本文選題：機(jī)器視覺(jué) + 立體匹配��； 參考：《光學(xué)學(xué)報(bào)》2017年11期

【摘要】：針對(duì)Census變換易受噪聲影響使得立體匹配算法難以獲取高匹配精度的問(wèn)題,提出了一種改進(jìn)Census變換和異常值剔除的抗噪立體匹配算法.在初始匹配代價(jià)階段,該方法首先將窗口鄰域中值作為參考值并通過(guò)映射函數(shù)控制異常值,提高了單像素匹配代價(jià)的可靠性;然后在代價(jià)聚合階段,對(duì)動(dòng)態(tài)聚合窗口中初始代價(jià)值進(jìn)行異常值剔除;最后通過(guò)視差計(jì)算、視差優(yōu)化得到最終的視差圖.在VS2013軟件平臺(tái)上采用Middlebury標(biāo)準(zhǔn)測(cè)試圖對(duì)初始匹配代價(jià)、代價(jià)聚合、最終視差圖階段進(jìn)行測(cè)試.實(shí)驗(yàn)結(jié)果表明,本文算法的抗噪性能優(yōu)于現(xiàn)有Census變換算法,且錯(cuò)誤匹配率達(dá)到5.71%.
[Abstract]:To solve the problem that Census transform is easily affected by noise and it is difficult for stereo matching algorithm to obtain high matching accuracy, a new anti-noise stereo matching algorithm is proposed, which is based on improved Census transform and outliers elimination. In the initial matching cost stage, the window neighborhood median is first used as the reference value and the outlier value is controlled by the mapping function, which improves the reliability of the matching cost of a single pixel, and then in the cost aggregation stage, The outlier value is eliminated from the initial generation value in the dynamic aggregation window, and the parallax graph is obtained by the parallax calculation. Middlebury standard test diagram is used on VS2013 software platform to test initial matching cost, cost aggregation and final parallax phase. Experimental results show that the proposed algorithm has better anti-noise performance than the existing Census transform algorithm, and the error matching rate is 5.71%.
【作者單位】： 上海大學(xué)通信與信息工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(61471230)
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

中國(guó)期刊全文數(shù)據(jù)庫(kù) 前10條

1 雷磊;鄭江濱;宋雪梅;;基于改進(jìn)Census變換的立體匹配算法[J];計(jì)算機(jī)應(yīng)用研究;2013年10期

2 王軍政;朱華健;李靜;;一種基于Census變換的可變權(quán)值立體匹配算法[J];北京理工大學(xué)學(xué)報(bào);2013年07期

3 寧曉斐;胡波;趙磊;_澄鬧，

本文編號(hào)：1961108