本文選題：運(yùn)動(dòng)捕捉 + 關(guān)鍵幀提取��； 參考：《江蘇大學(xué)》2017年碩士論文

【摘要】：隨著科技的不斷進(jìn)步,動(dòng)畫(huà)合成技術(shù)的應(yīng)用越來(lái)越廣泛。人們對(duì)動(dòng)畫(huà)合成技術(shù)有了新的功能需求,那就是對(duì)現(xiàn)有的動(dòng)作進(jìn)行重用,從而產(chǎn)生一些不同的效果。即采用動(dòng)畫(huà)合成技術(shù)給用戶(hù)一種強(qiáng)烈的視覺(jué)沖擊,并帶給他們震撼的喜劇效果。而現(xiàn)有的動(dòng)畫(huà)合成技術(shù)不能滿(mǎn)足這種需求。針對(duì)該問(wèn)題,本文作了相關(guān)的課題研究,旨在通過(guò)已有的動(dòng)作生成一種與眾不同的動(dòng)畫(huà)效果。本文首先從課題的研究背景和意義展開(kāi),深入研究課題的相關(guān)應(yīng)用情況和現(xiàn)存問(wèn)題,設(shè)計(jì)并實(shí)現(xiàn)了本文的研究方法:一種基于三維運(yùn)動(dòng)捕捉數(shù)據(jù)關(guān)鍵幀的動(dòng)畫(huà)合成方法。然后圍繞課題的相關(guān)工作,從動(dòng)畫(huà)合成的技術(shù)內(nèi)容進(jìn)行闡述,簡(jiǎn)單介紹了運(yùn)動(dòng)合成和運(yùn)動(dòng)重定向在三維動(dòng)畫(huà)合成領(lǐng)域中的技術(shù)特征,進(jìn)一步介紹了二者所需的關(guān)鍵技術(shù),主要有關(guān)鍵幀提取技術(shù)和動(dòng)作捕捉的分割技術(shù)。在已有的理論研究基礎(chǔ)上,本文設(shè)計(jì)了和提出了兩種關(guān)鍵幀提取方法。最后基于本文設(shè)計(jì)和提出的方法,利用插值的思想,設(shè)計(jì)并且實(shí)現(xiàn)了基于三維運(yùn)動(dòng)捕捉數(shù)據(jù)關(guān)鍵幀的動(dòng)畫(huà)合成系統(tǒng)。本文主要研究?jī)?nèi)容如下:(1)設(shè)計(jì)并實(shí)現(xiàn)了基于余弦距離層次聚類(lèi)的運(yùn)動(dòng)捕捉數(shù)據(jù)關(guān)鍵幀提取方法。該方法充分利用關(guān)節(jié)點(diǎn)的旋轉(zhuǎn)量來(lái)作為分割運(yùn)動(dòng)捕捉數(shù)據(jù)的特征值,接著去除捕捉數(shù)據(jù)中的噪音,然后通過(guò)降維的方法將高維數(shù)據(jù)映射為低維數(shù)據(jù)。隨后用余弦距離計(jì)算相似度,緊接著采用層次聚類(lèi)分割,將各個(gè)分割點(diǎn)和各段中的幀姿勢(shì)與均值誤差最小的幀作為關(guān)鍵幀序列。實(shí)驗(yàn)表明,相比較基于速率的分割方法和基于曲率的分割方法,該方法具有較高的準(zhǔn)確率和查全率。(2)提出了基于最優(yōu)分割的運(yùn)動(dòng)捕捉數(shù)據(jù)關(guān)鍵幀提取方法�？紤]到基于余弦距離層次聚類(lèi)的運(yùn)動(dòng)捕捉數(shù)據(jù)關(guān)鍵幀提取方法僅是通過(guò)經(jīng)驗(yàn)啟發(fā)式設(shè)計(jì)的,我們對(duì)關(guān)鍵幀的求解過(guò)程做了進(jìn)一步的擴(kuò)展。該方法首先引入模型機(jī)制建立模型,運(yùn)用該模型將運(yùn)動(dòng)捕捉數(shù)據(jù)的分割問(wèn)題建模成一個(gè)有序樣本聚類(lèi)問(wèn)題。其次,采用最優(yōu)分割算法對(duì)運(yùn)動(dòng)捕捉數(shù)據(jù)進(jìn)行分段,求出最小化段內(nèi)平方誤差和。最后提取出分割點(diǎn)和每段中幀姿態(tài)與均值誤差最小的幀作為關(guān)鍵幀。實(shí)驗(yàn)結(jié)果表明,與DWT以及PAA算法進(jìn)行相比,所提出的方法具有較好的可視化結(jié)果,所得關(guān)鍵幀在表達(dá)原始運(yùn)動(dòng)捕捉數(shù)據(jù)上具有一定優(yōu)勢(shì),能夠?qū)υ歼\(yùn)動(dòng)捕捉數(shù)據(jù)進(jìn)行較好的概括和總結(jié)。(3)設(shè)計(jì)并實(shí)現(xiàn)了基于三維運(yùn)動(dòng)捕捉數(shù)據(jù)關(guān)鍵幀的動(dòng)畫(huà)合成系統(tǒng)�；谝陨系膬煞N方法,結(jié)合貝塞爾曲線(xiàn)算法,運(yùn)用軟件設(shè)計(jì)過(guò)程中面向?qū)ο蟮乃枷?設(shè)計(jì)并實(shí)現(xiàn)了基于三維運(yùn)動(dòng)捕捉數(shù)據(jù)關(guān)鍵幀的動(dòng)畫(huà)合成系統(tǒng)。該系統(tǒng)不僅界面友好,操作簡(jiǎn)單,功能齊全,而且系統(tǒng)的動(dòng)畫(huà)片段重用性高,能夠?qū)崿F(xiàn)別具一格的動(dòng)畫(huà)效果,進(jìn)一步驗(yàn)證了方法的可用性。
[Abstract]:With the development of science and technology, the application of animation synthesis technology is more and more extensive. Animation synthesis technology has a new functional requirement, that is, to reuse the existing actions, thus producing some different effects. That is, using animation synthesis technology to give users a strong visual impact, and bring them shocking comedy effect. The existing animation synthesis technology can not meet this demand. To solve this problem, this paper makes a related research, aiming to create a distinctive animation effect through existing actions. In this paper, the research background and significance of the subject are discussed, and the related applications and existing problems are deeply studied. The research method of this paper is designed and implemented: an animation synthesis method based