本文關(guān)鍵詞： 面向?qū)ο?基于異質(zhì)性最小合并準(zhǔn)則 遙感影像分割 基于主動(dòng)學(xué)習(xí)的SVM 遙感影像分類　出處：《北方民族大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：近年來工業(yè)固體廢物污染已經(jīng)成為十大環(huán)境污染問題之一。隨著工業(yè)生產(chǎn)的不斷發(fā)展,工業(yè)固廢的數(shù)量日益增加。工業(yè)固廢存在的問題有:一是影響城鎮(zhèn)等的美觀;二是工業(yè)固廢中的有害成分會(huì)隨著雨水滲入到土壤中造成水、土質(zhì)等的污染,產(chǎn)生二次危害,因此對(duì)工業(yè)固廢的分布情況的了解可以很好的掌握污染的情況。工業(yè)固廢遙感影像的分割結(jié)果的準(zhǔn)確度,直接影響對(duì)其監(jiān)測(cè)結(jié)果的判斷。然而傳統(tǒng)的影像分類是基于像素,沒有考慮高分辨率影像的特征信息,而使得到的分類精度并不是很高。針對(duì)以上問題,將面向?qū)ο蟮乃枷脒\(yùn)用到影像的分割和分類的方法中,即從傳統(tǒng)的基于像元的處理變成了基于對(duì)象的處理;通過充分的使用形狀和光譜特征,從而使分割對(duì)象的多邊形更接近于真實(shí)地物的邊界。本文的面向?qū)ο蟮墓I(yè)固廢的遙感影像的分割和分類的主要方式可以概括為如下四大步:(1)在遙感影像處理之前進(jìn)行PCA的處理分割,然后再進(jìn)行四叉樹的分割將影像處理成一定的影像塊,即影像對(duì)象;(2)基于異質(zhì)性最小的準(zhǔn)則計(jì)算塊與塊之間權(quán)值的大小;(3)運(yùn)用一種快速的合并方法將影像分割成塊與塊之間異質(zhì)性最大,同質(zhì)性最小的對(duì)象,即得到最終的分割結(jié)果;(4)針對(duì)得到的分割結(jié)果運(yùn)用主動(dòng)學(xué)習(xí)的SVM方法進(jìn)行相應(yīng)的分類,并將最終的分類結(jié)果與傳統(tǒng)的一些方法進(jìn)行比較。本文通過將分割、分類的結(jié)果和傳統(tǒng)方法及一些相應(yīng)改進(jìn)方法對(duì)比分析,分割結(jié)果運(yùn)用同質(zhì)性、異質(zhì)性和PRI做了對(duì)比,分類結(jié)果在總體的精度和kappa系數(shù)方面都取得了相對(duì)較好的效果。
[Abstract]:In recent years, industrial solid waste pollution has become one of the top ten environmental pollution problems. With the development of industrial production, the quantity of industrial solid waste is increasing day by day. Second, as Rain Water seeps into the soil to pollute water, soil quality, and so on, the harmful components in industrial solid waste will cause secondary harm. Therefore, the distribution of industrial solid waste can be well understood. The accuracy of the segmentation results of industrial solid waste remote sensing images directly affects the judgment of the monitoring results. However, the traditional image classification is based on pixels. The feature information of high-resolution image is not considered, but the classification accuracy is not very high. In view of the above problems, the object-oriented idea is applied to the image segmentation and classification method. That is, from traditional pixel based processing to object based processing; by making full use of shape and spectral features, Thus, the polygon of segmented objects is closer to the boundary of real objects. The main ways of segmentation and classification of object oriented industrial solid waste remote sensing images in this paper can be summarized as follows: 1) in remote sensing image processing. PCA processing before segmentation, Then the quadtree is segmented and the image is processed into a certain image block. That is to say, the image object is based on the criterion of minimum heterogeneity to calculate the weight value between blocks and blocks. A fast merging method is used to divide the image into objects with the greatest heterogeneity and the least homogeneity between blocks. That is to say, the final segmentation result is obtained. (4) the SVM method of active learning is used to classify the segmentation results, and the final classification results are compared with some traditional methods. The classification results are compared with the traditional methods and some corresponding improved methods. The segmentation results are compared with those of PRI using homogeneity heterogeneity. The classification results have achieved relatively good results in terms of overall accuracy and kappa coefficients.
【學(xué)位授予單位】：北方民族大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 單臣玉;閆吉春;崔耀東;柳楊;;寧夏大宗工業(yè)固體廢物特性及綜合利用方式的研究[J];寧夏工程技術(shù);2016年03期

2 張方利;杜世宏;郭舟;;應(yīng)用高分辨率影像的城市固體廢棄物提取[J];光譜學(xué)與光譜分析;2013年08期

3 溫長吉;王生生;于合龍;蘇恒強(qiáng);;基于改進(jìn)蜂群算法優(yōu)化神經(jīng)網(wǎng)絡(luò)的玉米病害圖像分割[J];農(nóng)業(yè)工程學(xué)報(bào);2013年13期

4 譚樂怡;王守覺;;基于多尺度分析和均值漂移的Kway-Ncut算法[J];模式識(shí)別與人工智能;2013年04期

5 巫兆聰;胡忠文;張謙;崔衛(wèi)紅;;結(jié)合光譜、紋理與形狀結(jié)構(gòu)信息的遙感影像分割方法[J];測(cè)繪學(xué)報(bào);2013年01期

6 鄭力;文娜;;寧東能源化工基地工業(yè)固體廢物現(xiàn)狀分析及污染防治對(duì)策研究[J];能源與節(jié)能;2012年10期

7 劉春閣;;梯度邊緣檢測(cè)算子綜述[J];科技視界;2012年28期

8 孟方;尹秉喜;;寧夏煤炭資源現(xiàn)狀及其保障程度預(yù)測(cè)分析[J];寧夏工程技術(shù);2012年01期

9 宋相法;焦李成;;基于稀疏表示及光譜信息的高光譜遙感圖像分類[J];電子與信息學(xué)報(bào);2012年02期

10 唐新亭;張小峰;鄒海林;;圖像分割的最大熵方法的改進(jìn)[J];計(jì)算機(jī)工程與應(yīng)用;2012年01期

相關(guān)碩士學(xué)位論文 前3條

1 楊寧;高分辨率影像面向?qū)ο蠓诸愄卣鬟x擇方法研究[D];西安科技大學(xué);2012年

2 王波;基于面向?qū)ο蟮母叻直媛蔬b感影像人工地物信息提取[D];江西理工大學(xué);2011年

3 田野;面向?qū)ο蟮倪b感影像多尺度自適應(yīng)分割技術(shù)[D];上海交通大學(xué);2009年

，

本文編號(hào)：1507826