摘要
在立体匹配问题中,基于3D标签的算法可以取得更高精度的亚像素视差图。针对3D标签的随机初始化问题,提出一种基于超像素结构与三角剖分的标签初始化方法。利用基于超像素边界提取到的特征点构建三角剖分,生成初始3D标签;针对图割算法迭代优化3D标签时效率的问题,在超像素结构上利用图割算法进行全局优化3D标签,迭代中加入对当前标签状态的假设扩展标签候选,提升了标签搜索效率。在Middlebury2014数据集上对方法进行验证,实验结果表明,所提方法的平均误匹配率(8.31%)低于LocalExp算法的平均误匹配率(8.39%),并且处理单幅图像耗费的平均时间约为LocalExp算法的70%。
The algorithm based on a 3D label can obtain a more accurate subpixel disparity map in the stereo matching problem.To overcome the random initialization of 3D labels,we proposed a label initialization approach based on superpixel structure and triangulation.An initial 3D label is generated by triangulating the feature points retrieved from the superpixel boundary.To increase the efficiency of the graph cut approach in iterative optimization of 3D labels,we conduct optimization on the superpixel structure,adding the hypothesis of current label state throughout the iteration to expand the label candidates,which improves label search efficiency.Experiments on the Middlebury2014 dataset demonstrate that the proposed approach has a lower average error rate(8.31%)than the LocalExp algorithm(8.39%),and the average processing time for single image is~70%that of the LocalExp algorithm.
作者
李萌昊
葛宝臻
权佳宁
陈其博
Li Menghao;Ge Baozhen;Quan Jianing;Chen Qibo(School of Precision Instrument and OptoElectronics Engineering,Tianjin University,Tianjin 300072,China;Key Laboratory of OptoElectronics Information Technology,Ministry of Education,Tianjin 300072,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2022年第8期339-347,共9页
Laser & Optoelectronics Progress
基金
国家自然科学基金重点项目(61535008)。
关键词
机器视觉
立体匹配
3D标签
超像素
三角剖分
图割
machine vision
stereo matching
3D label
superpixel
triangulation
graph cut
