电光与控制, 2023, 30 (3): 33, 网络出版: 2023-04-03  

基于自适应窗口和改进Census变换的半全局立体匹配算法

Semi-global Stereo Matching Algorithm Based on Adaptive Window and Improved Census Transform
作者单位
东华理工大学机械与电子工程学院, 南昌 330000
摘要
针对基于Census变换的立体匹配算法匹配精度不理想、易受噪声干扰的问题, 提出一种自适应窗口结合改进Census变换的方法。通过自适应选择变换窗口大小, 并在Census变换中引入噪声容限参数, 且将其改进Census代价与RGB颜色差值代价加权融合, 再采用四路径代价聚合策略完成初始代价聚合, 最后用WTA算法计算初始视差后通过后处理优化得到最终视差。实验结果表明所提算法误匹配率较低, 抗噪性能有较好提升。
Abstract
Aiming at the problem that stereo matching algorithm based on Census transform has poor matching accuracy and is susceptible to noise interference, a method combining adaptive window with improved Census transform is proposed.The size of the transform window is selected adaptively, the noise tolerance parameter is introduced into the Census transform to calculate the cost, and the improved Census cost and RGB color difference cost are weighted and fused.Then, the four-path cost aggregation strategy is adopted to complete the initial cost aggregation.Finally, the WTA algorithm is used to calculate the initial disparity, and the final disparity is obtained through post-processing optimization.The experimental results show that the proposed algorithm has low mismatching rate and better anti-noise performance.
参考文献

[1] 卢艳军,王诗宇,张太宁,等.针对目标跟踪过程的双目视觉测距方法研究[J].电光与控制,2020, 27(1):60-63, 101.

[2] 王曹松.基于双目视觉的障碍物距离检测系统[D].无锡:江南大学,2021.

[3] LIM J, KIM Y, LEE S.A census transform-based robust stereo matching under radiometric changes[C]//Signal and Information Processing Association Annual Summit and Conference.Jeju:IEEE, 2016:782-786.

[4] 门宇博,马宁,张国印,等.非参数变换和改进动态规划的立体匹配算法[J].哈尔滨工业大学学报,2015, 47(3):60-65.

[5] 刘建国,俞力,柳思健,等.基于改进Census变换和多尺度空间的立体匹配算法[J].华南理工大学学报(自然科学版),2017, 45(12):43-49.

[6] 范海瑞,杨帆,潘旭冉,等.一种改进Census变换与梯度融合的立体匹配算法[J].光学学报,2018, 38(2):267-277.

[7] 祝世平,闫利那,李政.基于改进Census变换和动态规划的立体匹配算法[J].光学学报,2016, 36(4):216-224.

[8] 周喆,沈建新,韩鹏,等.基于Census变换和引导滤波的立体匹配算法[J].应用光学,2020, 41(1):79-85.

[9] 刘振友,郑茜颖,程树英.基于改进Census变换的抗噪立体匹配算法[J].半导体光电,2021, 42(1):100-105.

[10] HERNANDEZ-JUAREZ D, CHACN A, ESPINOSA A, et al.Embedded real-time stereo estimation via semi-global matching on the GPU[J].Procedia Computer Science, 2016, 80:143-153.

[11] 马瑞浩,朱枫,吴清潇,等.基于图像分割的稠密立体匹配算法[J].光学学报,2019, 39(3):240-248.

[12] 黄超,赵华治.根据灰度值信息自适应窗口的半全局匹配[J].中国图象图形学报,2019, 24(8):1381-1390.

[13] BAEK E T, HO Y S.Cost aggregation with guided image filter and superpixel for stereo matching[C]//Signal and Information Processing Association Annual Summit and Conference.Jeju:IEEE, 2016:697-701.

[14] 刘杰,张建勋,代煜,等.基于跨尺度引导图像滤波的稠密立体匹配[J].光学学报,2018, 38(1):232-238.

[15] 梁海波,邹佳玲.改进的非参数Census变换立体匹配算法[J].吉林大学学报(理学版),2019, 57(5):1163-1168.

胡志新, 梅紫俊, 王涛, 曹刘洋. 基于自适应窗口和改进Census变换的半全局立体匹配算法[J]. 电光与控制, 2023, 30(3): 33. HU Zhixin, MEI Zijun, WANG Tao, CAO Liuyang. Semi-global Stereo Matching Algorithm Based on Adaptive Window and Improved Census Transform[J]. Electronics Optics & Control, 2023, 30(3): 33.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!