發(fā)布時(shí)間：2018-04-25 07:15

  本文選題：日冕物質(zhì)拋射 + 背景建模　； 參考：《昆明理工大學(xué)》2017年碩士論文

【摘要】：日冕物質(zhì)拋射(CME)是太陽(yáng)爆發(fā)活動(dòng)中規(guī)模最大、對(duì)地球環(huán)境影響最為嚴(yán)重的活動(dòng)現(xiàn)象。這種現(xiàn)象可能引起通訊中斷、宇航失靈、衛(wèi)星故障、以及電網(wǎng)輸送網(wǎng)絡(luò)和電力設(shè)備的崩潰。因此研究CME的提取與探測(cè)對(duì)于空間天氣預(yù)報(bào)有著十分重要的意義。CME的提取和探測(cè)過程實(shí)際上就是對(duì)觀測(cè)的序列圖像,運(yùn)用數(shù)學(xué)建模的方法和圖像處理技術(shù)探測(cè)CME的過程。CME的探測(cè)可以看作是動(dòng)態(tài)背景下的運(yùn)動(dòng)目標(biāo)檢測(cè),其中背景建模技術(shù)對(duì)CME的探測(cè)有著至關(guān)重要的作用。針對(duì)CME的序列圖像中背景環(huán)境復(fù)雜的特點(diǎn)(行星和彗星、冕流的變化),本論文在對(duì)比和分析光流法、傳統(tǒng)幀間差分法和背景差分法的特點(diǎn)和不足后,改進(jìn)了傳統(tǒng)的Kalman濾波背景更新算法。以極坐標(biāo)下的序列圖像為背景建模對(duì)象,通過對(duì)傳統(tǒng)Kalman濾波在模型初始化、模型學(xué)習(xí)率做出改進(jìn),建立動(dòng)態(tài)變化的圖像背景,并運(yùn)用背景差分法和形態(tài)學(xué)技術(shù)對(duì)差分圖像進(jìn)行后處理來(lái)檢測(cè)和識(shí)別CME,并對(duì)CME進(jìn)行跟蹤。相對(duì)于光流法、傳統(tǒng)幀間差分法和背景差分法,本論文提出的方法檢測(cè)到的C ME輪廓比較完整、準(zhǔn)確率史高、誤差小,史能適應(yīng)太陽(yáng)序列圖像中復(fù)雜的背景環(huán)境,針對(duì)變化的動(dòng)態(tài)環(huán)境能更好地去除噪聲、冕流等干擾,建立更加趨近真實(shí)的背景。本論文的主要研究?jī)?nèi)容和結(jié)果如下:(1)首先,講述CME研究的背景和意義,概述運(yùn)動(dòng)目標(biāo)檢測(cè)的研究方法、CME的國(guó)內(nèi)外研究方法的現(xiàn)狀,以及概述運(yùn)動(dòng)目標(biāo)檢測(cè)的研究難點(diǎn)。(2)對(duì)運(yùn)動(dòng)目標(biāo)檢測(cè)中當(dāng)前主流的幀間差分法、光流法、背景差分法和傳統(tǒng)的Kalman算法進(jìn)行簡(jiǎn)單的介紹,并對(duì)算法的優(yōu)勢(shì)和不足進(jìn)行深入地對(duì)比和分析。(3)針對(duì)當(dāng)前運(yùn)動(dòng)目標(biāo)檢測(cè)算法存在的主要問題,改進(jìn)了傳統(tǒng)的Kalman濾波背景更新算法,并詳細(xì)地介紹了該算法的改進(jìn)過程。改進(jìn)的內(nèi)容主要包括背景模型的初始化參數(shù)估計(jì)、背景模型的更新以及后處理中CME運(yùn)動(dòng)區(qū)域的提取與處理等。并將改進(jìn)的算法應(yīng)用到CME的提取處理中,主要步驟包括圖像的預(yù)處理、改進(jìn)Kalman背景的提取、運(yùn)動(dòng)物質(zhì)的確定,運(yùn)動(dòng)目標(biāo)的連通性分析、孔洞填充,閾值分割等。(4)將本文提出的改進(jìn)Kalman背景差分法與傳統(tǒng)的算法進(jìn)行對(duì)比和分析,以手工檢測(cè)CME的CDAW為基準(zhǔn),分別與SEEDS、CACTus、幀間差分法、傳統(tǒng)Kalman濾波背景更新法進(jìn)行對(duì)比和分析。實(shí)驗(yàn)表明,它不僅能有效的探測(cè)LASCO C2序列圖像中的CME,還能夠探測(cè)到CDAW手工目錄上探測(cè)不到的C3序列圖像上的CME。與手工識(shí)別相比,本論文中的探測(cè)方法更為快速,魯棒性更好。在精度方面,它不僅可以探測(cè)到CDAW手動(dòng)目錄上列出的CME,還可以檢測(cè)到亮度比較弱的CME,在一定程度上提高了自動(dòng)檢測(cè)算法的準(zhǔn)確率。同時(shí),對(duì)檢測(cè)到的CME的跟蹤效果也良好。本論文方法的不足之處是仍舊存在較小的誤檢率。
[Abstract]:Coronal mass ejection (CMEs) is the largest active phenomenon in the solar burst and has the most serious impact on the earth's environment. This could cause communications disruptions, aerospace failures, satellite failures, and the breakdown of power networks and power equipment. Therefore, it is very important to study the extraction and detection of CME for space weather forecast. In fact, the process of extracting and detecting CME is the sequence image of observation. The detection of CME by mathematical modeling and image processing can be regarded as moving target detection in dynamic background. Background modeling plays an important role in the detection of CME. In view of the complex background environment of CME sequence images (planets and comets, coronal current changes), this paper compares and analyzes the characteristics and shortcomings of optical flow method, traditional inter-frame difference method and background difference method. The traditional background updating algorithm of Kalman filter is improved. Taking the sequence images in polar