基于Agent的遙感影像分類方法及其應(yīng)用研究
發(fā)布時(shí)間：2019-03-23 20:05
【摘要】：利用影像進(jìn)行分類是遙感信息提取的重要方法之一,分類后處理是改善初始分類圖像質(zhì)量的必要手段。通過(guò)對(duì)國(guó)內(nèi)外現(xiàn)有遙感影像分類研究進(jìn)行綜述與分析,并結(jié)合實(shí)際生產(chǎn)任務(wù)的需要,發(fā)現(xiàn)當(dāng)前研究存在不足:①絕大多數(shù)的研究偏重于分類方法的改進(jìn)及應(yīng)用,對(duì)分類后處理卻鮮有涉及;②部分學(xué)者提出的分類后處理方法僅針對(duì)分類圖像本身,而影像包含的信息量未能得到充分利用;③人工分類后處理嚴(yán)重依賴經(jīng)驗(yàn),且費(fèi)時(shí)費(fèi)力,現(xiàn)有商業(yè)軟件的自動(dòng)化處理工具盡管在一定程度上改善初始分類圖像質(zhì)量,但存在過(guò)度聚類的現(xiàn)象。計(jì)算Agent是存在于動(dòng)態(tài)環(huán)境中的一種抽象模型,在數(shù)字圖像處理中表現(xiàn)出高度的智能性。本文嘗試將Agent理論和模型引入遙感影像分類研究,在梳理Agent相關(guān)概念和理論的基礎(chǔ)上,構(gòu)建用于遙感影像分類后處理工作的Agent和多Agent系統(tǒng)。針對(duì)初始分類圖像的特點(diǎn)以及遙感影像上可挖掘的地物增強(qiáng)信息,構(gòu)建由分類型、決策型和綜合調(diào)節(jié)型Agent三者協(xié)同工作的多Agent系統(tǒng),通過(guò)Agent對(duì)分類圖像環(huán)境和遙感影像環(huán)境的感知、推理和信息利用,能夠?qū)Τ跏挤诸悎D像上常見(jiàn)缺陷進(jìn)行自動(dòng)調(diào)整。之后利用IDL語(yǔ)言開(kāi)發(fā)了Agent分類后處理工具的核心功能模塊,便于以工作流的方式實(shí)現(xiàn)基于Agent的分類后處理任務(wù)。研究中以北京市作為實(shí)例,對(duì)預(yù)處理后的北京市Landsat 8 OLI影像,采用最大似然法、神經(jīng)網(wǎng)絡(luò)法和光譜角法實(shí)施監(jiān)督分類,同時(shí)從影像上提取NDVI、亮度、綠度等9類特征信息,在Agent分類后處理工具的支持下,對(duì)初始分類圖像進(jìn)行自動(dòng)化的調(diào)整,從精度統(tǒng)計(jì)和目視解譯兩方面驗(yàn)證了本文提出方法的有效性,并與ENVI內(nèi)置工具處理結(jié)果進(jìn)行了對(duì)比。研究結(jié)論有:①本文提出的基于Agent分類后處理工作模式可以實(shí)現(xiàn)遙感影像分類后處理任務(wù)的自動(dòng)化,能有效抑制“椒鹽噪聲”等問(wèn)題,最高可將總體分類精度提高5.5%;②Agent分類后處理工具綜合利用初始分類圖像和遙感影像,避免單純基于濾波處理方式導(dǎo)致的過(guò)度聚類問(wèn)題,且在輔助資料缺失時(shí),本文方法仍然適用;③分類圖像初始精度相對(duì)較低情況下,Agent分類后處理方法對(duì)分類精度提升效果優(yōu)于初始分類圖像精度較高的情況;④以IDL開(kāi)發(fā)核心功能模塊,便于與ENVI軟件集成或開(kāi)發(fā)獨(dú)立系統(tǒng),利于推廣應(yīng)用。
[Abstract]:Image classification is one of the most important methods for remote sensing information extraction, and post-classification is a necessary method to improve the quality of initial classification image. Through summarizing and analyzing the existing remote sensing image classification research at home and abroad, and combining with the needs of actual production tasks, it is found that there are some deficiencies in the current research: 1 the vast majority of research focuses on the improvement and application of classification methods. The post-processing of classification is rarely involved; (2) the classification post-processing method proposed by some scholars only aims at the classification image itself, but the information contained in the image has not been fully utilized; (3) the post-processing of manual classification depends heavily on experience and is time-consuming and laborious. Although the automatic processing tools of existing commercial software improve the quality of initial classification images to a certain extent, there is an over-clustering phenomenon. Computing Agent is an abstract model that exists in the dynamic environment. It shows a high degree of intelligence in digital image processing. This paper attempts to introduce the Agent theory and model into the research of remote sensing image classification. On the basis of combing the related concepts and theories of Agent, a Agent and multi-Agent system for the post-processing of remote sensing image classification is constructed. According to the characteristics of the initial classification image and the mineable feature enhancement information on the remote sensing image, a multi-Agent system is constructed, which consists of classification, decision-making and integrated adjustment-based Agent. Through the perception, reasoning and information utilization of the classified image environment and remote sensing image environment by Agent, the common defects in the initial classification image can be automatically adjusted. Then the core function module of Agent classification post-processing tool is developed with IDL language, which is convenient to realize the post-processing task based on Agent in the way of workflow. Taking Beijing as an example, the maximum likelihood method, neural network method and spectral angle method were used to monitor and classify the pre-processed Landsat 8 OLI images in Beijing. At the same time, 9 kinds of feature information, such as NDVI, brightness and green degree, were extracted from the images. With the support of the post-processing tool of Agent, the automatic adjustment of the initial classification image is carried out. The validity of the proposed method is verified from the two aspects of precision statistics and visual interpretation, and the results are compared with those of the ENVI built-in tool. The conclusions are as follows: (1) the post-processing mode based on Agent can realize the automation of the post-processing task of remote sensing image classification, and can effectively suppress the "pepper and salt noise" and so on. The overall classification accuracy