【摘要】：近年來,基于衛(wèi)星遙感圖像的目標(biāo)識別技術(shù)得到迅猛發(fā)展,被廣泛地應(yīng)用于軍事領(lǐng)域和民用領(lǐng)域。目前,各國學(xué)者在遙感圖像飛機識別上取得了一定的突破。然而,現(xiàn)實環(huán)境遠不及理論來的理想化,遙感圖像必然存在噪聲、復(fù)雜背景等干擾,這定當(dāng)會影響后續(xù)的識別,因此現(xiàn)有的理論成果仍有不足之處,比如在識別精度、耗時量、通用性等方面還不盡如人意。為此,如何在復(fù)雜的環(huán)境中高效的識別出飛機目標(biāo)成為了本文的研究重點和關(guān)鍵。眾所周知,目標(biāo)識別過程大致包括:預(yù)處理、分割、特征提取及識別。而本文的研究重點——遙感圖像分割、特征提取,已取得如下成果:1、為了提高遙感圖像目標(biāo)分割的精度,提出了一種基于引力搜索算法參數(shù)優(yōu)化的改進脈沖耦合神經(jīng)網(wǎng)絡(luò)(PCNN-Pulse Coupled Neural Network)遙感圖像分割算法。首先,通過二次描述神經(jīng)元間的激勵和抑制關(guān)系,改進連接輸入項和動態(tài)閾值來優(yōu)化經(jīng)典PCNN模型。然后利用上述模型對輸入信息進行點火處理,并從其輸出結(jié)果中提取圖像熵和能量的比值作為引力搜索算法的適應(yīng)度函數(shù),且將熵的變化值作為引力搜索算法的收斂依據(jù),利用引力搜索算法的全局搜索能力尋找PCNN模型中影響分割效果的關(guān)鍵參數(shù)的最優(yōu)值。最終將該算法與OTSU、最大熵直方圖算法和原始PCNN算法進行對比,并通過Matlab仿真實驗證明了本文算法更適用于遙感圖像分割。2、針對幾何不變矩對仿射形變目標(biāo)描述的不足,為提高飛機類型的識別精度,給出了基于小波和仿射不變矩特征融合的飛機識別算法。首先對二值飛機圖像做歸一化操作,并分別計算歸一化飛機目標(biāo)的小波矩和仿射不變矩特征值;然后通過計算樣本特征均值與標(biāo)準(zhǔn)差的商,篩選出魯棒性好、穩(wěn)定性高的特征,通過歸一化方法進行融合;最后將五種不同型號的飛機構(gòu)造成樣本集,并采用支持向量機(Support Vector Machine,SVM)方法識別測試樣本的型號。實驗將不同類型的矩特征、不同容量的樣本集就識別精度、穩(wěn)定性指標(biāo)進行了比較,結(jié)果表明,文中給出的方法提高了精度,而且在訓(xùn)練樣本集較小時仍能獲得較高的識別率。3、基于以上兩個重要步驟,再結(jié)合支持向量機,完整地完成了整個識別過程。通過實驗證明文中提出的方法不僅能克服類型各異及比例不同的噪聲干擾,還能適用于復(fù)雜背景圖像的飛機目標(biāo)。同時,也保證了較高的識別精度和較少的耗時量。
[Abstract]:In recent years, the technology of target recognition based on satellite remote sensing image has been developed rapidly and widely used in military and civilian fields. At present, many scholars have made a breakthrough in remote sensing image aircraft recognition. However, the real environment is far from idealized by theory, and there must be noise and complex background interference in remote sensing images, which will definitely affect the subsequent recognition. Therefore, the existing theoretical achievements still have some shortcomings, such as recognition accuracy, time consuming, etc. Versatility and other aspects are not satisfactory. Therefore, how to efficiently identify aircraft targets in complex environments has become the focus and key of this paper. As we all know, the process of target recognition includes preprocessing, segmentation, feature extraction and recognition. The research focus of this paper, remote sensing image segmentation, feature extraction, has achieved the following results: 1, in order to improve the accuracy of remote sensing image segmentation, An improved pulse coupled neural network (PCNN-Pulse Coupled Neural Network) algorithm for remote sensing image segmentation based on parameter optimization of gravity search algorithm is proposed. Firstly, the classical PCNN model is optimized by quadratic description of the excitation and suppression relationship between neurons and the improvement of connecting input terms and dynamic threshold. Then the input information is ignited by the above model, and the ratio of image entropy and energy is extracted from the output result as the fitness function of the gravity search algorithm, and the change of entropy is taken as the convergence basis of the gravity search algorithm. The global search ability of the gravitational search algorithm is used to find the optimal value of the key parameters in the PCNN model that affect the segmentation effect. Finally, the algorithm is compared with the OTSU, maximum entropy histogram algorithm and the original PCNN algorithm, and the Matlab simulation results show that the proposed algorithm is more suitable for remote sensing image segmentation. 2. In order to improve the accuracy of aircraft type recognition, an aircraft recognition algorithm based on wavelet and affine moment invariant feature fusion is presented. Firstly, the binary plane image is normalized, and the eigenvalues of wavelet moment and affine invariant moment of the normalized aircraft target are calculated respectively. Then, by calculating the quotient of the mean and standard deviation of the sample feature, the features with good robustness and high stability are screened out, and the fusion is carried out by the normalization method. Finally, five different types of flying mechanism are made into sample sets, and support vector machine (Support Vector Machine,SVM) method is used to identify the model of test samples. The experimental results show that the method proposed in this paper has improved the accuracy and stability of the samples with different types of moment features and different capacity. Moreover, a high recognition rate can be obtained when the training sample set is small. 3. Based on the above two important steps and combining with support vector machine, the whole recognition process is completed. It is proved by experiments that the proposed method can not only overcome the noise interference of different types and proportions, but also be suitable for aircraft targets with complex background images. At the same time, it also ensures higher recognition accuracy and less time consuming.
【學(xué)位授予單位】：江蘇科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP751

