国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

首頁> 外文期刊>The Visual Computer >Local stereo matching algorithm with efficient matching cost and adaptive guided image filter
【24h】

Local stereo matching algorithm with efficient matching cost and adaptive guided image filter

機(jī)譯：具有高效匹配成本和自適應(yīng)導(dǎo)引圖像濾波器的局部立體匹配算法

獲取原文
獲取原文并翻譯 | 示例
  • 摘要
  • 著錄項
  • 相似文獻(xiàn)
  • 相關(guān)主題

摘要

To make a matching algorithm to satisfy the requirements of high precision and anti-interference, a novel stereo-matching algorithm with efficient matching cost and adaptive guided image filter is proposed. Firstly, we adopt a modified Census transform with a local texture metric to compute the initial cost. It can make full use of the cross-correlation information between pixels. Meanwhile, we incorporate the Census, color and gradient costs as a mixed matching cost algorithm. Then, we aggregate the costs with guided image filter based on adaptive rectangular support window instead of the traditional fixed support window. The variable kernel window is constructed by the local color similarity and spatial distance. In this way, less occluded points will be included in the support region. On this basis, we adopt integral image to further speed up the computation of this step. Finally, the initial disparity of each pixel is selected using winner takes all optimization and the final disparity maps are gained after post-processing. The experimental results demonstrate that the proposed algorithm not only achieves an average error rate of 5.22 % on the Middlebury stereo benchmark data set, but can also overcome the influence of illumination distortion in the matching effectively.
機(jī)譯：為了使匹配算法滿足高精度和抗干擾的要求，提出了一種具有高匹配成本和自適應(yīng)導(dǎo)引圖像濾波器的立體匹配算法。首先，我們采用帶有局部紋理度量的改進(jìn)的Census變換來計算初始成本。它可以充分利用像素之間的互相關(guān)信息。同時，我們將普查，顏色和漸變成本作為混合匹配成本算法進(jìn)行了合并。然后，我們使用基于自適應(yīng)矩形支持窗口而不是傳統(tǒng)的固定支持窗口的引導(dǎo)圖像過濾器來匯總成本?？勺兒舜翱谟删植款伾嗨贫群涂臻g距離構(gòu)成。以此方式，較少的遮擋點(diǎn)將被包括在支撐區(qū)域中。在此基礎(chǔ)上，我們采用積分圖像來進(jìn)一步加快該步驟的計算。最終，使用優(yōu)勝者進(jìn)行所有優(yōu)化來選擇每個像素的初始視差，并在后處理后獲得最終視差圖。實驗結(jié)果表明，該算法不僅在米德爾伯里立體基準(zhǔn)數(shù)據(jù)集上達(dá)到了5.22％的平均誤碼率，而且可以有效克服照明畸變在匹配中的影響。

著錄項

相似文獻(xiàn)

  • 外文文獻(xiàn)
  • 中文文獻(xiàn)
  • 專利
獲取原文

客服郵箱：kefu@zhangqiaokeyan.com

京公網(wǎng)安備：11010802029741號 ICP備案號：京ICP備15016152號-6 六維聯(lián)合信息科技 (北京) 有限公司?版權(quán)所有

  • 客服微信

  • 服務(wù)號