类，再融合得到分割模板图；最后，将所得到的灰度图、边缘特征图和分割模板图用于视差计算和视差优化的过程，计算得到视差图。相比绝对差值和（SAD）算法，所提算法在精度上平均提升了14.23个百分点，时间开销上平均每万个像素点只多消耗了7.16 ms。实验结果表明，该算法在纯色及弱纹理区域和视差不连续区域取得了更加平滑的匹配结果，在图像分割上能够自动计算阈值且能够较快地对图像进行分割。

关键词: 边缘特征, 图像分割, 弱纹理纯色区域, 二值化, 立体匹配

Abstract:

Aiming at the problem of inaccurate matching of weak texture and pure color region in stereo matching and long time consumption of image segmentation algorithms, a stereo matching algorithm fused with image segmentation was proposed. Firstly, the initial image was filtered by Gaussian and smoothed by Sobel to obtain the edge feature map of the image. Secondly, the red, green and blue channel values of the original image were dichotomized by using the Otsu method and then refused to obtain the segmentation template map. Finally, the obtained grayscale map, edge feature map and segmentation template map were applied in the parallax calculation and parallax optimization process in order to calculate the parallax map. The proposed algorithm has the accuracy improved by 14.23 percentage points on average with the time cost per 10 000 pixels increased by 7.16 ms in comparison with Sum of Absolute Differences (SAD) algorithm. The experimental results show that the proposed algorithm can obtain smoother matching results in pure color and weak texture regions and parallax discontinuity regions, and it can automatically calculate the threshold and segment the image faster.

Key words: edge feature, image segmentation, weak texture and pure color region, binarization, stereo matching

中图分类号:

TP391.41

张一飞, 李新福, 田学东. 基于图像分割的立体匹配算法[J]. 计算机应用, 2020, 40(5): 1415-1420.

ZHANG Yifei, LI Xinfu, TIAN Xuedong. Stereo matching algorithm based on image segmentation[J]. Journal of Computer Applications, 2020, 40(5): 1415-1420.

