本文選題：視頻監(jiān)控　切入點(diǎn)：在線跟蹤　出處：《電子學(xué)報(bào)》2017年03期 　論文類型：期刊論文

【摘要】：多目標(biāo)在線跟蹤是視頻監(jiān)控中的關(guān)鍵問題之一.針對(duì)日益增長(zhǎng)的智能化視頻監(jiān)控的需求,提出了一種基于模糊空時(shí)線索的多目標(biāo)在線跟蹤算法.在該算法中,引入模糊空時(shí)多屬性特征定義距離函數(shù),利用模糊C均值聚類優(yōu)化得到交叉隸屬度矩陣,實(shí)現(xiàn)目標(biāo)與觀測(cè)間的數(shù)據(jù)關(guān)聯(lián).為了減少錯(cuò)誤的軌跡起始,利用空時(shí)線索定義了遮擋度函數(shù),判別出新目標(biāo)并起始相應(yīng)的目標(biāo)軌跡.實(shí)驗(yàn)結(jié)果表明,本文算法能夠準(zhǔn)確地估計(jì)出目標(biāo)的運(yùn)動(dòng)軌跡.本文算法可應(yīng)用于視頻監(jiān)控、安防以及自動(dòng)駕駛等領(lǐng)域.
[Abstract]:Multi-target online tracking is one of the key problems in video surveillance. Aiming at the increasing demand of intelligent video surveillance, a multi-target online tracking algorithm based on fuzzy space-time clues is proposed. The distance function is defined by fuzzy space-time multi-attribute feature, and the cross-membership matrix is obtained by fuzzy C-means clustering optimization. The data correlation between target and observation is realized. The occlusion function is defined by space-time cues to distinguish new targets and start the corresponding target trajectories. The experimental results show that the proposed algorithm can accurately estimate the moving trajectories of the targets, and the proposed algorithm can be applied to video surveillance. Areas such as security and autopilot.
【作者單位】： 深圳大學(xué)ATR國(guó)防科技重點(diǎn)實(shí)驗(yàn)室;
【基金】：國(guó)家自然科學(xué)基金(No.61301074,No.61271107) 廣東省自然科學(xué)基金(No.S2012010009417) 廣東省科技廳產(chǎn)學(xué)研協(xié)同創(chuàng)新成果轉(zhuǎn)化項(xiàng)目(No.509111098127) 深圳市科技計(jì)劃項(xiàng)目(No.JCYJ20140418095735618) 國(guó)防預(yù)研基金項(xiàng)目(No.91400C800501140C80340)
【分類號(hào)】：TP391.41;TN948.6

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 程健,曾以亮;IPv6在產(chǎn)品特性在線跟蹤中的應(yīng)用[J];機(jī)械與電子;2004年07期

，

本文編號(hào)：1590335