can be increased by 5.5% at the highest level. The 2Agent classification post-processing tool uses the initial classification image and the remote sensing image synthetically, avoids the over-clustering problem caused by the simple filtering processing, and when the auxiliary data is missing, the method in this paper is still applicable. (3) when the initial accuracy of the classification image is relatively low, the Agent classification post-processing method is better than the initial classification image in improving the classification accuracy; (4) develop the core function module with IDL, it is convenient to integrate with ENVI software or develop independent system, which is helpful to popularize and apply.
【學(xué)位授予單位】：中國(guó)地質(zhì)大學(xué)(北京)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP751
本文編號(hào)：2446183
[Abstract]:Image classification is one of the most important methods for remote sensing information extraction, and post-classification is a necessary method to improve the quality of initial classification image. Through summarizing and analyzing the existing remote sensing image classification research at home and abroad, and combining with the needs of actual production tasks, it is found that there are some deficiencies in the current research: 1 the vast majority of research focuses on the improvement and application of classification methods. The post-processing of classification is rarely involved; (2) the classification post-processing method proposed by some scholars only aims at the classification image itself, but the information contained in the image has not been fully utilized; (3) the post-processing of manual classification depends heavily on experience and is time-consuming and laborious. Although the automatic processing tools of existing commercial software improve the quality of initial classification images to a certain extent, there is an over-clustering phenomenon. Computing Agent is an abstract model that exists in the dynamic environment. It shows a high degree of intelligence in digital image processing. This paper attempts to introduce the Agent theory and model into the research of remote sensing image classification. On the basis of combing the related concepts and theories of Agent, a Agent and multi-Agent system for the post-processing of remote sensing image classification is constructed. According to the characteristics of the initial classification image and the mineable feature enhancement information on the remote sensing image, a multi-Agent system is constructed, which consists of classification, decision-making and integrated adjustment-based Agent. Through the perception, reasoning and information utilization of the classified image environment and remote sensing image environment by Agent, the common defects in the initial classification image can be automatically adjusted. Then the core function module of Agent classification post-processing tool is developed with IDL language, which is convenient to realize the post-processing task based on Agent in the way of workflow. Taking Beijing as an example, the maximum likelihood method, neural network method and spectral angle method were used to monitor and classify the pre-processed Landsat 8 OLI images in Beijing. At the same time, 9 kinds of feature information, such as NDVI, brightness and green degree, were extracted from the images. With the support of the post-processing tool of Agent, the automatic adjustment of the initial classification image is carried out. The validity of the proposed method is verified from the two aspects of precision statistics and visual interpretation, and the results are compared with those of the ENVI built-in tool. The conclusions are as follows: (1) the post-processing mode based on Agent can realize the automation of the post-processing task of remote sensing image classification, and can effectively suppress the "pepper and salt noise" and so on. The overall classification accuracy can be increased by 5.5% at the highest level. The 2Agent classification post-processing tool uses the initial classification image and the remote sensing image synthetically, avoids the over-clustering problem caused by the simple filtering processing, and when the auxiliary data is missing, the method in this paper is still applicable. (3) when the initial accuracy of the classification image is relatively low, the Agent classification post-processing method is better than the initial classification image in improving the classification accuracy; (4) develop the core function module with IDL, it is convenient to integrate with ENVI software or develop independent system, which is helpful to popularize and apply.