参考文献

1 游素亚,徐光祐 . 立体视觉研究的现状与进展[J]. 中国图象图形学报, 1997, 2(1):17-24. (YOU S Y, XU G Y. State of the art and Future the development of stereo vision[J]. Journal of Image and Graphics, 1997, 2(1):17-24
2 MYINT M , YONEMORI K , YANOU A , et al . Visual-servo-based autonomous docking system for underwater vehicle using dual-eyes camera 3D-pose tracking[C]// Proceedings of the 2015 IEEE/SICE International Symposium on System Integration. Piscataway: IEEE, 2015:989-994.
3 高瞻宇 . 基于立体视觉的空间动态目标测量与跟踪算法设计[D]. 北京: 中国科学院大学, 2018:5-6. (GAO Z Y. Design of spatial dynamic target measurement and tracking algorithm based on stereo vision[D]. Beijing: University of Chinese Academy of Sciences, 2018:5-6.
4 DINHAM M , FANG G . Autonomous weld seam identification and localisation using eye-in-hand stereo vision for robotic arc welding[J]. Robotics and Computer-Integrated Manufacturing, 2013, 29(5):288-301.
5 武强,李智,王勇军 . 无人机飞行目标导航定位图像优化匹配仿真[J].计算机仿真, 2019, 36(3):98-104, 163. (WU Q, LI Z, WANG Y J. The simulation on optimization and matching of image for navigation and positioning of UAV flight target[J]. Computer Simulation, 2019, 36(3):98-104, 163.)
6 FAN R , AI X , DAHNOUN N . Road surface 3D reconstruction based on dense subpixel disparity map estimation[J]. IEEE Transactions on Image Processing, 2018, 27(6):3025-3035.
7 YOU Y , LI B , LI P , et al . A two-stage clustering based 3D visual saliency model for dynamic scenarios[J]. IEEE Transactions on Multimedia, 2019, 21(4):809-820.
8 王旭初,刘辉煌,牛彦敏 . 融合多尺度局部特征与深度特征的双目立体匹配[J]. 光学学报, 2020, 40(2): No.0215001. (WANG X C, LIU H H, NIU Y M. Binocular stereo matching by combining multiscale local and deep features[J]. Acta Optica Sinica, 2020, 40(2): No.0215001.)
9 俞力 . 双目视觉中立体匹配算法研究[D]. 武汉:武汉理工大学, 2018:21-25. (YU L. Research of stereo matching algorithm in binocular vision[D]. Wuhan: Wuhan University of Technology, 2018:21-25.
10 CHEN L , HUANG P , CAI J . Extracting and matching lines of low-textured region in close-range navigation for tethered space robot[J]. IEEE Transactions on Industrial Electronics, 2019, 66(9):7131-7140.
11 张一飞,李新福,田学东 . 融合边缘特征的SAD立体匹配算法[J/OL]. 计算机工程 [2019-09-02]. http://kns.cnki.net/kcms /detail/31.1289.TP.20190817.1225.002.html. ZHANG Y F , LI X F , TIAN X D . SAD Stereo Matching Algorithm Combining Edge Features[J/OL]. Computer Engineering [2019-09-02]. http://kns.cnki.net/kcms/detail/31.1289.TP.20190817.1225.002.html.
12 邹进贵,万荧,孟丽媛 . 一种基于自适应权重SAD与Census融合的匹配算法[J]. 测绘通报, 2018(11):11-15. (ZHOU J G, WAN Y, MENG L Y. A new stereo matching algorithm based on adaptive weight SAD algorithm and census algorithm[J]. Bulletin of Surveying and Mapping, 2018(11):11-15.)
13 高雅昆,刘涛,李海滨,等 . 基于像素类别优化的PatchMatch立体匹配算法[J]. 光学学报, 2019, 39(7):No.0715006. GAO Y K, LIU T, LI H B,et al. Stereo matching algorithm based on pixel category optimized PatchMatch[J]. Acta Optica Sinica,2019, 39(7):No.0715006.
14 马伟,李曈,龚超凡,等 . 结合CNN与分割约束的立体匹配算法[J]. 北京工业大学学报, 2019, 45(5):413-420. MA W , LI T , GONG C F , et al . Stereo matching with CNN and constraints from segmentation[J]. Journal of Beijing University of Technology, 2019, 45(5):413-420.
15 MOHAMMADI H , SAMADZADEGAN F , REINARTZ P . 2D/3D information fusion for building extraction from high-resolution satellite stereo images using kernel graph cuts[J]. International Journal of Remote Sensing, 2019, 40(15):5835-5860.
16 郁怀波,胡越黎,徐杰 . 基于多特征融合与树形结构代价聚合的立体匹配算法[J]. 上海大学学报(自然科学版), 2019, 25(1):66-74. (YU H B, HU Y L, XU J. Stereo matching algorithm based on multi-feature fusion and tree structure aggregation[J]. Journal of Shanghai University (Natural Science Edition), 2019, 25(1):66-74.)
17 CANNY J . A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI- 8(6): 679-697.
18 刘丽霞,李宝文,王阳萍,等 . 改进Canny边缘检测的遥感影像分割[J]. 计算机工程与应用, 2019, 55(12):54-58. LIU L X , LI B W , WANG Y P , et al . Remote sensing image segmentation based on improved Canny edge detection[J]. Computer Engineering and Applications, 2019, 55(12):54-58.
19 FERHAT F A , MOHAMED L A , KERDJIDJ O , et al . Implementation of SOBEL, PREWITT , ROBERTS edge detection on FPGA[EB/OL].[2019-06-20].http://worldcomp-proceedings.com/proc/p2013/IPC3404.pdf.
20 LI L , ZHANG S , YU X , et al . PMSC: PatchMatch-based superpixel cut for accurate stereo matching[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(3):679-692.
21 MA W , YANG L , ZHANG Y , et al . Fast interactive stereo image segmentation[J]. Multimedia Tools and Applications, 2016, 75(18)： 10935-10948.
22 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):No.s210002 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): No.s210002.)
23 BORDINI A , PROTTI F , SILVA T G DA , et al . New algorithms for the minimum coloring cut problem[J]. International Transactions in Operational Research, 2019, 26(5):1868-1883.
24 易三莉,张桂芳,贺建峰,等 . 基于最大类间方差的最大熵图像分割[J]. 计算机工程与科学, 2018, 40(10):1874-1881. YI S L , ZHANG G F , HE J F , et al . Maximum entropy image segmentation based on maximum interclass variance[J]. Computer Engineering and Science, 2018, 40(10):1874-1881.
25 NG H F . Automatic thresholding for defect detection[J]. Pattern Recognition Letters, 2006， 27(14):1644-1649.
26 MOGHADDAM FARRAHI , R, CHERIET M . AdOtsu: an adaptive and parameterless generalization of Otsu’s method for document image binarization[J]. Pattern Recognition, 2012, 45(6):2419-2431.
27 RIBAL C , LERMé N , LE HéGARAT-MASCLE S . Efficient graph cut optimization for shape from focus[J]. Journal of Visual Communication and Image Representation, 2018, 55:529-539.

