復(fù)雜地面背景下目標(biāo)魯棒跟蹤技術(shù)研究
發(fā)布時(shí)間：2018-07-24 08:08
【摘要】：復(fù)雜地面背景下目標(biāo)魯棒跟蹤技術(shù)是實(shí)現(xiàn)無人機(jī)對地偵察打擊任務(wù)的基礎(chǔ),也是各類精確制導(dǎo)武器在末制導(dǎo)階段實(shí)現(xiàn)實(shí)時(shí)準(zhǔn)確捕獲目標(biāo)的關(guān)鍵。然而由于地面場景中存在光照變化、遮擋、尺度縮放、旋轉(zhuǎn)、非剛體形變、雜亂背景干擾、由物體突然運(yùn)動(dòng)引起的圖像模糊、相似物干擾等挑戰(zhàn)因素,對運(yùn)動(dòng)單目標(biāo)進(jìn)行魯棒跟蹤仍面臨諸多困難。本文從一個(gè)典型跟蹤系統(tǒng)包含的四個(gè)組成部分入手展開研究,以半監(jiān)督在線學(xué)習(xí)理論為基礎(chǔ),提出相應(yīng)的跟蹤算法以克服上述因素的影響。主要研究內(nèi)容包括以下幾方面:1、介紹了半監(jiān)督在線學(xué)習(xí)的基本理論及兩類典型的基于半監(jiān)督在線學(xué)習(xí)的目標(biāo)跟蹤方法:Online MIL跟蹤與TLD跟蹤。它們對開展復(fù)雜地面背景下目標(biāo)魯棒跟蹤技術(shù)研究具有重要的指導(dǎo)及借鑒作用。Online MIL跟蹤用包袋來封裝具有相近標(biāo)簽的實(shí)例,并用包袋標(biāo)簽代替實(shí)例標(biāo)簽,通過對樣本標(biāo)簽進(jìn)行模糊化處理以弱化監(jiān)督效應(yīng),能較好的解決樣本模糊問題,其實(shí)質(zhì)是對目標(biāo)外觀表示方法的創(chuàng)新。TLD跟蹤提出了一種新的目標(biāo)跟蹤框架,利用在線學(xué)習(xí)機(jī)制融合跟蹤結(jié)果與檢測結(jié)果,同時(shí)在線學(xué)習(xí)也使跟蹤算法具有”記憶”功能,當(dāng)丟失的目標(biāo)在視場中重現(xiàn)時(shí),能夠重新捕獲到該目標(biāo),它拓展和完善了傳統(tǒng)的基于檢測的目標(biāo)跟蹤理論,彌補(bǔ)了僅依靠純檢測或純跟蹤方法存在的跟蹤性能不穩(wěn)定的不足,實(shí)質(zhì)是對跟蹤方法的創(chuàng)新。2、提出了一種具有尺度自適應(yīng)的特征壓縮跟蹤方法,解決辨別式跟蹤算法中的樣本特征降維及對目標(biāo)尺度變化的適應(yīng)性問題。將壓縮感知理論引入目標(biāo)跟蹤領(lǐng)域,首先用一個(gè)滿足有限等距準(zhǔn)則的高斯隨機(jī)測量矩陣對提取的樣本特征進(jìn)行壓縮降維,再用降維后的特征進(jìn)行分類,這不僅有助于降低計(jì)算量、提高跟蹤算法的實(shí)時(shí)性,而且由于壓縮特征保留了原始特征的大部分信息,因而能較好的表征目標(biāo)特性、保證目標(biāo)跟蹤精度。同時(shí),為了使跟蹤算法適應(yīng)目標(biāo)尺度變化,在樣本采樣階段,通過結(jié)構(gòu)約束性采樣獲得能盡量反映目標(biāo)位置及尺度變化的樣本集,以便在跟蹤過程中能找到與目標(biāo)當(dāng)前狀態(tài)匹配的最佳樣本。3、提出一種基于正負(fù)樣本響應(yīng)差異最大化的在線加權(quán)特征選擇目標(biāo)跟蹤方法,解決特征冗余問題。分類器輸入特征數(shù)量與輸出性能之間不一定存在線性關(guān)系,當(dāng)特征數(shù)量超過一定值時(shí),不僅耗費(fèi)巨大的計(jì)算開銷,而且還會降低分類器輸出性能。通過定義一個(gè)樣本響應(yīng)差異函數(shù)來選擇多個(gè)特征選擇器(即弱分類器)組成強(qiáng)分類器,并用該強(qiáng)分類器對樣本進(jìn)行分類,分類得分最高的樣本塊即對應(yīng)當(dāng)前幀跟蹤結(jié)果。在選取特征選擇器組成強(qiáng)分類器過程中,根據(jù)樣本與目標(biāo)位置間的距離及重疊度關(guān)系賦予該樣本相應(yīng)的權(quán)重,以突出正樣本、抑制負(fù)樣本,增強(qiáng)分類器對正負(fù)樣本響應(yīng)的辨識能力,從而找出最佳正樣本來描述目標(biāo)當(dāng)前狀態(tài)。4、提出一種基于壓縮特征稀疏表示的目標(biāo)跟蹤方法,解決壓縮特征在PCA子空間中的表示問題。PCA子空間表示法用目標(biāo)模板集的主成分分量來描述候選目標(biāo),極大地增強(qiáng)目標(biāo)外觀描述能力,能夠克服噪聲、光照變化的影響。利用生成式表示策略及增量學(xué)習(xí)更新方式對表示目標(biāo)外觀模型的壓縮特征子空間及瑣碎模板進(jìn)行稀疏表示,將目標(biāo)跟蹤看成是壓縮特征的稀疏近似問題。為了更新遮擋條件下的目標(biāo)外觀模型,提出一種逆指示策略,根據(jù)壓縮特征子空間獲得的似然值尋找原始圖像空間中具有最大觀測似然的圖像塊。與基于模板集或基于PCA子空間的目標(biāo)外觀表示方法相比,本文方法雖然也需解決一序列l(wèi)_1正則最小二乘問題,但由于壓縮特征維數(shù)低,故計(jì)算復(fù)雜度大大降低。本文方法對光照變化、部分遮擋、尺度及姿態(tài)變化等因素的影響具有較強(qiáng)的魯棒性。5、基于上下文在解決目標(biāo)抗遮擋、相似表觀干擾等方面表現(xiàn)出的優(yōu)越性,提出兩種基于上下文輔助的目標(biāo)跟蹤方法。一種是基于兩級隱式形狀模型的目標(biāo)抗遮擋跟蹤方法,主要解決嚴(yán)重遮擋條件下的目標(biāo)定位問題。在兩級碼本特征中,一級特征源于目標(biāo)自身,另一級特征源自周圍目標(biāo),用這些碼本特征構(gòu)建兩級投票模型。根據(jù)遮擋程度的不同,賦予這些特征不同的投票權(quán)重,以提高遮擋條件下的目標(biāo)定位精度,該方法實(shí)質(zhì)是利用稀疏上下文輔助目標(biāo)跟蹤。另一種是具有尺度及方向自適應(yīng)的時(shí)空上下文(SOASTC)輔助目標(biāo)跟蹤方法,將目標(biāo)跟蹤看成是一個(gè)貝葉斯框架下求解目標(biāo)位置似然置信圖極值的問題,其突出的優(yōu)點(diǎn)在于更新時(shí)空上下文模型、獲取目標(biāo)位置似然估計(jì)時(shí)利用FFT加速運(yùn)算,運(yùn)行速度較快。利用主成分分析法求解目標(biāo)區(qū)域權(quán)值圖像的協(xié)方差矩陣,估計(jì)目標(biāo)尺度及旋轉(zhuǎn)角度,自適應(yīng)目標(biāo)尺度及方向變化。該方法具有較強(qiáng)的抗遮擋及抗光照變化能力,對目標(biāo)快速運(yùn)動(dòng)引起的圖像模糊具有一定的適應(yīng)能力,能夠抗相似物干擾、目標(biāo)非剛體形變及雜亂背景的干擾,實(shí)質(zhì)是利用稠密上下文輔助目標(biāo)跟蹤。
[Abstract]:The robust tracking technique of target in complex ground background is the basis for realizing the mission of unmanned aerial vehicle to ground reconnaissance. It is also the key to achieve real-time and accurate target acquisition of all kinds of precision guided weapons at the terminal guidance stage. However, because of the illumination changes, occlusion, scale contraction, rotation, non rigid body shape, random background interference, and objects in the ground scene, the object is the key to the realization of real time and accurate target acquisition of all kinds of precision guided weapons. It is still facing many difficulties for the robust tracking of the single target. This paper starts with the four components of a typical tracking system. Based on the semi