激光与光电子学进展, 2021, 58 (2): 0215008, 网络出版: 2021-01-11
基于改进Census变换与梯度融合的立体匹配算法 下载: 988次
Stereo Matching Algorithm Based on Improved Census Transform and Gradient Fusion
图 & 表
图 2. 不同算法得到的Census变换窗口。(a)不同的窗口;(b)中心像素值;(c)窗口像素的平均值;(d)本算法
Fig. 2. Census transform windows obtained by different algorithms. (a) Different windows; (b) center pixel value; (c) average value of window pixels; (d) our algorithm
图 3. 不同算法得到的视差图。(a)左图像;(b)右图像;(c)真实视差图;(d)CT;(e)Impro-CT;(f)GRD;(g)本算法
Fig. 3. Disparity images obtained by different algorithms. (a) Left image; (b) right image; (c) true disparity image; (d) CT; (e) impro-CT; (f) GRD; (g) our algorithm
图 4. 本算法得到的Aloe视差图。(a)左图像;(b)右图像;(c)真实视差图;(d)多尺度空间下的视差图;(e)最终视差图
Fig. 4. Aloe disparity images obtained by our algorithm. (a) Left image; (b) right image; (c) real disparity image; (d) disparity image in multi-scale space; (e) final disparity image
图 5. 不同算法在不同条件下得到的视差图。(a)左图像;(b)右图像;(c)真实视差图;(d)CT;(e)Impro-CT;(f)GRD;(g)本算法
Fig. 5. Disparity images obtained by different algorithms under different conditions. (a) Left image; (b) right image; (c) ground truth; (d) CT; (e) Impro-CT; (f) GRD; (g) our algorithm
表 2不同代价算法的误匹配率(非遮挡区域)
Table2. Mismatch rates of different cost algorithms (non-occluded area) unit: %
|
表 3不同代价算法的误匹配率(遮挡区域)
Table3. Mismatch rates of different cost algorithms (occlusion area) unit: %
|
萧红, 田川, 张毅, 魏博, 康家旗. 基于改进Census变换与梯度融合的立体匹配算法[J]. 激光与光电子学进展, 2021, 58(2): 0215008. Hong Xiao, Chuan Tian, Yi Zhang, Bo Wei, Jiaqi Kang. Stereo Matching Algorithm Based on Improved Census Transform and Gradient Fusion[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0215008.