【摘要】：隨著人造衛(wèi)星、載人航天飛船和國際空間站等航天器的發(fā)射,空間目標(biāo)識別是進(jìn)一步安全開發(fā)空間資源的前提條件。而有效識別空間目標(biāo)的表面材質(zhì)對進(jìn)一步識別目標(biāo)具有重要的現(xiàn)實意義和應(yīng)用價值。散射光譜能夠有效表征被測樣本的表面特性,統(tǒng)計機(jī)器學(xué)習(xí)為解決樣本之間不易分類識別的問題,提供了技術(shù)手段。本論文基于散射光譜,結(jié)合四種統(tǒng)計機(jī)器學(xué)習(xí)算法,研究了空間目標(biāo)材質(zhì)的識別問題。具體研究內(nèi)容如下:1.搭建材質(zhì)散射光譜測量系統(tǒng),該系統(tǒng)可測得材質(zhì)多角度下的的散射光譜。對測得的散射光譜進(jìn)行了預(yù)處理,分別為:去噪、計算雙向反射分布函數(shù)和歸一化三個部分,并建立了材質(zhì)數(shù)據(jù)庫。2.基于散射光譜與統(tǒng)計機(jī)器學(xué)習(xí)算法原理,分別建立了樸素貝葉斯分類器、K近鄰算法、誤差反向傳播神經(jīng)網(wǎng)絡(luò)和卷積神經(jīng)網(wǎng)絡(luò)的算法框架,并利用MATLAB軟件進(jìn)行了編程實現(xiàn)。3.基于散射光譜,結(jié)合樸素貝葉斯分類器、K近鄰算法、誤差反向傳播神經(jīng)網(wǎng)絡(luò)和卷積神經(jīng)網(wǎng)絡(luò)四種算法,對經(jīng)過預(yù)處理的材質(zhì)散射光譜進(jìn)行了分類識別實驗,并對識別結(jié)果進(jìn)行了對比分析。研究結(jié)果表明:(1)夾角余弦和歐氏距離結(jié)合嵌入使用于K近鄰算法時,由于綜合考慮了光譜的線型特征與幅度特征,具有精度高,耗時較少的特點,該方法在基于散射光譜的識別領(lǐng)域,具有一定的適用性;(2)卷積神經(jīng)網(wǎng)絡(luò)由于特殊的網(wǎng)絡(luò)結(jié)構(gòu),具有耗時少,精度較高的特點,該方法對于大數(shù)據(jù)量的空間目標(biāo)分類識別領(lǐng)域,具有區(qū)別于其他方法一定的優(yōu)越性和適用性。
[Abstract]:With the launch of satellites, manned spaceships and international space stations, space target recognition is a prerequisite for the further development of space resources. It is very important to recognize the surface material of the space target effectively for the further recognition of the target. The scattering spectrum can effectively characterize the surface characteristics of the measured samples. Statistical machine learning provides a technical means to solve the problem of difficult classification and identification between samples. In this paper, based on scattering spectrum and four statistical machine learning algorithms, the recognition of spatial target materials is studied. The specific contents of the study are as follows: 1. The material scattering spectrum measurement system is set up, which can measure the scattering spectrum of material with multiple angles. The measured scattering spectra are preprocessed into three parts: denoising, calculating the bidirectional reflectance distribution function and normalization, and the material database. 2. Based on the theory of scattering spectrum and statistical machine learning algorithm, the algorithm framework of naive Bayesian classifier K nearest neighbor algorithm, error back propagation neural network and convolution neural network is established, and the program of. 3 is implemented by using MATLAB software. Based on scattering spectrum, combined with naive Bayesian classifier and K-nearest neighbor algorithm, error back-propagation neural network and convolution neural network, the pre-processed material scattering spectrum was classified and recognized. The recognition results are compared and analyzed. The results show that: (1) when the inclusion cosine and Euclidean distance are embedded in the K-nearest neighbor algorithm, because the linear and amplitude characteristics of the spectrum are taken into account, it has the characteristics of high precision and less time consuming. This method has some applicability in the field of recognition based on scattering spectrum. (2) because of the special network structure, the convolution neural network has the characteristics of less time consuming and higher precision. It has some advantages and applicability which is different from other methods.
【學(xué)位授予單位】：長春理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：V419;O657.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王安祥;吳振森;曹運華;;硅太陽能電池板的光譜BRDF測量及色度特性的研究[J];紅外與激光工程;2013年11期

2 于洋;郝中騏;李常茂;郭連波;李闊湖;曾慶棟;李祥友;任昭;曾曉雁;;支持向量機(jī)算法在激光誘導(dǎo)擊穿光譜技術(shù)塑料識別中的應(yīng)用研究[J];物理學(xué)報;2013年21期

3 徐姍姍;劉應(yīng)安;徐f;;基于卷積神經(jīng)網(wǎng)絡(luò)的木材缺陷識別[J];山東大學(xué)學(xué)報(工學(xué)版);2013年02期

4 韓意;孫華燕;;空間目標(biāo)光學(xué)散射特性研究進(jìn)展[J];紅外與激光工程;2013年03期

5 楊長才;田金文;葉瑾;尚軻;田昕;;天基光學(xué)成像系統(tǒng)空間目標(biāo)成像模擬技術(shù)[J];紅外與激光工程;2012年09期

6 劉正春;曾永年;何麗麗;吳孔江;靳文憑;;基于光譜歸一化的變組分光譜混合分析(NMESMA)方法及其應(yīng)用[J];遙感技術(shù)與應(yīng)用;2012年02期

7 楊玉峰;吳振森;曹運華;;一種實用型粗糙面六參數(shù)雙向反射分布函數(shù)模型[J];光學(xué)學(xué)報;2012年02期

8 袁艷;孫成明;黃鋒振;趙慧潔;王潛;;深空背景下空間目標(biāo)紫外特性建模方法研究[J];物理學(xué)報;2011年08期

9 孫成明;袁艷;張修寶;;深空背景下空間目標(biāo)紅外特性建模方法研究[J];物理學(xué)報;2010年10期

10 袁艷;孫成明;張修寶;趙慧潔;王潛;;姿態(tài)變化對空間目標(biāo)可見光特性的影響分析[J];光學(xué)學(xué)報;2010年09期

相關(guān)博士學(xué)位論文 前1條

1 陳國慶;熒光光譜技術(shù)在食品安全監(jiān)控中的應(yīng)用研究[D];江南大學(xué);2010年

相關(guān)碩士學(xué)位論文 前1條

1 白玉兵;復(fù)雜環(huán)境下雷達(dá)探測范圍可視化研究[D];湖南大學(xué);2013年

，

本文編號：2172948