基于边缘检测的视差图效果优化
|
摘要
在立体视觉中,匹配之后得到的视差图利用投影模型可以得到原图像的深度信息和三维信息。为了达到提高立体匹配的精度与速度的目的,提高视差图的质量成为了立体匹配的核心问题。利用Canny检测算法、Sobel检测算法、Scharr检测算法对双目图像进行边缘提取。在此基础上,分别使用BM(Boyer-Moore algorithm)算法、SGBM(Semi-global block Matching)算法以及DP(Dynamic programming)算法进行立体匹配,并且分别计算视差图及误匹配率。经分析,Canny检测算法与SGBM算法相结合的方法剔除了大量不相关信息,大幅度减少数据的处理量。选取真实场景图片对该方法进行结论验证。实验结果表明,该方法提高了视差图的质量。
In stereo vision, disparity map after stereo matching using projection model can get the depth information and 3 D information of the original image. In order to improve the accuracy and speed of stereo matching, improving the quality of disparity map becomes the core problem of stereo matching. The paper extracted edge information of binocular images using Canny, Scharr and Sobel edge detection algorithm. On this basis, BM(Boyer-Moore algorithm), SGBM(Semi-global block matching) algorithm and DP(Dynamic programming) algorithm were used for stereo matching, and disparity map and mismatch rate were calculated respectively. After analysis, the combination of Canny detection algorithm and SGBM algorithm could eliminate a large number of irrelevant information and reduce the amount of data processing. The real scene image was selected to validate the method. The experimental results show that this method improves the quality of disparity map.
In stereo vision, disparity map after stereo matching using projection model can get the depth information and 3 D information of the original image. In order to improve the accuracy and speed of stereo matching, improving the quality of disparity map becomes the core problem of stereo matching. The paper extracted edge information of binocular images using Canny, Scharr and Sobel edge detection algorithm. On this basis, BM(Boyer-Moore algorithm), SGBM(Semi-global block matching) algorithm and DP(Dynamic programming) algorithm were used for stereo matching, and disparity map and mismatch rate were calculated respectively. After analysis, the combination of Canny detection algorithm and SGBM algorithm could eliminate a large number of irrelevant information and reduce the amount of data processing. The real scene image was selected to validate the method. The experimental results show that this method improves the quality of disparity map.
引文
[1] 王茜,陈一民,丁友东.基于改进卷积神经网络的机动车图像分类算法[J].计算机应用与软件,2018,35(7):263-266,298.
[2] Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window:Theory and experiment[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1994,16(9):920-932.
[3] Veksler O.Stereo correspondence with compact windows via minimum ratio cycle[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2002,24(12):1654-1660.
[4] 李金凤,边继龙.基于迭代指导滤波的立体匹配方法[J].计算机应用与软件,2017,34(9):178-182,239.
[5] Sun J,Shum H Y,Zheng N N.Stereo Matching Using Belief Propagation[J].Pattern Analysis & Machine Intelligence IEEE Transactions on,2003,25(7):787-800.
[6] 曹之乐,严中红,王洪.双目立体视觉匹配技术综述[J].重庆理工大学学报(自然科学),2015(2):70-75.
[7] 韩峻峰,王帅.基于双目立体视觉技术的汽车测距系统实现[J].计算机应用与软件,2016,33(9):227-230.
[8] 葛亮,朱庆生,傅思思,等.改进的立体像对稠密匹配算法[J].吉林大学学报(工学版),2010(1):212-217.
[9] 宗晨临.基于双目立体匹配的视差提取算法研究[D].成都:西南交通大学,2013.
[10] Hosni A,Rhemann C,Bleyer M,et al.Fast Cost-Volume Filtering for Visual Correspondence and Beyond[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,35(2):504-511.
[11] Mühlmann K,Maier D,Hesser J,et al.Calculating Dense Disparity Maps from Color Stereo Images,an Efficient Implementation[J].International Journal of Computer Vision,2002,47(1):79-88.
[12] Hirschmüller H.Stereo Processing by Semiglobal Matching and Mutual Information[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,30(2):328-341.
[13] Hirschmüller H.Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).IEEE,2005,2:807-814.
[14] 张欢,安利,张强,等.SGBM算法与BM算法分析研究[J].测绘与空间地理信息,2016(10):214-216.
[15] 龚文.基于动态规划的立体匹配算法研究[D].南昌:南昌航空大学,2015
[16] Jin L,Guo B,Jiang Y,et al.Study on the Impact Degrees of Several Driving Behaviors When Driving While Performing Secondary Tasks[J].IEEE Access,2018,6(1):65772-65782.
[17] Yue X Y,Wang F R,Guo B C,et al.Disparity map optimization based on edge detection[C]//2018 Chinese Control And Decision Conference(CCDC).2018:3311-3315.
[2] Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window:Theory and experiment[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1994,16(9):920-932.
[3] Veksler O.Stereo correspondence with compact windows via minimum ratio cycle[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2002,24(12):1654-1660.
[4] 李金凤,边继龙.基于迭代指导滤波的立体匹配方法[J].计算机应用与软件,2017,34(9):178-182,239.
[5] Sun J,Shum H Y,Zheng N N.Stereo Matching Using Belief Propagation[J].Pattern Analysis & Machine Intelligence IEEE Transactions on,2003,25(7):787-800.
[6] 曹之乐,严中红,王洪.双目立体视觉匹配技术综述[J].重庆理工大学学报(自然科学),2015(2):70-75.
[7] 韩峻峰,王帅.基于双目立体视觉技术的汽车测距系统实现[J].计算机应用与软件,2016,33(9):227-230.
[8] 葛亮,朱庆生,傅思思,等.改进的立体像对稠密匹配算法[J].吉林大学学报(工学版),2010(1):212-217.
[9] 宗晨临.基于双目立体匹配的视差提取算法研究[D].成都:西南交通大学,2013.
[10] Hosni A,Rhemann C,Bleyer M,et al.Fast Cost-Volume Filtering for Visual Correspondence and Beyond[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,35(2):504-511.
[11] Mühlmann K,Maier D,Hesser J,et al.Calculating Dense Disparity Maps from Color Stereo Images,an Efficient Implementation[J].International Journal of Computer Vision,2002,47(1):79-88.
[12] Hirschmüller H.Stereo Processing by Semiglobal Matching and Mutual Information[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,30(2):328-341.
[13] Hirschmüller H.Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).IEEE,2005,2:807-814.
[14] 张欢,安利,张强,等.SGBM算法与BM算法分析研究[J].测绘与空间地理信息,2016(10):214-216.
[15] 龚文.基于动态规划的立体匹配算法研究[D].南昌:南昌航空大学,2015
[16] Jin L,Guo B,Jiang Y,et al.Study on the Impact Degrees of Several Driving Behaviors When Driving While Performing Secondary Tasks[J].IEEE Access,2018,6(1):65772-65782.
[17] Yue X Y,Wang F R,Guo B C,et al.Disparity map optimization based on edge detection[C]//2018 Chinese Control And Decision Conference(CCDC).2018:3311-3315.