礦井車載視頻圖像穩(wěn)像算法研究
發(fā)布時(shí)間:2018-06-30 09:59
本文選題:礦井視頻監(jiān)控 + 車載視頻 ; 參考:《工礦自動(dòng)化》2017年11期
【摘要】:針對(duì)礦井車載攝像系統(tǒng)拍攝的視頻因含有前景運(yùn)動(dòng)目標(biāo)及高噪聲造成的全局運(yùn)動(dòng)矢量估計(jì)誤匹配率高、實(shí)時(shí)性較差等問題,提出了一種基于ORB特征匹配與改進(jìn)粒子濾波的礦井車載視頻圖像穩(wěn)像算法。在運(yùn)動(dòng)矢量估計(jì)階段,采用ORB算法提取圖像特征點(diǎn);采用基于圖像塊的連續(xù)3幀間差分法,聯(lián)合時(shí)空一致性準(zhǔn)則快速剔除前景運(yùn)動(dòng)區(qū)域的特征點(diǎn);結(jié)合前景標(biāo)記區(qū)域,對(duì)特征點(diǎn)位置進(jìn)行初次篩選,對(duì)保留下來的背景特征點(diǎn)進(jìn)行配準(zhǔn);利用仿射變換模型實(shí)現(xiàn)幀間運(yùn)動(dòng)矢量的估計(jì)。在運(yùn)動(dòng)濾波階段,采用基于估計(jì)窗的實(shí)時(shí)粒子濾波算法濾除抖動(dòng)分量,獲得補(bǔ)償參數(shù)。實(shí)驗(yàn)結(jié)果表明,該算法有效避免了前景運(yùn)動(dòng)目標(biāo)對(duì)穩(wěn)像精度的影響,且具有較快的處理速度。
[Abstract]:Aiming at the problems of high mismatch rate of global motion vector estimation caused by the existence of foreground moving target and high noise in the video recorded by the vehicle camera system in mine, the real time performance of the video is poor, and so on. An image stabilization algorithm based on Orb feature matching and improved particle filter is proposed. In motion vector estimation stage, Orb algorithm is used to extract image feature points, image block based continuous three frame difference method is used to quickly eliminate feature points of foreground moving region by using spatio-temporal consistency criterion, and foreground tagging region is combined. The location of feature points is first selected, the remaining background feature points are registered, and the motion vectors between frames are estimated by affine transformation model. In the phase of motion filtering, the real time particle filter algorithm based on estimation window is used to filter the jitter component and obtain the compensation parameters. Experimental results show that the proposed algorithm can effectively avoid the influence of foreground moving targets on image stabilization accuracy and has a faster processing speed.
【作者單位】: 中國(guó)礦業(yè)大學(xué)信息與控制工程學(xué)院;徐州市公安局科技處;
【基金】:江蘇省“六大人才高峰”高層次人才培養(yǎng)項(xiàng)目(2015-ZBZZ-009)
【分類號(hào)】:TD76;TP391.41
【相似文獻(xiàn)】
相關(guān)碩士學(xué)位論文 前1條
1 牛維;頭盔攝像頭視頻的穩(wěn)像算法研究[D];西北大學(xué);2014年
,本文編號(hào):2085898
本文鏈接:http://www.sikaile.net/kejilunwen/anquangongcheng/2085898.html
最近更新
教材專著