Colour-weighted rank transform and improved dynamic programming for fast and accurate stereo matching

Mohamed Hallek, Randa Khemiri, Ali Algarwi, Abdellatif Mtibaa, Mohamed Atri
{"title":"Colour-weighted rank transform and improved dynamic programming for fast and accurate stereo matching","authors":"Mohamed Hallek, Randa Khemiri, Ali Algarwi, Abdellatif Mtibaa, Mohamed Atri","doi":"10.1080/13682199.2023.2202096","DOIUrl":null,"url":null,"abstract":"Real-time stereo matching with high accuracy is a dynamic research topic; it is attractive in diverse computer vision applications. This paper presents a stereo-matching algorithm that produces high-quality disparity map while maintaining real-time performance. The proposed stereo-matching method is based on three per-pixel difference measurements with adjustment elements. The absolute differences and the gradient matching are combined with a colour-weighted extension of complete rank transform to reduce the effect of radiometric distortion. The disparity calculation is realized using improved dynamic programming that optimizes along and across all scanlines. It solves the inter-scanline inconsistency problem and increases the matching accuracy. The proposed algorithm is implemented on parallel high-performance graphic hardware using the Compute Unified Device Architecture to reach over 240 million disparity evaluations per second. The processing speed of our algorithm reaches 98 frames per second on 240 × 320-pixel images and 32 disparity levels. Our method ranks fourth in terms of accuracy and runtime for quarter-resolution images in the Middlebury stereo benchmark.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Imaging Science Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/13682199.2023.2202096","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Real-time stereo matching with high accuracy is a dynamic research topic; it is attractive in diverse computer vision applications. This paper presents a stereo-matching algorithm that produces high-quality disparity map while maintaining real-time performance. The proposed stereo-matching method is based on three per-pixel difference measurements with adjustment elements. The absolute differences and the gradient matching are combined with a colour-weighted extension of complete rank transform to reduce the effect of radiometric distortion. The disparity calculation is realized using improved dynamic programming that optimizes along and across all scanlines. It solves the inter-scanline inconsistency problem and increases the matching accuracy. The proposed algorithm is implemented on parallel high-performance graphic hardware using the Compute Unified Device Architecture to reach over 240 million disparity evaluations per second. The processing speed of our algorithm reaches 98 frames per second on 240 × 320-pixel images and 32 disparity levels. Our method ranks fourth in terms of accuracy and runtime for quarter-resolution images in the Middlebury stereo benchmark.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
颜色加权秩变换和改进的动态规划,用于快速准确的立体匹配
高精度实时立体匹配是一个动态的研究课题;它在各种计算机视觉应用中具有很大的吸引力。本文提出了一种能够在保证实时性的前提下生成高质量视差图的立体匹配算法。所提出的立体匹配方法是基于三个带有平差元素的每像素差分测量。将绝对差和梯度匹配与完全秩变换的颜色加权扩展相结合,以减小辐射失真的影响。视差计算是通过改进的动态规划实现的,该规划沿着所有扫描线进行优化。解决了扫描线间不一致的问题,提高了匹配精度。该算法在并行高性能图形硬件上使用计算统一设备架构实现,每秒可达到2.4亿次视差评估。在240 × 320像素、32个视差等级的图像上,算法的处理速度达到98帧/秒。在米德尔伯里立体基准中,我们的方法在四分之一分辨率图像的精度和运行时间方面排名第四。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Impact of the Internet of Medical Things on Artificial Intelligence-enhanced medical imaging systems from 2019 to 2023 Advancements in adversarial generative text-to-image models: a review Enhancing image encryption security through integration multi-chaotic systems and mixed pixel-bit level Unsupervised low-light image enhancement by data augmentation and contrastive learning Minimum error threshold segmentation method for SAR image based on Rayleigh distribution assumption
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1