[1]王 丹,杨家琪,杨谢柳.基于改进 Census 变换的图像立体匹配算法研究[J].机械与电子,2021,(05):62-67.
　WANG Dan,YANG Jiaqi,YANG Xieliu.Research on Image Stereo Matching Algorithm Based on Improved Census Transform[J].Machinery & Electronics,2021,(05):62-67.
点击复制

基于改进 Census 变换的图像立体匹配算法研究()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2021年05期
页码:
62-67
栏目:
智能工程
出版日期:
2021-05-24

文章信息/Info

Title:
Research on Image Stereo Matching Algorithm Based on Improved Census Transform
文章编号:
１００１-２２５７ ( ２０２１ ) ０５-００６２-０６
作者:
王 丹; 杨家琪; 杨谢柳
沈阳建筑大学机械工程学院,辽宁 沈阳 １１０１６８
Author(s):
WANG Dan ;  YANG Jiaqi ;  YANG Xieliu
( College of Mechanical Engineering ,Shenyang Jianzhu University , Shenyang １１０１６８ , China
关键词:
机器视觉; 立体匹配; Census 变换; 多尺度空间; 视差
Keywords:
machine vision ;  stereo matching ;  Census transform ;  multi-scale space ;  parallax
分类号:
TP３９１.4
文献标志码:
A
摘要:
针对传统的 Census 区域匹配算法过分依赖窗口中心像素信息,导致算法受到噪声干扰时匹配精度降低的问题,提出一种基于改进 Census 变换的匹配算法.采用局部像素反差值为中心像素选择的评判标准,对传统的 Census 变换进行改进,增强了窗口像素信息的利用,提高了算法对像素值突变的适应性,使算法有更好的鲁棒性;代价聚合阶段采用引导图滤波算法并结合多尺度聚合模型,增强平坦区域像素间的区分度;采用 win-take-all 算法选取最优视差值,完成视差计算;采用区域投票策略和中值滤波算法完成视差精化.利用该改进算法对 Middlebury 平台提供的标准图像进行实验,实验结果表明该算法较传统Census 算法有较好的抗噪能力和立体匹配精度.
Abstract:
Aiming at the problem that the traditional Census area matching algorithm relies too much on the pixel information of the center of the window,resulting in the reduction of matching accuracy when the algorithm is interfered by noise,a matching algorithm based on improved Census transform is proposed．Using the local pixel contrast value as the criterion for selecting the central pixel , the traditional Census transform is improved , the use of window pixel information is enhanced , th ealgorithm＇s adaptability? to pixel value mutations is improved ,and the algorithm is more robust ; In the cost aggregation stage , the guide graph filtering algorithm and the multi- scale aggregation model are used to enhance the discrimination between pixels in flat areas ; the win-take-all algorithm is used to select the optimal parallax value to complete the parallax calculation ; the regional voting strategy and median filtering are used．Thealgorithmcompletestheparallaxrefinement．The improved algorithm was used to experiment on the standard images provided by the Middlebury platform．The experimental results show that the algorithm has better noise immunity and stereo matching accuracy than the traditional Census algorithm．

参考文献/References:

[１] KIM J C , LEE K M , CHOI B T , et al．A dense stereo matching using two-pass dynamic programming with generalized ground control points [ C ]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition , ２００５ , ９ ( ２ ): １０７５-１０８２．

[２] BLEYER M , GELAUTZ M．Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions [ J ] ．Signal processing-image communication , ２００７ , ２２ ( ２ ): １２７-１４３．
[３] 陈宁江,李介谷,邓雁萍 ．遗传算法在立体图象匹配中的应用[J ] ．上海交通大学学报, １９９８ ( ９ ): ５１-５４．
[４] 闫利,王芮,刘华,等 ．基于改进代价计算和自适应引导滤波的立体匹配[J ] ．光学学报, ２０１８ , ３８ ( １１ ): ２５７-２６７．
[５] LANG S．Introduction to algebraic geometry [ J ] ．Mathematical gazette , １９７３ , １９９ ( ６ ): ４８４．
[６] LONGUET-HIGGINS H C．A computer algorithm for reconstructing a scene from two projections [ J ] ．Nature , １９８１ , ２９３ ( ５８２８ ): １３３-１３５．
[７] ZABIH R , WOODFILL J．Non-parametric local transforms for computing visual correspondence [ C ]// European Conference on Computer Vision , １９９４ : １５１-１５８．
[８] DE-ＧMAEZTU L , VILLANUEVA A , CABEZA R , et al．Stereo matching using gradient similarity and locally adaptive support weight [ J ] ．Pattern recognition letters ,２０１１,３２ (１３): １６４３-１６５１．
[９] LEE Z , JUANG J , NGUYEN T Q．Local disparity estimation with three-moded cross census and advanced support weight [ J ] ．IEEE Transactions on multimedia ,２０１３ ,１５ ( ８ ): １８５５-１８６４．
[１０] HIRSCHMULLER H , SCHARSTEIN D．Evaluation of stereo matching costs on images with radiometric differences [ J ] ． IEEE Transactions on pattern analysis and machine intelligence , ２００９ , ３１ ( ９ ): １５８２-１５９９．
[１１] 许金鑫,李庆武,刘艳,等 ．基于色彩 权值 和 树形 动态规 划 的 立 体 匹 配 算 [ J ] ．光 学 学 报, ２０１７ , ３７( １２ ):２８９-２９７．
[１２] MEI X , SUN X , ZHOU M , et al．On building an accurate stereo matching system on graphics hardware[ C ]// International Conference on Computer Vision ,２０１１ : ４６７-４７４．
[１３] 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．
[１４] HE K M , SUN J , TANG X O．Guided image filtering[ C ]// European Conference on Computer Vision ,２０１０ : １-１４．
[１５] ZHU X , MILANFAR P．Automatic parameter selection for denoising algorithms using a no-reference measure of image content [ J ] ． IEEE Transactions on image processing , ２０１０ , １９ ( １２ ): ３１１６-３１３２．
[１６] KIM G B , CHUNG S C．An accurate and robust stereo matching algorithm with variable windows for ３D measurements [ J ] ．Mechatronics , ２００４ , １４ ( ６ ): ７１５-７３５．
[１７] ZHANG K , FANG Y , MIN D , et al．Cross-scale cost aggregation for stereo matching [ C ]// Computer Vision and Pattern Recognition , ２０１４ : １５９０-１５９７．
[１８] MIN D B , LU J B , DO M N．A revisit to cost aggregation in stereo matching : How fa rcan we reduce its computational redundancy [ C ]// International Conference on Computer Vision , ２０１１ : １５６７-１５７４．
[１９] HUMENBERGER M , ZINNER C , WEBER M , et al．A fast stereo matching algorithm suitable for embedded real-time systems [ J ] ．Computer vision and image understanding , ２０１０ , １１４ ( １１ ): １１８０-１２０２．
[２０] 马利,李晶皎,马技 ．邻域相关信息的改进 Census 变换立体匹 配算 法 [ J ] ．计 算 机 工 程 与 应 用,２０１４ , ５０(２４ ): １６-２０ , ４６．
[２１] AMBROSCH K , KUBINGER W．Accurate hardwarebased stereo vision [ J ] ．Computer vision and image understanding , ２０１０ , １１４ ( １１ ): １３０３-１３１６．