supervised online learning theory, this paper proposes a corresponding tracking algorithm to overcome the factors mentioned above. The main research contents include the following aspects: 1, the basic theory of semi supervised online learning and two typical target tracking methods based on semi supervised online learning are introduced: Online MIL tracking and TLD tracking. They have important guidance and reference to the research of robust tracking technology for target in complex ground background and.Online MI L tracking uses bags to encapsulate examples with similar labels, and use bag labels instead of instance labels. By fuzzing the sample labels to weaken the supervision effect, it can better solve the problem of sample fuzzy. The essence is to put forward a new target tracking framework for the innovative.TLD tracking of the object appearance representation method, which is used in the application of a new target tracking framework. The line learning mechanism combines the tracking results and the detection results, while the online learning also makes the tracking algorithm have the "memory" function. When the lost target is reproduced in the field of view, it can be recaptured to the target. It extends and perfects the traditional detection based target tracking theory, and makes up for the existence of only pure detection or pure tracking methods. The inadequacy of tracking performance instability is essentially an innovation of the tracking method.2. A feature compression tracking method with scale adaptive is proposed to solve the dimension reduction of sample characteristics and the adaptability to the change of target scale in the discriminant tracking algorithm. The compression perception theory is introduced into the target tracking field, and the first one satisfies the finite element. The Gauss random measurement matrix of the isometric criterion is used to compress and reduce the feature of the extracted sample, then classify the feature after reducing the dimension, which not only helps to reduce the computation and improve the real-time performance of the tracking algorithm, but also preserves most of the information of the original feature because of the compression characteristics, so it can better characterize the target and guarantee the target. At the same time, in order to make the tracking algorithm adapt to the change of target scale, a sample set which can reflect the position and scale of the target as much as possible is obtained by structural constraint sampling in sample sampling stage, so as to find the best sample.3 which matches the current state of the target in the tracking process, and proposes a kind of the most discrepancy based on the positive and negative sample response. The on-line weighted feature selection of the maximization selects the target tracking method to solve the problem of feature redundancy. The number of classifier input features does not have a linear relationship with the output performance. When the number of features exceeds a certain value, it can not only consume huge computation overhead, but also reduce the performance of the classifier. By defining a sample response difference A strong classifier is composed of multiple feature selectors (weak classifier), and the strong classifier is used to classify the samples. The sample block with the highest score is the result of the following frame tracking. In the process of selecting the strong classifier with the selection of feature selectors, the sample is given to the sample according to the relationship between the distance and the overlap between the target location and the target location. In order to highlight positive samples, suppress negative samples and enhance the recognition ability of positive and negative samples, the best positive sample is found to describe the current state