coordinates as the background modeling object, by initializing the traditional Kalman filter in the model, the learning rate of the model is improved, and the dynamic image background is established. The background differential method and morphological technique are used to detect and recognize the differential image and track the CME. Compared with the optical flow method, the traditional frame difference method and the background difference method, the CME profile detected by this method is relatively complete, the accuracy is high, the error is small, and the history can adapt to the complex background environment in the sun sequence image. The noise and coronal flow can be removed better in the dynamic environment, and a more realistic background can be established. The main contents and results of this thesis are as follows: (1) first of all, the background and significance of CME research are described, and the research methods of moving target detection are summarized. And the research difficulty of moving target detection is briefly introduced, such as inter-frame differential method, optical flow method, background differential method and traditional Kalman algorithm. The advantages and disadvantages of the algorithm are compared and analyzed deeply. Aiming at the main problems of the current moving target detection algorithm, the traditional background updating algorithm of Kalman filter is improved, and the improvement process of the algorithm is introduced in detail. The improvements include the initialization parameter estimation of the background model, the updating of the background model, and the extraction and processing of the CME motion region in the post-processing. The improved algorithm is applied to the extraction of CME. The main steps include image preprocessing, the extraction of improved Kalman background, the determination of moving material, the connectivity analysis of moving object, the filling of holes. Threshold segmentation, etc.) compare and analyze the improved Kalman background difference method and the traditional algorithm, and compare and analyze the traditional Kalman filtering background updating method with the SEEDSCACTus, inter-frame difference method and traditional Kalman filter background updating method, respectively, based on the manual detection of CME CDAW as the benchmark. Experiments show that it can detect not only the LASCO C2 sequence image, but also the C3 sequence image which can not be detected on the CDAW manual directory. Compared with manual recognition, the detection method in this paper is faster and more robust. In terms of accuracy, it can detect not only the CDAW listed on the manual directory, but also the CMEs with weak brightness, which improves the accuracy of the automatic detection algorithm to a certain extent. At the same time, the tracking effect of the detected CME is also good. The shortcoming of this method is that there is still a small false detection rate.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：P35;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 郭厚q;吳峰;黃萍;;基于壓縮感知和字典學(xué)習(xí)的背景差分法[J];華東交通大學(xué)學(xué)報(bào);2012年01期

