本文選題：網(wǎng)格顯著性 + 流形排序　； 參考：《大連理工大學(xué)》2016年博士論文

【摘要】：隨著掃描獲取技術(shù)的發(fā)展和計算機處理能力的提高,三維幾何模型成為新興的數(shù)據(jù)類型,在娛樂、生物信息以及互聯(lián)網(wǎng)有廣泛的應(yīng)用。數(shù)字幾何處理是用計算機處理三維幾何模型的技術(shù),是計算機圖形學(xué)的研究熱點。本文對數(shù)字幾何處理中網(wǎng)格顯著性進行研究,主要工作如下：1.提出了基于描述子空間流形排序的網(wǎng)格顯著性檢測方法。首先,把網(wǎng)格過分割為超像素面片,借助局部中心對比機制計算每個超像素面片的局部對比值。局部對比值小的超像素面片認為是背景超像素面片,相反,則認為是前景超像素面片。其次,通過排序每個超像素面片與不顯著的背景超像素面片的相關(guān)性得到顯著圖。最后,利用拉普拉斯算子得到光滑的顯著圖。與顯著的前景超像素面片作為排序算法中的查詢節(jié)點作對比,這樣可以提高算法的魯棒性,并且對查詢節(jié)點的閾值不敏感。另外,考慮到三維模型的顯著區(qū)域在空間域中是分散的,本文把流形結(jié)構(gòu)加入到超像素面片的描述子空間中,在其中設(shè)計的排序算法更適合網(wǎng)格顯著性。在大量的模型上與以前的方法進行對比,實驗說明了本文算法的有效性和魯棒性。2.提出了基于吸收馬爾可夫鏈的網(wǎng)格顯著性檢測方法。本文利用特征方差得到不顯著的區(qū)域,并考慮了背景信息和前景信息。首先,利用Ncuts算法對輸入網(wǎng)格進行分塊,根據(jù)Zernike系數(shù)將每塊過分割成超像素面片,通過計算每塊的特征方差來選擇背景超像素面片。其次,把背景超像素面片復(fù)制為吸收馬爾可夫鏈的吸收節(jié)點,計算每個節(jié)點的被吸收時間,得到了粗略的顯著圖。接著,從得到的顯著圖中提取前景節(jié)點,復(fù)制為吸收節(jié)點,相似的計算過程可以得到更好的顯著結(jié)果,該過程抑制了背景區(qū)域并且有效的增強了顯著的前景區(qū)域。最后,利用拉普拉斯算子得到光滑的顯著結(jié)果。實驗結(jié)果證實了本文的方法比以前方法具有優(yōu)越性。3.視覺顯著性可用來指導(dǎo)很多計算機圖形學(xué)技術(shù),比如簡化、分割、光滑、視角選取。根據(jù)人類視覺變化的基本原則,本文利用局部對比機制來度量顯著性�？紤]到熵具有描述系統(tǒng)混亂程度的屬性,采用熵值來刻畫區(qū)域的局部變化。把法向量作為頂點描述子,計算每點的局部鄰域內(nèi)所有法向量的熵值,從而得到顯著圖。該方法簡單、快速、有效并能產(chǎn)生好的結(jié)果。另外,本文還將顯著性結(jié)果應(yīng)用到了一些幾何處理中。
[Abstract]:With the development of scanning acquisition technology and the improvement of computer processing ability, 3D geometry model has become a new type of data, and has been widely used in entertainment, biological information and the Internet. Digital geometry processing is the technology of computer processing 3D geometry model, and it is the research hotspot of computer graphics. In this paper, the significance of mesh in digital geometric processing is studied. The main work is as follows: 1. A mesh salience detection method based on description subspace manifold sorting is proposed. Firstly, the meshes are divided into superpixel slices, and the local contrast values of each superpixel surface are calculated by means of the local center comparison mechanism. The super-pixel slice with small local contrast value is considered as the background super-pixel surface, whereas the foreground super-pixel surface is considered as the background super-pixel surface. Secondly, the significance map is obtained by sorting the correlation between each super-pixel slice and the background super-pixel slice. Finally, the smooth salient graph is obtained by using Laplace operator. Compared with the significant foreground super-pixel slice as the query node in the sorting algorithm, the robustness of the algorithm can be improved and the threshold of the query node is insensitive. In addition considering that the significant region of the 3D model is decentralized in the spatial domain the manifold structure is added to the description subspace of the superpixel surface in which the sorting algorithm designed is more suitable for mesh saliency. Compared with the previous methods in a large number of models, the experimental results show the effectiveness and robustness of the proposed algorithm. A mesh salience detection method based on absorbing Markov chains is proposed. In this paper, we use the characteristic variance to obtain the region which is not significant, and consider the background information and foreground information. Firstly, the input meshes are divided into blocks by using Ncuts algorithm, and each over-pixel surface is divided into super-pixel slices according to Zernike coefficients, and the background super-pixel surface is selected by calculating the characteristic variance of each block. Secondly, the background super-pixel surface is copied as the absorbing node of the absorbing Markov chain, and the absorption time of each node is calculated, and a rough salient diagram is obtained. Then, the foreground node is extracted from the obtained salient map and copied to the absorbing node. The similar computing process can obtain better significant results, which can suppress the background area and effectively enhance the significant foreground region. Finally, by using Laplacian operator, a smooth and significant result is obtained. The experimental results show that the proposed method is superior to the previous method. Visual salience can be used to guide many computer graphics techniques, such as simplification, segmentation, smoothness, angle selection. According to the basic principle of human visual change, this paper uses local contrast mechanism to measure salience. Considering that entropy has the attribute of describing the degree of chaos of the system, the entropy value is used to describe the local variation of the region. The normal vector is regarded as the vertex descriptor, and the entropy of all normal vectors in the local neighborhood of each point is calculated, and the salient graph is obtained. The method is simple, fast, effective and can produce good results. In addition, the significant results are applied to some geometric processing.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP391.41