of the target.4, and a target tracking method based on compressed feature sparse representation is proposed to solve the representation problem of compression characteristic in the PCA subspace,.PCA subspace representation. The method uses the principal component component of the set of target template to describe the candidate target, greatly enhances the appearance description ability of the target, and can overcome the influence of noise and illumination change. Using the generation representation strategy and incremental learning update method, the compressed feature subspace and trivial template representing the object appearance model are sparse representation, and the target is tracked. In order to update the object appearance model under the occlusion condition, an inverse indicator strategy is proposed to find the maximum likelihood image block in the original image space based on the likelihood value obtained by the compressed feature subspace. Compared with the template based or the PCA subspace based object appearance representation method, This method needs to solve a sequence of l_1 regular least squares problem, but because the dimension of the compression feature is low, the computational complexity is greatly reduced. This method has strong robustness.5 for the influence of illumination change, partial occlusion, scale and attitude change. Based on the above below, the target anti occlusion, similar apparent interference and so on are solved. Two kinds of target tracking methods based on context aided are presented. One is a target anti occlusion tracking method based on two level implicit shape model, which mainly solves the problem of target location under severe occlusion. In the two level codebook feature, the first level feature is derived from the target itself and the other is derived from the surrounding target. The two level voting model is constructed with these codebook features. According to the different occlusion degree, these features are given different voting weights to improve the target location precision under the occlusion condition. The method is essentially using the sparse context to assist the target tracking. The other is the space-time context (SOASTC) aided target with the scale and square adaptation. The tracking method regards target tracking as a problem of solving the maximum likelihood of the likelihood confidence map of the target position under a Bayesian framework. Its outstanding advantage is to update the spatio-temporal context model and obtain the target location likelihood estimation by using the FFT acceleration operation. The principal component analysis method is used to solve the co square of the target area weight image. Difference matrix, estimation of target scale and rotation angle, adaptive target scale and direction change. This method has strong ability to resist occlusion and illumination change. It has certain adaptability to image blurring caused by fast moving target, can resist the interference of similar objects, the object is non rigid body shape change and the disturbance of random background, in essence it is the use of consistency. Dense context assisted target tracking.
【學(xué)位授予單位】：國防科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2015
【分類號】：V249;TJ765;TP391.41
本文編號：2140757