【參考文獻】

相關(guān)期刊論文 前10條

1 曲仕茹;楊紅紅;;基于遺傳算法參數(shù)優(yōu)化的PCNN紅外圖像分割[J];強激光與粒子束;2015年05期

2 潘改;;改進的PCNN用于遙感圖像分割[J];小型微型計算機系統(tǒng);2015年04期

3 徐亮;李欣;;PSO最優(yōu)化PCNN參數(shù)的皮質(zhì)骨微觀結(jié)構(gòu)圖像分割研究[J];激光雜志;2015年02期

4 明俊峰;汪仁煌;岳洪偉;唐蘇湘;;基于偽Zernike矩的羽毛缺陷幾何特征提取及識別[J];四川兵工學(xué)報;2014年09期

5 曾接賢;付俊;符祥;;特征點和不變矩結(jié)合的遙感圖像飛機目標(biāo)識別[J];中國圖象圖形學(xué)報;2014年04期

6 吳駿;孫明明;肖志濤;張芳;耿磊;;聯(lián)合蟻群算法和PCNN的腦部MRI圖像分割方法[J];光電子.激光;2014年03期

7 李渝;吳增印;;基于局部和整體特征的飛機識別方法[J];現(xiàn)代電子技術(shù);2013年14期

8 丁銳;劉甲甲;李柏林;馬靜恒;熊鷹;王凱;;改進的Otsu圖像多閾值分割方法[J];計算機應(yīng)用;2013年S1期

9 閻繼寧;周可法;王金林;孫莉;秦艷芳;吳艷爽;;一種高光譜遙感數(shù)據(jù)條帶及隨機點噪聲去除方法[J];遙感信息;2013年03期

10 張維平;任雪飛;李國強;牛培峰;;改進的萬有引力搜索算法在函數(shù)優(yōu)化中的應(yīng)用[J];計算機應(yīng)用;2013年05期

相關(guān)碩士學(xué)位論文 前7條

1 高琪琪;遙感圖像飛機目標(biāo)檢測與識別算法研究[D];南昌航空大學(xué);2015年

2 付俊;基于特征融合的遙感圖像飛機目標(biāo)識別研究[D];南昌航空大學(xué);2014年

3 張樹臣;融合顏色和形狀特征的圖像檢索技術(shù)[D];吉林大學(xué);2012年

4 鄒熠;基于小波矩的圖像內(nèi)容識別技術(shù)研究[D];西南交通大學(xué);2010年

5 孫貝;基于矩特征提取的圖像識別算法研究[D];太原理工大學(xué);2010年

6 鄭南;遙感圖像中飛機目標(biāo)的識別分類算法研究[D];吉林大學(xué);2007年

7 肖靚;基于支持向量機的圖像分類研究[D];同濟大學(xué);2006年

，

本文編號：2336172