1.山东大学机械工程学院 济南 250061;2.山东大学高效洁净机械制造教育部重点实验室 济南 250061;3.山东大学机械工程国家级实验教学示范中心 济南 250061
TP301.6
Zhang Jie
1.School of Mechanical Engineering, Shandong University, Jinan 250012; 2. Key Laboratory of Efficient and Clean Machinery Manufacturing of Ministry of Education, Shandong University, Jinan 250012; 3. Shandong University Mechanical Engineering National Experimental Teaching Demonstration Center, Jinan 250012Wang Zengcai
1.School of Mechanical Engineering, Shandong University, Jinan 250012; 2. Key Laboratory of Efficient and Clean Machinery Manufacturing of Ministry of Education, Shandong University, Jinan 250012; 3. Shandong University Mechanical Engineering National Experimental Teaching Demonstration Center, Jinan 250012Yan Ming
1.School of Mechanical Engineering, Shandong University, Jinan 250012; 2. Key Laboratory of Efficient and Clean Machinery Manufacturing of Ministry of Education, Shandong University, Jinan 250012; 3. Shandong University Mechanical Engineering National Experimental Teaching Demonstration Center, Jinan 2500121.School of Mechanical Engineering, Shandong University, Jinan 250012; 2. Key Laboratory of Efficient and Clean Machinery Manufacturing of Ministry of Education, Shandong University, Jinan 250012; 3. Shandong University Mechanical Engineering National Experimental Teaching Demonstration Center, Jinan 250012
针对传统Census算法过于依赖中心像素，从而易受噪声影响和AD-Census算法不能充分利用不同算法的优势等问题，本文提出了一种改进的Census变换和自适应权重的立体匹配算法。首先利用Census变换窗口内的均值及中心点与四个方向邻域像素的信息，将相近像素点自动归为一类，提高了Census变换对噪声的鲁棒性。其次引入SAD算法与Sobel边缘检测，根据梯度信息来确定SAD与Census变换的权重，提高了算法在不同区域的适应性。最后采用十字交叉域的代价聚合方式及后续优化得到最终的视差图。将不同图像的视差图在Middlebury平台上进行验证，本文所提算法的平均误差为9.33%较AD-Census算法下降了3.39%。较其它算法在视差不连续区域及重复纹理区具有更好的匹配精度，对噪声及光照也具有更好的鲁棒性。
Aiming at the problem that the traditional Census algorithm is too dependent on the center pixel, which is susceptible to noise, and the AD-Census algorithm can not make full use of the advantages of different algorithms, this paper proposes an improved Census transformation and adaptive weight stereo matching algorithm. Firstly, the mean value of the Census transform window and the pixel information of the center point and neighborhood in four directions are used to automatically classify the close pixels into one class, which improves the robustness of the Census transform against noise. Secondly, the SAD algorithm and Sobel edge detection are introduced, and the weight of SAD and Census transform is determined according to the gradient information, which improves the adaptability of the algorithm in different regions. Finally, the final disparity map is obtained by the cost aggregation method of the cross-domain and subsequent optimization. The parallax maps of different images are verified on the Middlebury platform, and the average error of the proposed algorithm is 9.33%, which is 3.39% lower than the AD-Census algorithm. Compared with other algorithms, the algorithm has better matching accuracy in the parallax discontinuous region and repeated texture region, and better robustness against noise and light.
张杰,王增才,闫明.基于改进Census变换和自适应权重的立体匹配算法[J].电子测量技术,2022,45(23):45-52
复制
