發(fā)布時間：2018-02-23 18:29

  本文關(guān)鍵詞： 合成孔徑雷達(dá) 自動目標(biāo)識別 稀疏性 特征提取 結(jié)構(gòu)化稀疏 聯(lián)合稀疏 深度置信網(wǎng)絡(luò) 卷積神經(jīng)網(wǎng)絡(luò)　出處：《西安電子科技大學(xué)》2015年博士論文　論文類型：學(xué)位論文

【摘要】：合成孔徑雷達(dá)(SAR)是一種重要的對地觀測手段。利用SAR圖像進(jìn)行目標(biāo)識別在戰(zhàn)場環(huán)境中具有非常重要的意義。本論文圍繞基于稀疏理論的SAR圖像目標(biāo)識別進(jìn)行了深入的研究：重點針對存在遮擋情況下的SAR目標(biāo)識別問題和從數(shù)據(jù)中自動進(jìn)行特征提取的問題。各部分的主要內(nèi)容概括如下：第一部分,針對合成孔徑雷達(dá)(SAR,)圖像目標(biāo)識別中存在物體遮擋的情況,提出一種基于非負(fù)稀疏表示的分類方法。通過分析L0范數(shù)和L1范數(shù)最小化在求解非負(fù)稀疏表示問題上的區(qū)別,證明在一定條件下,Ll范數(shù)最小化方法除了保持解的稀疏性還能得到與輸入信號更加相似的原子集合,因此也更加適用于分類問題中。在運動和靜止目標(biāo)獲取與識別(MSTAR)數(shù)據(jù)集上的識別實驗結(jié)果表明,采用L1范數(shù)的非負(fù)稀疏表示分類方法能達(dá)到較好的識別性能,并且相對傳統(tǒng)方法對存在遮擋情況下的識別問題更穩(wěn)健。第二部分,雖然基于稀疏表示或者非負(fù)稀疏表示的模型在遮擋情況下的目標(biāo)識別表現(xiàn)出一定的穩(wěn)健性能,但是其模型中對于遮擋部分采用的都是像素級假設(shè),即：遮擋效應(yīng)引起的是目標(biāo)圖像上少量像素點的變化,并且假定受影響的像素點在空間位置上是獨立出現(xiàn)的。然而真實情況是,對于尺度小于成像單元大小的遮擋物,其遮擋效應(yīng)在目標(biāo)圖像上的表現(xiàn)通常與相干斑造成的效果相近。而對于尺度大于成像單元大小的遮擋物,其使得目標(biāo)圖像上發(fā)生強度變化的區(qū)域?qū)且粔K連續(xù)的區(qū)域。因此我們可以利用遮擋效應(yīng)的這一結(jié)構(gòu)化特點,對遮擋部分進(jìn)行單獨建模,提出了結(jié)構(gòu)化稀疏遮擋模型。該模型嘗試將測試數(shù)據(jù)中的遮擋部分以及在訓(xùn)練樣本集上的稀疏表示部分分離開來。在識別時,僅僅通過稀疏表示部分進(jìn)行目標(biāo)分類,從而避免了遮擋的影響。仿真實驗表明,基于結(jié)構(gòu)化稀疏遮擋模型的方法不僅對于遮擋區(qū)域的大小,形狀,塊數(shù)以及散射起伏都具有較好的穩(wěn)健性。第三部分,地面目標(biāo)的SAR圖像中除了包含目標(biāo)散射回波形成的區(qū)域,還包括由目標(biāo)遮擋地面形成的陰影區(qū)域。但是由于這兩種區(qū)域中的圖像特性不相同,所以傳統(tǒng)的SAR圖像自動目標(biāo)識別主要利用目標(biāo)區(qū)域信息進(jìn)行目標(biāo)識別,或者單獨使用陰影區(qū)域進(jìn)行識別。該文提出一種陰影區(qū)域與目標(biāo)區(qū)域圖像聯(lián)合的稀疏表示模型。通過使用LI\L2范數(shù)最小化方法求解該模型得到聯(lián)合的稀疏表示,然后根據(jù)聯(lián)合重構(gòu)誤差最小準(zhǔn)則進(jìn)行SAR圖像目標(biāo)識別。在運動和靜止目標(biāo)獲取與識別(MSTAR)數(shù)據(jù)集上的識別實驗結(jié)果表明,通過聯(lián)合稀疏表示模型可以有效的將目標(biāo)區(qū)域與陰影區(qū)域信息進(jìn)行融合,相對于采用單獨區(qū)域圖像的稀疏表示識別方法性能更好。第四部分,對于傳統(tǒng)的字典學(xué)習(xí)方法,如KSVD,其目標(biāo)函數(shù)是最小化重構(gòu)誤差。本章通過在字典學(xué)習(xí)目標(biāo)函數(shù)中增加對稀疏表示系數(shù)之間的相似性約束得到具有判決能力的字典。該約束使得不同類樣本的稀疏表示間的相似性趨向于0,即最不相似。因此在稀疏表示系數(shù)這樣的特征空間中不同類別之間的差異更大,更容易找到好的分類面。實驗顯示,添加了相似性約束后學(xué)習(xí)到的字典及其稀疏表示相比傳統(tǒng)的字典學(xué)習(xí)方法可以更好的區(qū)分各類SAR目標(biāo)。第五部分,特征提取是合成孔徑雷達(dá)(SAR)圖像目標(biāo)識別的關(guān)鍵環(huán)節(jié)。SAR圖像中存在的相干斑點和非光滑特性使得傳統(tǒng)針對光學(xué)圖像的特征提取方法變得很難應(yīng)用。雖然可以采用深度置信網(wǎng)絡(luò)(Deep belief network, DBN)自動地進(jìn)行特征學(xué)習(xí),但是該方法屬于無監(jiān)督學(xué)習(xí)方法,這使得學(xué)習(xí)到的特征與具體的任務(wù)是無關(guān)的。本文提出了一種叫做相似性約束的限制玻爾茲曼機模型。該模型在學(xué)習(xí)過程中通過約束特征向量之間的相似性達(dá)到引入監(jiān)督信息的目的。另外,可以將多個相似性約束的限制玻爾茲曼機堆疊成一種新的深度模型,我們稱其為相似性約束的深度置信網(wǎng)絡(luò)模型。實驗結(jié)果表明在SAR圖像目標(biāo)識別應(yīng)用中,本文方法相比主成分分析(PCA)以及原始DBN具有更好的識別性能。第六部分,針對現(xiàn)實SAR ATR應(yīng)該解決的幾個問題：需要具備目標(biāo)平移不變性,對于相干斑噪聲隨機性不敏感以及能夠容忍訓(xùn)練數(shù)據(jù)集中一定程度的姿態(tài)圖像缺失,首先研究了通過已有圖像合成未知方位角下的圖像以彌補訓(xùn)練集中姿態(tài)圖像缺失的可能性。受稀疏表示模型啟發(fā)下,提出了一種姿態(tài)圖像合成模型。實驗顯示,通過姿態(tài)圖像合成的方式可以有效的提升識別性能。隨后通過姿態(tài)圖像合成擴充、平移擴充以及相干斑加噪擴充的方式增大訓(xùn)練樣本集合,并通過擴充后的數(shù)據(jù)對卷積神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練學(xué)習(xí)。大量實驗表明,該方法訓(xùn)練得到的模型可以有效的克服測試樣本中出現(xiàn)的平移問題、相干斑變化以及姿態(tài)變化的情況。
