基于边缘约束的自适应引导滤波立体匹配算法  

An adaptive guided filtering stereo matching algorithm based on edge constraints

作　　者：陈立伟[1] 李山坤 CHEN Liwei;LI Shankun(College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《应用科技》2020年第4期47-53,共7页Applied Science and Technology

基　　金：国家自然科学基金项目(61102105).

摘　　要：为解决局部立体匹配算法存在深度图边界区域不连续问题,本文提出了一种基于边缘约束的自适应引导滤波立体匹配算法。将梯度值和颜色信息结合进行匹配代价计算;然后,基于图像边缘局部特征,对图像的像素点基于颜色阈值和边界条件构建自适应十字交叉区域,并对自适应窗口进行引导滤波代价聚合;最后,采用胜者为王策略(winner takes all,WTA)进行视差计算,对视差图进行视差精细化处理。实验结果表明:本文算法生成的深度图能够更好地保留细节特征,边界纹理区域的误匹配现象明显改善,可有效降低误匹配率,本文算法在Middlebury数据集误匹配率仅为5.22%。In order to solve the problem of discontinuity in the boundary region of depth map in local stereo matching algorithm,an adaptive guided filtering stereo matching algorithm is proposed based on edge constraint.Firstly,the gradient value and color information are combined to calculate the matching cost;further,based on the local features of the image edge,an adaptive cross region is constructed for the pixels of the image based on the color threshold and boundary conditions,and in the meanwhile,the guided filtering cost aggregation of adaptive window is conducted.Finally,the disparity is calculated by using the winner-takes-all strategy,and the disparity map is refined.Experimental results show that the depth map generated by this algorithm can better retain the detail features,and the mismatch phenomenon in the boundary texture area is significantly improved.This algorithm can effectively reduce the mismatch rate,and the mismatch rate of it in Middlebury dataset is only 5.22%.

关 键 词：立体匹配 引导滤波 代价计算 交叉区域 代价聚合 视差后处理 CANNY算法 加权中值滤波 

分 类 号：TN911.72[电子电信—通信与信息系统]