發(fā)布時(shí)間：2018-10-17 12:51

【摘要】：近年來(lái),在航運(yùn)中泄漏到海洋與內(nèi)河河流中的數(shù)萬(wàn)噸石油對(duì)周邊環(huán)境造成了極其嚴(yán)重的污染。在海上溢油監(jiān)測(cè)技術(shù)領(lǐng)域,國(guó)內(nèi)外已取得了矚目的成績(jī)。然而,內(nèi)河流域因其水文環(huán)境復(fù)雜,現(xiàn)有溢油監(jiān)測(cè)技術(shù)仍無(wú)法應(yīng)對(duì)突發(fā)的溢油事故。本論文以溢油紋理特征為出發(fā)點(diǎn),根據(jù)"強(qiáng)光照下,油膜和水面呈現(xiàn)不同視覺(jué)效果"這一特性,通過(guò)紋理特征提取方法,分別對(duì)油膜和水面紋理進(jìn)行特征提取,得到特征量。以紋理特征量為數(shù)據(jù)源,利用支持向量機(jī)分類(lèi)原理,預(yù)測(cè)油膜和水面紋理圖像分類(lèi)準(zhǔn)確率。對(duì)比不同提取方法下得到的預(yù)測(cè)準(zhǔn)確率。預(yù)測(cè)準(zhǔn)確率越高,說(shuō)明紋理特征量包含的油膜和水面紋理特征越精確,越有助于后期溢油圖像的監(jiān)測(cè)識(shí)別工作。基于油膜和水面紋理特征,本論文對(duì)特征提取中經(jīng)典的灰度共生矩陣方法進(jìn)行了詳細(xì)說(shuō)明。Haralick從該矩陣中提取了 14個(gè)特征量,本文從中選擇了能夠表征油膜和水面紋理特征的特征量:角二階矩、對(duì)比度、相關(guān)性、熵以及逆差矩,然后在灰度共生矩陣的基礎(chǔ)上,衍生出一維灰度共生矩陣方法。根據(jù)油膜紋理的彩色特性,將灰度共生矩陣和顏色信息相結(jié)合,獲得顏色共生矩陣,并由此衍生出一維顏色共生矩陣、各分量顏色共生矩陣等方法。根據(jù)HSI空間下溢油紋理特征,本文提出一種基于色調(diào)和飽和度分量的提取方法——色調(diào)飽和度共生矩陣法。利用上述方法提取油膜和水面紋理特征量,最終獲得預(yù)測(cè)準(zhǔn)確率。對(duì)比準(zhǔn)確率,分析各方法優(yōu)劣性。實(shí)驗(yàn)結(jié)果表明,針對(duì)強(qiáng)光照下的溢油紋理特征,從顏色共生矩陣和色調(diào)飽和度共生矩陣方法中提取的紋理特征量具有更高的分類(lèi)準(zhǔn)確度。顏色信息、像素空間關(guān)系信息以及色調(diào)飽和度分量信息在表征油膜和水面紋理特征方面具有重要的研究參考價(jià)值,可用于后續(xù)強(qiáng)光照下內(nèi)河溢油的監(jiān)測(cè)、識(shí)別工作。
[Abstract]:In recent years, tens of thousands of tons of oil leaking into the ocean and inland rivers in shipping have caused extremely serious pollution to the surrounding environment. In the field of offshore oil spill monitoring technology, domestic and foreign has made remarkable achievements. However, due to its complex hydrological environment, the existing oil spill monitoring technology is still unable to cope with sudden oil spill accidents. In this paper, based on the feature of oil spill texture, according to the feature of "oil film and water surface show different visual effects under strong light", the oil film and water surface texture are extracted by the method of texture feature extraction, and the feature quantity is obtained. The classification accuracy of oil film and water surface texture images is predicted by using support vector machine (SVM). The prediction accuracy of different extraction methods is compared. The higher the prediction accuracy is, the more accurate the oil film and surface texture feature included in the texture feature quantity is, and the more helpful to monitor and identify the oil spill image. Based on oil film and surface texture features, the classical gray level co-occurrence matrix method in feature extraction is described in this paper. Haralick extracts 14 feature quantities from the matrix. In this paper, we select the characteristics of oil film and water surface texture: angular second order moment, contrast, correlation, entropy and deficit moment, and then derive one dimensional gray level co-occurrence matrix method based on gray level co-occurrence matrix. According to the color characteristics of oil film texture, the color-co-occurrence matrix is obtained by combining the gray level co-occurrence matrix with the color information, and the one-dimensional color co-occurrence matrix and each component color-co-occurrence matrix are derived. Based on the texture features of oil spill in HSI space, a new extraction method based on hue and saturation components is presented in this paper, which is called hue saturation co-occurrence matrix method. The oil film and surface texture features are extracted by the above methods, and the prediction accuracy is obtained. Compare the accuracy and analyze the advantages and disadvantages of each method. The experimental results show that the texture features extracted from the color co-occurrence matrix and the hue saturation co-occurrence matrix method have higher classification accuracy for the oil spill texture features under strong illumination. Color information, pixel spatial information and hue saturation information have important reference value in the characterization of oil film and water surface texture features, and can be used to monitor and identify the oil spill of inland rivers under the following strong illumination.
【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李大華;趙相飛;許亮;于波;;基于紋理特征與HSI空間的蘋(píng)果識(shí)別與標(biāo)定[J];圖學(xué)學(xué)報(bào);2016年05期