[Abstract]:The robust tracking technique of target in complex ground background is the basis for realizing the mission of unmanned aerial vehicle to ground reconnaissance. It is also the key to achieve real-time and accurate target acquisition of all kinds of precision guided weapons at the terminal guidance stage. However, because of the illumination changes, occlusion, scale contraction, rotation, non rigid body shape, random background interference, and objects in the ground scene, the object is the key to the realization of real time and accurate target acquisition of all kinds of precision guided weapons. It is still facing many difficulties for the robust tracking of the single target. This paper starts with the four components of a typical tracking system. Based on the semi supervised online learning theory, this paper proposes a corresponding tracking algorithm to overcome the factors mentioned above. The main research contents include the following aspects: 1, the basic theory of semi supervised online learning and two typical target tracking methods based on semi supervised online learning are introduced: Online MIL tracking and TLD tracking. They have important guidance and reference to the research of robust tracking technology for target in complex ground background and.Online MI L tracking uses bags to encapsulate examples with similar labels, and use bag labels instead of instance labels. By fuzzing the sample labels to weaken the supervision effect, it can better solve the problem of sample fuzzy. The essence is to put forward a new target tracking framework for the innovative.TLD tracking of the object appearance representation method, which is used in the application of a new target tracking framework. The line learning mechanism combines the tracking results and the detection results, while the online learning also makes the tracking algorithm have the "memory" function. When the lost target is reproduced in the field of view, it can be recaptured to the target. It extends and perfects the traditional detection based target tracking theory, and makes up for the existence of only pure detection or pure tracking methods. The inadequacy of tracking performance instability is essentially an innovation of the tracking method.2. A feature compression tracking method with scale adaptive is proposed to solve the dimension reduction of sample characteristics and the adaptability to the change of target scale in the discriminant tracking algorithm. The compression perception theory is introduced into the target tracking field, and the first one satisfies the finite element. The Gauss random measurement matrix of the isometric criterion is used to compress and reduce the feature of the extracted sample, then classify the feature after reducing the dimension, which not only helps to reduce the computation and improve the real-time performance of the tracking algorithm, but also preserves most of the information of the original feature because of the compression characteristics, so it can better characterize the target and guarantee the target. At the same time, in order to make the tracking algorithm adapt to the change of target scale, a sample set which can reflect the position and scale of the target as much as possible is obtained by structural constraint sampling in sample sampling stage, so as to find the best sample.3 which matches the current state of the target in the tracking process, and proposes a kind of the most discrepancy based on the positive and negative sample response. The on-line weighted feature selection of the maximization selects the target tracking method to solve the problem of feature redundancy. The number of classifier input features does not have a linear relationship with the output performance. When the number of features exceeds a certain value, it can not only consume huge computation overhead, but also reduce the performance of the classifier. By defining a sample response difference A strong classifier is composed of multiple feature selectors (weak classifier), and the strong classifier is used to classify the samples. The sample block with the highest score is the result of the following frame tracking. In the process of selecting the strong classifier with the selection of feature selectors, the sample is given to the sample according to the relationship between the distance and the overlap between the target