【學(xué)位授予單位】：中國(guó)地質(zhì)大學(xué)(北京)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP751
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 殷亞秋;李家國(guó);余濤;楊紅艷;張永紅;;基于高分辨率遙感影像的面向?qū)ο笏w提取方法研究[J];測(cè)繪通報(bào);2015年01期
2 東啟亮;林輝;孫華;臧卓;胡佳;范應(yīng)龍;;獨(dú)立分量分析與主成分分析方法的濕地遙感分類精度對(duì)比——以西洞庭湖濕地為例[J];濕地科學(xué);2014年03期
3 唐菲;徐涵秋;;高光譜與多光譜遙感影像反演地表不透水面的對(duì)比——以Hyperion和TM/ETM+為例[J];光譜學(xué)與光譜分析;2014年04期
4 錢銘杰;吳靜;袁春;王巍;;礦區(qū)廢棄地復(fù)墾為農(nóng)用地潛力評(píng)價(jià)方法的比較[J];農(nóng)業(yè)工程學(xué)報(bào);2014年06期
5 戴文雯;別翌薈;張洪海;楊磊;;基于NetLogo的終端區(qū)交通流仿真[J];航空計(jì)算技術(shù);2014年01期
6 王巍;袁濤;周偉;董艷麗;;一種高分辨率遙感影像汽車識(shí)別檢測(cè)方法[J];測(cè)繪通報(bào);2013年10期
7 劉德兒;于海霞;蘭小機(jī);陳元增;;基于最優(yōu)波段組合的TM影像土地覆蓋信息分類[J];金屬礦山;2013年10期
8 靳娟;楊日紅;李家存;;ASTER數(shù)據(jù)蝕變礦物信息提取技術(shù)研究及其應(yīng)用綜述[J];國(guó)土資源科技管理;2013年04期
9 賈坤;姚云軍;魏香琴;高帥;江波;趙祥;;植被覆蓋度遙感估算研究進(jìn)展[J];地球科學(xué)進(jìn)展;2013年07期
10 楊日紅;陳秀法;李志忠;;基于遙感示礦信息的秘魯阿雷基帕省南部斑巖銅礦遙感綜合評(píng)價(jià)[J];遙感信息;2013年02期
相關(guān)博士學(xué)位論文 前1條
1 劉煒;基于網(wǎng)格的面向Agent軟件分析與設(shè)計(jì)建模方法及環(huán)境研究[D];上海大學(xué);2005年
相關(guān)碩士學(xué)位論文 前2條
1 王東;基于多智能體的生態(tài)用地格局演化研究[D];廣州大學(xué);2012年
2 黃秀蘭;基于多智能體與元胞自動(dòng)機(jī)的城市生態(tài)用地演變研究[D];中南大學(xué);2008年
，本文編號(hào)：2446183
本文鏈接：http://sikaile.net/guanlilunwen/gongchengguanli/2446183.html
最近更新
教材專著