2 陳東賓;任波;;一種基于背景差分法的非法侵入監(jiān)測(cè)[J];現(xiàn)代計(jì)算機(jī)(專業(yè)版);2007年10期

3 張鐵力;王然冉;李曉佳;;人體運(yùn)動(dòng)目標(biāo)的檢測(cè)與跟蹤[J];自動(dòng)化博覽;2007年05期

4 楊俊紅;魏威;;視頻安全監(jiān)控中的關(guān)鍵技術(shù)研究[J];開封大學(xué)學(xué)報(bào);2009年04期

5 王秀芬;王匯源;王松;;基于背景差分法和顯著性圖的海底目標(biāo)檢測(cè)方法[J];山東大學(xué)學(xué)報(bào)(工學(xué)版);2011年01期

6 孫歡;尚緒鳳;朱趙龍;張賀泉;;交通監(jiān)控系統(tǒng)中幀差法與背景差分法優(yōu)劣分析[J];電子科技;2012年10期

7 李秦君;黨宏社;王明偉;;基于視頻的改進(jìn)背景差分法車輛檢測(cè)與遮擋分離[J];陜西科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年04期

8 黃登斌;歐陽(yáng)民子;彭煈;王振明;;一種改進(jìn)的人體頭部精確定位方法[J];微計(jì)算機(jī)信息;2010年08期

9 李家才;陳治亞;王夢(mèng)格;;鐵路入侵運(yùn)動(dòng)目標(biāo)實(shí)時(shí)檢測(cè)技術(shù)[J];鐵道科學(xué)與工程學(xué)報(bào);2013年06期

10 劉瓔瑛;丁為民;沈明霞;;基于背景差分法的稻米動(dòng)態(tài)圖像檢測(cè)識(shí)別[J];浙江農(nóng)業(yè)學(xué)報(bào);2009年04期

相關(guān)碩士學(xué)位論文 前10條

1 孟妍;視頻目標(biāo)檢測(cè)與跟蹤技術(shù)的研究[D];華北理工大學(xué);2015年

2 劉舟檻;基于背景差法的籃球投籃自動(dòng)識(shí)別系統(tǒng)設(shè)計(jì)[D];湖南師范大學(xué);2015年

3 顧西存;視頻中前景檢測(cè)和背景建模算法的研究[D];重慶郵電大學(xué);2016年

4 張晟;渡口監(jiān)控視頻中的船舶檢測(cè)研究[D];大連海事大學(xué);2016年

5 李強(qiáng);Kalman濾波在CME圖像處理中的應(yīng)用[D];昆明理工大學(xué);2017年

6 楊宇騰;基于背景差分法與虛擬區(qū)域融合的視頻中車流量統(tǒng)計(jì)的方法[D];云南大學(xué);2015年

7 陳能榮;復(fù)雜場(chǎng)景下的運(yùn)動(dòng)目標(biāo)檢測(cè)算法研究[D];浙江工商大學(xué);2012年

8 李霞;人體運(yùn)動(dòng)識(shí)別技術(shù)研究[D];重慶交通大學(xué);2012年

9 韓燕;多運(yùn)動(dòng)目標(biāo)的檢測(cè)與跟蹤研究[D];北方工業(yè)大學(xué);2014年

10 徐盼盼;背景固定視頻中的行人檢測(cè)技術(shù)研究[D];北京交通大學(xué);2013年

，

本文編號(hào)：1800315