【摘要】：分割運(yùn)動(dòng)手部時(shí),為了不依賴(lài)不合理的假設(shè)和解決手臉遮擋問(wèn)題,該文提出一種基于膚色、灰度、深度和運(yùn)動(dòng)線索的分割方法。首先,利用灰度與深度光流的方差信息來(lái)自適應(yīng)提取運(yùn)動(dòng)感興趣區(qū)域(Motion Region of Interest,MRoI),以定位人體運(yùn)動(dòng)部位。然后,在MRoI中檢測(cè)滿足膚色與自適應(yīng)運(yùn)動(dòng)約束的角點(diǎn)作為皮膚種子點(diǎn)。接著,根據(jù)膚色、深度與運(yùn)動(dòng)準(zhǔn)則將皮膚種子點(diǎn)生長(zhǎng)為候選手部區(qū)域。最后,通過(guò)邊緣深度梯度、骨架提取和最優(yōu)路徑搜索從候選手部區(qū)域中分割出運(yùn)動(dòng)手部區(qū)域。實(shí)驗(yàn)結(jié)果表明,在不同情形下,特別是手臉遮擋時(shí),該方法可以有效和準(zhǔn)確地分割出運(yùn)動(dòng)手部區(qū)域。
[Abstract]:In order not to rely on unreasonable assumptions and solve the hand-face occlusion problem, this paper proposes a segmentation method based on skin color, gray level, depth and motion clues. Firstly, the variance information of gray level and depth optical flow is used to extract the region of interest (MRoI) adaptively to locate human motion. Then, the corners satisfying skin color and adaptive motion constraints are detected as skin seed points in MRI. Then, the skin seed points are grown into candidate hand regions according to skin color, depth and motion criteria. Finally, the motion hand is segmented from candidate hand regions by edge depth gradient, skeleton extraction and optimal path search. The experimental results show that the proposed method can effectively and accurately segment the moving hand region in different situations, especially in the case of hand-face occlusion.
【作者單位】： 北京工業(yè)大學(xué)電子信息與控制工程學(xué)院;計(jì)算智能與智能系統(tǒng)北京市重點(diǎn)實(shí)驗(yàn)室;
【基金】：國(guó)家自然科學(xué)基金(61375086) 北京市教育委員會(huì)科技計(jì)劃重點(diǎn)項(xiàng)目(KZ201610005010)~~
【分類(lèi)號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 田豐果;吳錦行;吳艷英;寇桂岳;熊，

本文編號(hào)：2228569