【相似文獻】

相關(guān)期刊論文 前10條

1 曾軍;器件模擬中網(wǎng)格的動態(tài)生成與調(diào)整[J];電子科技大學(xué)學(xué)報;1992年06期

2 劉勇奎,鄒善舉,米守防,李春時;六角網(wǎng)格上的圓與橢圓生成算法[J];大連民族學(xué)院學(xué)報;2002年01期

3 劉勇奎,石教英;六角網(wǎng)格上的圖形顯示[J];計算機輔助設(shè)計與圖形學(xué)學(xué)報;2004年03期

4 裴蒸;利用網(wǎng)格直接求解幾何問題的方法[J];計算機輔助設(shè)計與圖形學(xué)學(xué)報;1992年03期

5 雷曉松;透平葉柵網(wǎng)格的生成與繪制[J];鄂州大學(xué)學(xué)報;1999年03期

6 孟敏;計忠平;劉利剛;;基于保特征調(diào)和場的交互式網(wǎng)格分片[J];計算機輔助設(shè)計與圖形學(xué)學(xué)報;2008年09期

7 王梅珍;王府梅;王善元;;基于網(wǎng)格的織物虛擬場景真實感模擬及計算機實現(xiàn)[J];東華大學(xué)學(xué)報(自然科學(xué)版);2006年06期

8 馮占榮;于建群;付宏;盧洪濤;;一種二維貼體網(wǎng)格改進算法的研究[J];西安交通大學(xué)學(xué)報;2009年03期

9 Ian Foster;Yong Zhao;Ioan Raicu;Shiyong Lu;楊莎莎;劉宴兵;;網(wǎng)格計算和云計算360度比較[J];數(shù)字通信;2010年03期

10 葉強強;余燁;張靜;劉曉平;;基于網(wǎng)格的球面虛擬實景空間搭建方法[J];華南師范大學(xué)學(xué)報(自然科學(xué)版);2012年04期

相關(guān)會議論文 前9條

1 王瑞利;付漢清;;流體力學(xué)數(shù)值模擬中的網(wǎng)格自適應(yīng)技術(shù)[A];中國工程物理研究院科技年報（1999）[C];1999年

2 李盾;陳靖;方華;;復(fù)雜外形三維非結(jié)構(gòu)粘性直角網(wǎng)格的生成[A];中國造船工程學(xué)會電子技術(shù)學(xué)術(shù)委員會2006學(xué)術(shù)年會論文集（上冊）[C];2006年

3 葉強強;余燁;張靜;劉曉平;;基于網(wǎng)格的球面虛擬實景空間搭建方法[A];安徽首屆科普產(chǎn)業(yè)博士科技論壇——暨社區(qū)科技傳播體系與平臺建構(gòu)學(xué)術(shù)交流會論文集[C];2012年

4 鄭冠男;楊國偉;;三維非結(jié)構(gòu)動網(wǎng)格計算方法研究[A];第十三屆全國激波與激波管學(xué)術(shù)會議論文集[C];2008年

5 周磊;譚偉偉;;聚合多重網(wǎng)格的體網(wǎng)格可視化技術(shù)[A];探索 創(chuàng)新 交流（第4集）——第四屆中國航空學(xué)會青年科技論壇文集[C];2010年

6 晉長秋;曹雄;;二維拉氏程序中的重分[A];中國工程物理研究院科技年報（2000）[C];2000年

7 陳立崗;梁義;陳建軍;鄭耀;;保特征的曲面網(wǎng)格重生成方法[A];慶祝中國力學(xué)學(xué)會成立50周年暨中國力學(xué)學(xué)會學(xué)術(shù)大會’2007論文摘要集（下）[C];2007年

8 楊永;;基于網(wǎng)格計算的CFD模擬可信度分析[A];計算流體力學(xué)研究進展——第十二屆全國計算流體力學(xué)會議論文集[C];2004年

9 龔也君;;浸入界面法快速生成網(wǎng)格[A];第十七屆全國反應(yīng)堆結(jié)構(gòu)力學(xué)會議論文集[C];2012年

相關(guān)博士學(xué)位論文 前10條

1 郭e，

本文編號：2032841