相似文献/References:

[1]周瑜,李戈,张学贺,等.基于双目视觉的地形三维重建[J].机械与电子,2016,(07):57.
　ZHOU Yu,LI Ge,ZHANG Xuehe,et al.[J].Machinery & Electronics,2016,(05):57.
[2]乔爽,吴金波.改进的Otsu算法在缺陷检测中的应用[J].机械与电子,2016,(07):71.
　QIAO Shuang,WU Jinbo,[J].Machinery & Electronics,2016,(05):71.
[3]王婷婷,李戈,赵杰,等.基于双目视觉的运动目标检测跟踪与定位[J].机械与电子,2015,(06):73.
　WANG Tingting,LI Ge,ZHAO Jie,et al.Detection,Tracking and Positioning of Moving Target Based on Binocular Vision[J].Machinery & Electronics,2015,(05):73.
[4]李 勋１,张伟军１,徐智卿２,等.狭小空间内孔高测量机器人设计及视觉定位方法研究[J].机械与电子,2019,(12):60.
　,,et al.Research on Design and Visual Positioning Method of Hole Height Measurement Robot in Narrow Space[J].Machinery & Electronics,2019,(05):60.
[5]吴广雨,张伟军,杨保佳.机器人视觉装配中的精确定位策略研究[J].机械与电子,2020,(03):75.
　,Research on AccuratePositioningMethod in RobotVisualAssembly System[J].Machinery & Electronics,2020,(05):75.
[6]薛鹏程,苏 宁,齐 峰,等.基于机器视觉的总段对接方法[J].机械与电子,2021,(04):3.
　XUE Pengcheng,SU Ning,Qi Feng,et al.Block Erecting Method Based on Machine Vision[J].Machinery & Electronics,2021,(05):3.
[7]邵悦辰,贡 亮,沈晓晔,等.基于机器视觉的FDM-3D快速成型异常工况监控系统[J].机械与电子,2021,(04):28.
　SHAO Yuechen,GONG Liang,SHEN Xiaoye,et al.Abnormal Working Condition Monitoring System in FDM-3D Rapid Prototyping Based on Machine Vision[J].Machinery & Electronics,2021,(05):28.
[8]卞越洋,高晓科,张伟军.机器人带电作业中的视觉定位与优化策略[J].机械与电子,2021,(05):57.
　BIAN Yueyang,GAO Xiaoke,ZHANG Weijun.Vision Positioning and Optimization Strategyin Robot Live Work[J].Machinery & Electronics,2021,(05):57.
[9]于学均１,闵 诚１,李振龙１,等.机器视觉及激光轮廓扫描的电流互感器外观信息自动识别算法[J].机械与电子,2021,(07):75.
　YU Xuejun,MIN Cheng,LI Zhenlong,et al.Automatic Recognition Algorithm of Current Transformer Appearance Information Based on Machine Vision and Laser Contour Scan[J].Machinery & Electronics,2021,(05):75.
[10]魏 哲,王 盼.面向珍珠分拣机器人的形状视觉检测方法[J].机械与电子,2021,(08):68.
　WEI Zhe,WANG Pan.Visual Inspection Method of Pearl Shape for Sorting Robot[J].Machinery & Electronics,2021,(05):68.

备注/Memo

备注/Memo:
收稿日期: ２０２０-１２-１０
基金项目:辽宁省自然科学基金资助项目( ２０１９ ZD ０６７３ )
作者简介:王 丹 ( １９７７－ ),女,满族,辽宁新宾人,博士,副教授,研究方向为机器人相关技术.
更新日期/Last Update: 2021-06-04