摘 要:為解決復(fù)雜空中背景下紅外弱小目標(biāo)的檢測,提出一種新的基于多向梯度的背景預(yù)測方法。該方法根據(jù)云層邊緣區(qū)域、平緩背景區(qū)域及弱小目標(biāo)所呈現(xiàn)的不同梯度特點(diǎn),采取不同方法分別進(jìn)行預(yù)測;基本保留云層邊緣區(qū)域和平緩背景區(qū)域的點(diǎn),而對弱小目標(biāo)區(qū)域采用鄰域低灰度值點(diǎn)進(jìn)行預(yù)測。然后經(jīng)過背景消除和閾值分割,將弱小目標(biāo)檢測出來。仿真結(jié)果表明,該算法對復(fù)雜空中背景預(yù)測有很高的準(zhǔn)確性,能夠更加有效地抑制云層邊緣引起的虛警,將紅外弱小目標(biāo)點(diǎn)檢測出來。
關(guān)鍵詞:背景預(yù)測; 多向梯度; 閾值; 弱小目標(biāo)
中圖分類號:TN915.76 文獻(xiàn)標(biāo)識碼:A
文章編號:1004-373X(2010)12-0103-04
Dim Infrared Targets Detection Based on Multi-gradient Background Prediction
LI Xiao-long, WANG Jiang-an, MA Zhi-guo
(Academy of Electronic Engineering, Naval University of Engineering, Wuhan 430033, China)
Abstract:In order to solve the detection problems of dim infrared targets in the complicated air background, a new algorithm of background prediction based on multi-orientation gradient is presented. The different prediction methods are respectively adopted according to the different characteristics of gradients for the areas of cloud′s edge, flat background and dim infrared targets. For the points in the areas of the cloud′s edge and flat background, the most similar point is sought as a predictive point. For the dim infrared targets, the point with lower gray value in neighborhood is used as a predictive point. Then the dim infrared targets are detected after the background elimination and threshold segmentation. The simulation results show that this algorithm has a high accuracy of prediction for the dim IR targets in the complicated air background, can effectively suppress 1 alarms caused by the edge of cloud, and can detect dim infrared targets.
Keywords:background prediction; multi-gradient; threshold segmentation; small dim target
0 引 言
在現(xiàn)代化的高技術(shù)戰(zhàn)爭中,能及時(shí)地發(fā)現(xiàn)目標(biāo),實(shí)現(xiàn)迅速有效的攻擊,是機(jī)載武器系統(tǒng)發(fā)展的一個(gè)趨勢。對于遠(yuǎn)距離目標(biāo),且對比度較低的情況下,要保證可靠、準(zhǔn)確地檢測并跟蹤目標(biāo)是很困難的。
早期圍繞背景預(yù)測的紅外弱小目標(biāo)檢測技術(shù)使用較多的是中值濾波器和匹配濾波器,到后來提出的形態(tài)學(xué)濾波器等,但得到的作用效果有限。
目前,提出了一些新的背景預(yù)測方法,包括基本背景預(yù)測法、自適應(yīng)背景預(yù)測法、分塊背景預(yù)測法、基于神經(jīng)網(wǎng)絡(luò)的背景預(yù)測方法等。
但當(dāng)背景起伏較大,圖像信噪比較低時(shí),在背景的起伏邊緣就會(huì)出現(xiàn)較多的虛警。為了盡可能地對邊緣進(jìn)行準(zhǔn)確預(yù)測,使殘差圖中邊緣被極大抵消。
文獻(xiàn)[ 1] 和文獻(xiàn)[ 2] 提出了新的背景預(yù)測和小目標(biāo)檢測方法。……