[Abstract]:Synthetic aperture radar (SAR) is one of the important means of earth observation. Using SAR image target recognition is very important in the battlefield environment. SAR image target recognition based on sparse theory is studied in this thesis: focusing on the existing block SAR target recognition problems and from the data in the automatic feature extraction problems. The main contents of each part are as follows: in the first part, the synthetic aperture radar (SAR) objects occlusion image target recognition, a non negative sparse representation classification method based on. Through the analysis of the differences on the issues that the L0 norm and L1 norm minimization in to solve the non negative sparse, prove that under certain conditions, the Ll norm minimization method in addition to maintain the sparsity of the solution can get with the input signal is more similar to atomic collection, so it is more suitable In the classification problem. On a moving and stationary target acquisition and recognition (MSTAR) recognition experiments on the data set. The results show that the non negative sparse representation classification using L1 norm method can achieve better recognition performance, and compared with the traditional method of occlusion identification problem under the condition of more robust. The second part, although based on sparse representation or a non negative sparse representation model under occlusion target recognition showed robust performance, but the model for the occlusion are based on pixel level assumptions, namely: shielding effect caused by the small target image pixels change, and assume that pixels affected are independent in appearance the space position. But the reality is that the scale is less than the size of the imaging unit covering, the shielding effect in the target image usually causes and speckle effect is similar While the scale is larger than the size of the imaging unit covering the target image, regional intensity changes will be a continuous area. So we can use the structural features of the blockage of the occlusion were modeled separately, put forward a structured sparse block model. This model attempts to test sparse occlusion in the data in the training sample set and the said part separated. In recognition, only through the sparse representation of part of the target classification, so as to avoid the occlusion effect. Simulation results show that the method of structured sparse block model based on not only for the occlusion area size, shape, number and scattering fluctuations are better the robustness of SAR. In the third part, the image of ground targets in addition to containing the target scattering echo area, including a ground target occlusion form The shaded area. But because of the image characteristics of the two regions are not the same, so SAR image automatic target recognition using the traditional main target area information for target recognition, or used alone shadow region recognition. This paper proposes a shadow region and object region image joint sparse representation model. By using the LIL2 norm minimization the method of solving the model combined with the sparse representation, then SAR image target recognition based on joint reconstruction error criterion. On a moving and stationary target acquisition and recognition (MSTAR) recognition experiment data sets. The results show that the joint sparse representation model can effectively integrate the target region and the shadow region information, compared with the sparse a