[1]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[2]	沈雪雯, 王晓东, 姚宇. 基于空间分频的超声图像分割注意力网络[J]. 计算机应用, 2021, 41(6): 1828-1835.
[3]	黄梨, 卢龙. 基于长距离依赖编码与深度残差U-Net的缺血性卒中病灶分割[J]. 计算机应用, 2021, 41(6): 1820-1827.
[4]	董阳, 潘海为, 崔倩娜, 边晓菲, 滕腾, 王邦菊. 面向多模态磁共振脑瘤图像的小样本分割方法[J]. 计算机应用, 2021, 41(4): 1049-1054.
[5]	罗琴, 王艳. 无需初始轮廓的图像分割模型[J]. 计算机应用, 2021, 41(4): 1179-1183.
[6]	胡屹杉, 秦品乐, 曾建潮, 柴锐, 王丽芳. 基于特征融合和动态多尺度空洞卷积的超声甲状腺分割网络[J]. 计算机应用, 2021, 41(3): 891-897.
[7]	袁芊芊, 邓洪敏, 王晓航. 基于超像素快速模糊C均值聚类与支持向量机的柑橘病虫害区域分割[J]. 计算机应用, 2021, 41(2): 563-570.
[8]	韩艳茹, 尹梦晓, 覃子轩, 苏鹏, 杨锋. 图像和视频的低多边形渲染[J]. 计算机应用, 2021, 41(2): 504-510.
[9]	原泉, 王艳, 李玉先. 距离保持水平集演化模型的快速实现算法[J]. 计算机应用, 2020, 40(9): 2743-2747.
[10]	高海军, 曾祥银, 潘大志, 郑伯川. 基于U-Net改进模型的直肠肿瘤分割方法[J]. 计算机应用, 2020, 40(8): 2392-2397.
[11]	吴崇数, 林霖, 薛蕴菁, 时鹏. 基于自监督学习的病理图像层次分割[J]. 计算机应用, 2020, 40(6): 1856-1862.
[12]	曾招鑫, 刘俊. 基于深度学习的秀丽隐杆线虫显微图像分割方法[J]. 计算机应用, 2020, 40(5): 1453-1459.
[13]	魏小娜, 邢嘉祺, 王振宇, 王颖珊, 石洁, 赵地, 汪红志. 基于改进U-Net的关节滑膜磁共振图像的分割[J]. 计算机应用, 2020, 40(11): 3340-3345.
[14]	冯涛, 陈斌, 张跃飞. 基于改进的Mask R-CNN的染色体图像分割框架[J]. 计算机应用, 2020, 40(11): 3332-3339.
[15]	张泽林, 徐军. 基于条件生成对抗网络的乳腺上皮和间质区域自动分割[J]. 计算机应用, 2020, 40(10): 2910-2916.

基于图像分割的立体匹配算法

Stereo matching algorithm based on image segmentation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics