自適應(yīng)模態(tài)選擇的魯棒目標(biāo)跟蹤方法
發(fā)布時(shí)間：2019-03-24 14:33
【摘要】：在多模態(tài)跟蹤過程中,為了避免低質(zhì)量模態(tài)的噪聲影響和提高跟蹤方法的效率,提出了一種基于自適應(yīng)模態(tài)選擇的目標(biāo)跟蹤方法,能夠選擇較好的模態(tài)進(jìn)行跟蹤。具體地,對(duì)于每個(gè)模態(tài),使用聚類方法將目標(biāo)區(qū)域及其周圍背景區(qū)域各聚為若干個(gè)子類,然后通過它們子類之間的特征差異衡量目標(biāo)和周圍背景的判別性(即模態(tài)質(zhì)量),選擇判別性最大的模態(tài)對(duì)目標(biāo)使用相關(guān)性濾波算法進(jìn)行跟蹤。同時(shí),為了維持各個(gè)模態(tài)的目標(biāo)模型的有效性,提出了一種雙閾值策略更新選擇和未被選擇模態(tài)的跟蹤模型。在7組熱紅外和可見光視頻對(duì)上進(jìn)行了實(shí)驗(yàn),驗(yàn)證了該方法的有效性,且跟蹤速度達(dá)到141 f/s。
[Abstract]:In order to avoid the influence of low-quality mode noise and improve the efficiency of tracking method, a target tracking method based on adaptive mode selection is proposed in the multi-mode tracking process, which can select better modes for tracking. Specifically, for each modal, clustering methods are used to cluster the target region and its surrounding background regions into several sub-categories, and then measure the discriminance (i.e. modal quality) of the target and surrounding background through the characteristic differences between their subcategories. The most discriminant mode is selected to track the target using correlation filtering algorithm. At the same time, in order to maintain the effectiveness of the target model of each mode, a tracking model with double threshold strategy update selection and unselected mode is proposed. Experiments on 7 groups of thermal infrared and visible video pairs show that the proposed method is effective and the tracking speed is up to 141 fxs.
【作者單位】： 安徽大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】：“十二五”科技部支撐計(jì)劃項(xiàng)目No.2015BAK24B01~~
【分類號(hào)】：TN713
本文編號(hào)：2446412
[Abstract]:In order to avoid the influence of low-quality mode noise and improve the efficiency of tracking method, a target tracking method based on adaptive mode selection is proposed in the multi-mode tracking process, which can select better modes for tracking. Specifically, for each modal, clustering methods are used to cluster the target region and its surrounding background regions into several sub-categories, and then measure the discriminance (i.e. modal quality) of the target and surrounding background through the characteristic differences between their subcategories. The most discriminant mode is selected to track the target using correlation filtering algorithm. At the same time, in order to maintain the effectiveness of the target model of each mode, a tracking model with double threshold strategy update selection and unselected mode is proposed. Experiments on 7 groups of thermal infrared and visible video pairs show that the proposed method is effective and the tracking speed is up to 141 fxs.
【作者單位】： 安徽大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】：“十二五”科技部支撐計(jì)劃項(xiàng)目No.2015BAK24B01~~
【分類號(hào)】：TN713
【相似文獻(xiàn)】
相關(guān)期刊論文 前4條
1 李波睿;慕春棣;白天明;柳志娟;;一種混合的擴(kuò)展目標(biāo)跟蹤方法[J];航空學(xué)報(bào);2014年05期
2 ;紅外成象制導(dǎo)與光電對(duì)抗研討會(huì)會(huì)議部分論文文摘(下)[J];紅外與激光技術(shù);1992年03期
3 宋新;王魯平;王平;沈振康;;基于改進(jìn)均值位移的紅外目標(biāo)跟蹤方法[J];紅外與毫米波學(xué)報(bào);2007年06期
4 ;[J];;年期
相關(guān)博士學(xué)位論文 前1條
1 李波;基于隨機(jī)有限集理論的VTS目標(biāo)跟蹤方法研究[D];大連海事大學(xué);2015年
相關(guān)碩士學(xué)位論文 前2條
1 劉遠(yuǎn);基于形狀估計(jì)的隨機(jī)集多擴(kuò)展目標(biāo)跟蹤方法研究[D];西安電子科技大學(xué);2015年
2 陳雅珍;基于隨機(jī)集的擴(kuò)展目標(biāo)跟蹤方法研究[D];西安電子科技大學(xué);2014年
，本文編號(hào)：2446412
本文鏈接：http://sikaile.net/kejilunwen/dianzigongchenglunwen/2446412.html
最近更新
教材專著