location and the target location. In order to highlight positive samples, suppress negative samples and enhance the recognition ability of positive and negative samples, the best positive sample is found to describe the current state of the target.4, and a target tracking method based on compressed feature sparse representation is proposed to solve the representation problem of compression characteristic in the PCA subspace,.PCA subspace representation. The method uses the principal component component of the set of target template to describe the candidate target, greatly enhances the appearance description ability of the target, and can overcome the influence of noise and illumination change. Using the generation representation strategy and incremental learning update method, the compressed feature subspace and trivial template representing the object appearance model are sparse representation, and the target is tracked. In order to update the object appearance model under the occlusion condition, an inverse indicator strategy is proposed to find the maximum likelihood image block in the original image space based on the likelihood value obtained by the compressed feature subspace. Compared with the template based or the PCA subspace based object appearance representation method, This method needs to solve a sequence of l_1 regular least squares problem, but because the dimension of the compression feature is low, the computational complexity is greatly reduced. This method has strong robustness.5 for the influence of illumination change, partial occlusion, scale and attitude change. Based on the above below, the target anti occlusion, similar apparent interference and so on are solved. Two kinds of target tracking methods based on context aided are presented. One is a target anti occlusion tracking method based on two level implicit shape model, which mainly solves the problem of target location under severe occlusion. In the two level codebook feature, the first level feature is derived from the target itself and the other is derived from the surrounding target. The two level voting model is constructed with these codebook features. According to the different occlusion degree, these features are given different voting weights to improve the target location precision under the occlusion condition. The method is essentially using the sparse context to assist the target tracking. The other is the space-time context (SOASTC) aided target with the scale and square adaptation. The tracking method regards target tracking as a problem of solving the maximum likelihood of the likelihood confidence map of the target position under a Bayesian framework. Its outstanding advantage is to update the spatio-temporal context model and obtain the target location likelihood estimation by using the FFT acceleration operation. The principal component analysis method is used to solve the co square of the target area weight image. Difference matrix, estimation of target scale and rotation angle, adaptive target scale and direction change. This method has strong ability to resist occlusion and illumination change. It has certain adaptability to image blurring caused by fast moving target, can resist the interference of similar objects, the object is non rigid body shape change and the disturbance of random background, in essence it is the use of consistency. Dense context assisted target tracking.
【學(xué)位授予單位】：國防科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2015
【分類號】：V249;TJ765;TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前2條
1 石光明;劉丹華;高大化;劉哲;林杰;王良君;;壓縮感知理論及其研究進(jìn)展[J];電子學(xué)報(bào);2009年05期
2 董樂紅;耿國華;高原;;Boosting算法綜述[J];計(jì)算機(jī)應(yīng)用與軟件;2006年08期
相關(guān)碩士學(xué)位論文 前1條
1 屈冉;壓縮感知算法及其應(yīng)用研究[D];南京郵電大學(xué);2013年
，本文編號：2140757
本文鏈接：http://sikaile.net/kejilunwen/hangkongsky/2140757.html
最近更新
教材專著