separate regional representation of the image recognition method of performance better. In the fourth part, for the traditional dictionary learning methods, such as KSVD, its target Function is the reconstruction error minimization. This chapter increased by learning objective function in the dictionary that similarity coefficient between the constraint has the ability of judgment. This makes the dictionary sparse constraint sparse samples of different classes of similarity between said tends to 0, is the least similar. So in the sparse feature space coefficient in such the difference between different categories of the larger, more easy to find good classification. Experimental results show that adding the dictionary and sparse similarity constraints to learn that compared to the traditional dictionary learning method can better distinguish between various types of SAR. The fifth part, feature extraction is a synthetic aperture radar (SAR) image target key.SAR the identification of existing speckle and non smooth characteristics of the traditional feature extraction method for optical image becomes very difficult. Although the application can use the deep belief network (Deep belief network, DBN) automatically feature learning, but this method belongs to unsupervised learning method, which makes the features learned with a particular task is irrelevant. This paper presents a restricted Boltzmann machine model called similarity constraints. The model through the similarity between feature vectors to the introduction of supervision and restraint the purpose of information in the learning process. In addition, the stack limit Boltzmann machine multiple similarity constraints into a new depth model, we call it the similarity constraint deep belief network model. The experimental results show that the SAR image target recognition application, this method compared with principal component analysis (PCA) and the original DBN has better recognition performance. In the sixth part, several problems should be solved according to the reality of SAR ATR: need to have the goal of translation invariance, for speckle noise with the machine is not sensitive Sense and can tolerate attitude of image missing training data to a certain extent, first study the existing image by image synthesis of unknown azimuth to compensate for the possibility of the training set. The lack of motion image sparse representation model inspired, presents a synthesis model of attitude image. Experimental results show that can enhance the recognition performance through effective way the attitude of image synthesis. Then through gesture image synthesis expansion, speckle noise and translational expansion expansion increases the training set, and through the expansion of the data after the convolution neural network training. The experiments show that the method obtained from the training model can effectively overcome the problem of translation appeared in the test sample. Speckle variation and the change of attitude.

【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2015
【分類號】：TN957.52

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 孫志軍;薛磊;許陽明;孫志勇;;基于多層編碼器的SAR目標(biāo)及陰影聯(lián)合特征提取算法[J];雷達(dá)學(xué)報;2013年02期

，

本文編號：1527168