2 王林林;孫躍東;聶琮;石姣姣;;基于RGB色彩空間的花崗巖組成成分邊界曲線識(shí)別與提取[J];中國(guó)科技論文;2016年13期

3 李雙;;淺談突發(fā)水環(huán)境污染事故應(yīng)急監(jiān)測(cè)技術(shù)[J];科技風(fēng);2016年12期

4 崔鵬宇;;基于支持向量機(jī)的分類(lèi)器訓(xùn)練研究[J];數(shù)字技術(shù)與應(yīng)用;2016年06期

5 徐其林;康堯磊;羅時(shí)暉;;內(nèi)河溢油監(jiān)測(cè)應(yīng)急指揮系統(tǒng)設(shè)計(jì)與研究[J];自動(dòng)化與儀器儀表;2015年08期

6 陳璇琳;竺柏康;王東光;;港口碼頭溢油監(jiān)測(cè)報(bào)警系統(tǒng)的研究現(xiàn)狀及展望[J];中國(guó)水運(yùn)(下半月);2015年07期

7 丁祖萍;劉坤;王成;;一種基于顏色和紋理的顯著性目標(biāo)檢測(cè)算法[J];計(jì)算機(jī)工程與應(yīng)用;2016年19期

8 程金香;韓兆興;徐洪磊;陳冬元;;內(nèi)河水域船舶溢油應(yīng)急能力建設(shè)研究[J];環(huán)境保護(hù);2015年08期

9 劉萬(wàn)軍;張洪偉;;改進(jìn)顏色和小波變換紋理的圖像檢索方法研究[J];計(jì)算機(jī)工程與應(yīng)用;2016年17期

10 高龍?bào)J;陸鑫;崔丹;;內(nèi)河船舶溢油擴(kuò)散的建模與仿真[J];計(jì)算機(jī)應(yīng)用與軟件;2014年12期

相關(guān)博士學(xué)位論文 前1條

1 黃國(guó)祥;RGB顏色空間及其應(yīng)用研究[D];中南大學(xué);2002年

相關(guān)碩士學(xué)位論文 前6條

1 杜瑩萍;基于小波變換和多尺度多方向自相關(guān)函數(shù)法織物疵點(diǎn)檢測(cè)[D];西安工程大學(xué);2015年

2 薛樂(lè);基于傅里葉變換和Gabor變換的機(jī)織物紋理分析方法研究[D];東華大學(xué);2015年

3 王龍;圖像紋理特征提取及分類(lèi)研究[D];中國(guó)海洋大學(xué);2014年

4 董昱威;基于特征提取的紋理圖像分割[D];長(zhǎng)安大學(xué);2014年

5 廖茜;基于顏色共生矩陣的紋理特征提取及應(yīng)用[D];中南大學(xué);2012年

6 時(shí)吉強(qiáng);基于近紅外線CCD水面油膜監(jiān)測(cè)系統(tǒng)的研究[D];大連海事大學(xué);2008年

，

本文編號(hào)：2276718