一种边缘保持立体匹配方法

王孝余; 韩冰; 尚方; 罗军; 黄胜; 张杰

Chinese

您当前的位置：

首页 >

文章列表页 >

一种边缘保持立体匹配方法

更新时间：2026-09-04

- 一种边缘保持立体匹配方法
- An edge-aware stereo matching method
- 微电子学与计算机 2020年37卷第1期页码：59-65
- 作者机构：
  
  1. 国网黑龙江省电力有限公司，国网黑龙江省电力有限公司电力科学研究院,黑龙江,哈尔滨,150030
  2. 成都通甲优博科技有限责任公司，大数据与深度学习实验室,四川,成都,610213
- 作者简介：
- 基金信息：
  
  国家电网公司科技项目 522400180002
- DOI：
  中图分类号：
- 纸质出版：2020
- 稿件说明：
移动端阅览
王孝余, 韩冰, 尚方, 罗军, 黄胜, 张杰. 一种边缘保持立体匹配方法[J]. 微电子学与计算机, 2020, 37(1): 59-65.

WANG Xiao-yu, HAN Bing, SHANG Fang, et al. An edge-aware stereo matching method[J]. 2020, 37(1): 59-65.
王孝余, 韩冰, 尚方, 罗军, 黄胜, 张杰. 一种边缘保持立体匹配方法[J]. 微电子学与计算机, 2020, 37(1): 59-65. DOI：

WANG Xiao-yu, HAN Bing, SHANG Fang, et al. An edge-aware stereo matching method[J]. 2020, 37(1): 59-65. DOI：

摘要

针对边缘处前景和背景视差易混淆问题，提出一种边缘保持立体匹配方法.在代价匹配阶段，采用级联Census变换增强代价的抗噪特性.在代价聚集阶段，引入SLIC超像素分割信息进行快速边缘保持代价聚集.在视差后处理阶段，通过导向十字滤波器进一步优化边缘视差.实验结果表明，文中提出的立体匹配方法在Middlebury测试集以及实际场景获得高质量视差效果，并在边缘处的视差较以往非局部立体匹配方法有所提升.实验还发现在点云上采样时，引入本文所提的导向十字滤波器，可以解决点云在边缘处的过渡.

Abstract

To deal with the confusion of foreground and background disparity at the edge

an edge-aware stereo matching method is proposed. Cascaded census transform is used to enhance the anti-noise ability

during the cost compute stage. SLIC Super-pixel segmentation information is adopted to fast edge-preserving cost aggregation at the cost aggregation stage. The edge disparity is further optimized by the guide cross filter at the stage of disparity post-processing. Experimental results show that the method obtain high quality disparity results in the Middlebury test sets and the actual scene

and the disparity at the edge is improved compared with the previous non-local stereo matching method. The experimental also found that guided cross filter proposed in this paper can solve the transition problem of the point cloud at the edge in the point cloud upsampling technique.

关键词

Keywords

references

C ^\underset{\hat{\ }}{\mathop{\text{C}}}\, Ciǧlala C A. Recursive edge-aware filters for stereo matching[C]//Computer Vision and Pattern Recognition Workshops.IEEE, 2015: 27-34.

THEVENAZ P, SAGE D, UNSER M. Bi-Exponential Edge-Preserving Smoother[J]. IEEE Transactions on Image Processing, 2012, 21(9):3924-3936. DOI: 3924

MEI X, SUN X, DONG W, et al. Segment-tree based cost aggregation for stereo matching[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.L]. 2013: 313-320.

ZEGLAZI O, RZIZA M, AMINE A, et al. A hierarchical stereo matching algorithm based on adaptive support region aggregation method[J]. Pattern Recognition Letters, 2018(112): 205-211. DOI: 205

YANG Q. A non-local cost aggregation method for stereo matching[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. [S.L].IEEE, 2012: 1402-1409.

习路, 陆济湘, 涂婷.基于多尺度卷积神经网络的立体匹配方法[J].计算机工程与设计, 2018 (9): 38. DOI: 38

BARRON J T, ADAMS A, SHIH Y C, et al. Fast bilateral-space stereo for synthetic defocus[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, Massachusetts, 2015: 4466-4474.

HONG G S, KOO M S, SAHA A, et al. Efficient local stereo matching technique using weighted guided image filtering (wgif)[C]//2016 IEEE International Conference on Consumer Electronics (ICCE). Seoul, Korea, IEEE, 2016: 484-485.

MEI X, SUN X, ZHOU M, et al. On building an accurate stereo matching system on graphics hardware[C]//2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops). Barcelona, Spain, IEEE, 2011: 467-474.

王源, 孙启湲.适用于智能视频监控的立体匹配算法[J].计算机工程与设计, 2018, 39(10):189-194. DOI: 189

ZHANG Q, XU L, JIA J. 100+ times faster weighted median filter(WMF)[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus, Ohio, USA.2014: 2830-2837.

陈苏婷, 吴月路, 张艳艳.代价可变的S-census变换算法[J].计算机工程与设计, 2018, 39(2):414-419. DOI: 414

龚文彪, 顾国华, 钱惟贤, 等.基于图像分割和自适应支撑权重的立体匹配算法[J].光学学报, 2015, 35(supl2): s210002. DOI: s210002

ACHANTA R, SHAJI A, SMITH K, et al. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods[J]. IEEE Transactions on Pattern Analysis % Machine Intelligence, 2012, 34(11):2274-2282. DOI: 2274

GEIGER A, ROSER M, UTRTASUN R. Efficient large-scale stereo matching[C]//Asian conference on computer vision. Springer, Berlin, Heidelberg, 2010: 25-38.

LI Y, MIN D, DO M N, et al. Fast guided global interpolation for depth and motion[C]//European Conference on Computer Vision. Springer, Cham, 2016: 717-733.

杨罡, 晋涛, 王大伟, 等.一种改进的代价聚集快速立体匹配方法[J].计算机工程. https://doi.org/10.19678/j.issn.1000-3428.0050790.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

大模型发展综述：从BERT到Deepseek的技术演进

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

面向处理器分支预测单元的Spectre攻击轻量化防御方法

注意力机制与改进密集卷积引导的信息隐藏模型

基于改进RT-DETR的航拍小目标检测算法