本文關(guān)鍵詞： 機(jī)載視頻跟蹤 建筑區(qū)檢測(cè) 局部描述子 復(fù)雜場(chǎng)景　出處：《電子學(xué)報(bào)》2016年06期 　論文類型：期刊論文

【摘要】：特定建筑區(qū)域的自動(dòng)檢測(cè)及跟蹤在機(jī)載遙感視頻數(shù)據(jù)處理中具有重要意義,是非懸停機(jī)載平臺(tái)面向任務(wù)對(duì)地搜尋及火控系統(tǒng)引導(dǎo)的關(guān)鍵技術(shù)之一.針對(duì)實(shí)際復(fù)雜應(yīng)用場(chǎng)景,提出一種特定建筑區(qū)檢測(cè)跟蹤算法.首先,將離線獲得的目標(biāo)區(qū)參考圖進(jìn)行局部描述子特征提取.目標(biāo)區(qū)在線檢測(cè)階段,為保證時(shí)效性,提出基于邊緣顯著性的快速SIFT(Scale Invariant Feature Transform)特征提取方法,對(duì)待檢測(cè)大視場(chǎng)圖像中疑似建筑區(qū)域提取局部描述子特征;并通過(guò)設(shè)計(jì)層次化的特征點(diǎn)匹配方法實(shí)現(xiàn)目標(biāo)區(qū)的高可靠檢測(cè).目標(biāo)區(qū)在線跟蹤階段,通過(guò)自適應(yīng)開(kāi)窗及軌跡預(yù)測(cè)技術(shù)有效圈定疑似目標(biāo)區(qū),并在圈定的有限范圍內(nèi)進(jìn)行最終目標(biāo)確認(rèn)及穩(wěn)定跟蹤.實(shí)測(cè)數(shù)據(jù)仿真結(jié)果表明,本文提出的算法能在復(fù)雜場(chǎng)景條件下,實(shí)現(xiàn)對(duì)特定建筑區(qū)域的快速檢測(cè)及穩(wěn)定跟蹤.可為將來(lái)實(shí)際系統(tǒng)應(yīng)用提供關(guān)鍵技術(shù)支撐.
[Abstract]:Automatic detection and tracking of specific building areas is of great significance in airborne remote sensing video data processing. It is one of the key technologies of mission-to-ground search and fire control system guidance for non-hovering airborne platforms. A detection and tracking algorithm for specific building area is proposed. Firstly, the local description sub-feature is extracted from the off-line reference map of the target area. A fast SIFT(Scale Invariant Feature transform (SIFT(Scale Invariant Feature transform) feature extraction method based on edge salience is proposed to extract local descriptor features for suspected building areas in large field of view images. The high reliability detection of the target area is realized by designing hierarchical feature point matching method. In the online tracking phase of the target area, the suspected target area is effectively delineated by adaptive window opening and trajectory prediction techniques. And the final target confirmation and stable tracking are carried out in the limited range of the delineation. The simulation results of the measured data show that the algorithm proposed in this paper can be used in complex scene conditions. The rapid detection and stable tracking of the specific building area can provide key technical support for the practical application of the system in the future.
【作者單位】： 北方工業(yè)大學(xué)電子信息工程學(xué)院;北京理工大學(xué)雷達(dá)技術(shù)研究所;
【基金】：國(guó)家自然科學(xué)基金(No.61171194) 北京市教委科技計(jì)劃面上項(xiàng)目(No.KM201610009004)
【分類號(hào)】：TP751

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 葛世清;多麗彩擴(kuò)新品迭出——記國(guó)家照相機(jī)質(zhì)量監(jiān)督檢驗(yàn)中心首家進(jìn)行彩擴(kuò)設(shè)備質(zhì)量檢測(cè)跟蹤的企業(yè)[J];照相機(jī);2000年12期

2 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 游波;張明敏;;基于匹配場(chǎng)和長(zhǎng)項(xiàng)積分混合處理的多模式檢測(cè)跟蹤一體化算法[A];2004年全國(guó)水聲學(xué)學(xué)術(shù)會(huì)議論文集[C];2004年

，

本文編號(hào)：1552898