本文選題：高光譜遙感　切入點(diǎn)：特征選擇　出處：《華東師范大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：高光譜特征選擇是在保留圖像本身物理信息的基礎(chǔ)上,找出最具有代表性的波段組合的搜索過程。它本質(zhì)上是一個(gè)全局優(yōu)化過程。進(jìn)化算法是一種模擬生物自然進(jìn)化、基于種群的全局優(yōu)化方法。本文在分析比較傳統(tǒng)搜索方法的基礎(chǔ)上,嘗試將進(jìn)化算法應(yīng)用于高光譜圖像特征選擇,主要的研究?jī)?nèi)容包括：(1)首先,根據(jù)高光譜特征選擇問題與進(jìn)化算法相結(jié)合所要面臨的問題,通過設(shè)計(jì)合適的編碼方式和目標(biāo)函數(shù),給出了相應(yīng)的解決方法。以新目標(biāo)函數(shù)為評(píng)價(jià)準(zhǔn)則進(jìn)行基于進(jìn)化優(yōu)化的高光譜特征選擇。實(shí)驗(yàn)證明基于新目標(biāo)函數(shù)的進(jìn)化搜索算法得到的波段組合圖像具有比較好的分類性能。(2)其次,在進(jìn)化算法的基礎(chǔ)上,添加了局部搜索算子,提出基于Memetic算法的高光譜特征選擇。在對(duì)經(jīng)典的最佳指數(shù)法做出改進(jìn)的基礎(chǔ)上,從高光譜圖像波段間相關(guān)系數(shù)和單幅波段圖像的信息量?jī)蓚�(gè)方面設(shè)計(jì)局部搜索算子。本文中通過Online擇優(yōu)和Offline擇優(yōu)兩種方式對(duì)Memetic算法進(jìn)行了研究,并且在Online擇優(yōu)方式中提出了兩種局部搜索方法。實(shí)驗(yàn)結(jié)果表明添加了局部搜索算子的Memetic高光譜特征選擇算法不但提高了特征選擇能力,還提高了分類能力。(3)最后,我們嘗試將多目標(biāo)進(jìn)化算法應(yīng)用于高光譜特征選擇,從而避免單目標(biāo)進(jìn)化算法中部分參數(shù)選取的隨機(jī)性。
[Abstract]:Hyperspectral feature selection is a search process to find the most representative band combination on the basis of preserving the physical information of the image itself. It is essentially a global optimization process. On the basis of analyzing and comparing traditional search methods, this paper attempts to apply evolutionary algorithm to feature selection of hyperspectral images. The main research contents include: 1) first of all, According to the problems faced by the combination of the hyperspectral feature selection problem and the evolutionary algorithm, the appropriate coding method and objective function are designed. The corresponding solutions are given. The new objective function is used as the evaluation criterion to select the hyperspectral features based on evolutionary optimization. The experimental results show that the band combination images obtained by the evolutionary search algorithm based on the new objective function have a comparison. Good classification performance. Based on the evolutionary algorithm, the local search operator is added, and the hyperspectral feature selection based on Memetic algorithm is proposed. The local search operator is designed in terms of the correlation coefficient between bands of hyperspectral images and the amount of information in a single band image. In this paper, the Memetic algorithm is studied by means of Online preference and Offline preference. The experimental results show that the Memetic hyperspectral feature selection algorithm with local search operator not only improves the feature selection ability, but also improves the classification ability. We try to apply multi-objective evolutionary algorithm to hyperspectral feature selection to avoid the randomness of partial parameter selection in single-objective evolutionary algorithm.
【學(xué)位授予單位】：華東師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 甘甫平,王潤(rùn)生,江思宏,張宗貴,郭小方,王青華;基于完全譜形特征的成像光譜遙感巖礦識(shí)別技術(shù)及其應(yīng)用[J];地質(zhì)科學(xué);2000年03期

2 周家銳;紀(jì)震;沈琳琳;朱澤軒;陳思平;;基于Gabor小波與Memetic算法的人臉識(shí)別方法[J];電子學(xué)報(bào);2012年04期

3 于紹慧;張玉鈞;趙南京;肖雪;王歡博;;基于矩陣模式的高光譜波段選擇方法[J];光電工程;2012年06期

4 袁方;周志勇;宋鑫;;初始聚類中心優(yōu)化的k-means算法[J];計(jì)算機(jī)工程;2007年03期

5 李秀娟;;KNN分類算法研究[J];科技信息;2009年31期

6 劉波;王凌;金以慧;;差分進(jìn)化算法研究進(jìn)展[J];控制與決策;2007年07期

7 毛勇;周曉波;夏錚;尹征;孫優(yōu)賢;;特征選擇算法研究綜述[J];模式識(shí)別與人工智能;2007年02期

8 孫珂;陳圣波;;基于遺傳算法綜合Terra/Aqua MODIS熱紅外數(shù)據(jù)反演地表組分溫度[J];紅外與毫米波學(xué)報(bào);2012年05期

9 葛亮;王斌;張立明;;基于波段聚類的高光譜圖像波段選擇[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2012年11期

10 熊偉麗;陳敏芳;王肖;徐保國(guó);;運(yùn)用改進(jìn)差分進(jìn)化算法辨識(shí)Hammerstein模型[J];南京理工大學(xué)學(xué)報(bào);2013年04期

，

本文編號(hào)：1571704