on the key frames of 3D motion capture data. Then around the related work of the subject, the technical content of animation synthesis is expounded, and the technical characteristics of motion synthesis and motion redirection in 3D animation synthesis field are briefly introduced, and the key technologies required by them are further introduced. There are key frame extraction techniques and motion capture segmentation techniques. Based on the existing theoretical research, this paper designs and proposes two key frame extraction methods. Finally, an animation synthesis system based on the key frames of 3D motion capture data is designed and implemented based on the method designed and proposed in this paper and the idea of interpolation. The main contents of this paper are as follows: 1) the key frame extraction method of motion capture data based on cosine distance hierarchical clustering is designed and implemented. This method makes full use of the rotation of the node as the eigenvalue of the segmentation motion capture data, then removes the noise from the captured data, and then maps the high-dimensional data to the low-dimensional data by reducing the dimension. Then the similarity is calculated by cosine distance, and then hierarchical clustering is used to segment the frame pose and the frame with the minimum mean error in each segmentation point and segment as the key frame sequence. Experimental results show that compared with rate-based segmentation and curvature based segmentation, the proposed method has high accuracy and recall rate. (2) A motion capture key frame extraction method based on optimal segmentation is proposed. Considering that the key frame extraction method of motion capture data based on cosine distance hierarchical clustering is only designed by empirical heuristic we extend the key frame solving process. Firstly, the model mechanism is introduced to model the segmentation of motion capture data as an ordered sample clustering problem. Secondly, the optimal segmentation algorithm is used to segment the motion capture data to minimize the sum of square error. Finally, the frame with the minimum error between the attitude and the mean value of each segment is extracted as the key frame. The experimental results show that the proposed method has better visualization results than DWT and PAA algorithms, and the key frames have some advantages in representing the original motion capture data. The animation synthesis system based on the key frame of 3D motion capture data is designed and implemented. Based on the above two methods and the algorithm of Bezier curve, an animation synthesis system based on the key frame of 3D motion capture data is designed and implemented by using the object-oriented idea in the software design process. The system not only has friendly interface, simple operation, complete function, but also has high reusability of animation fragment, which can realize unique animation effect, and further verify the usability of the method.
【學(xué)位授予單位】：江蘇大學(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 郭燕;曾光;楊波;;基于頻率自適應(yīng)的雙二階巴特沃斯數(shù)字濾波方法[J];智能電網(wǎng);2016年12期

2 黃淼;王劉濤;張海朝;;基于Gabor小波變換與K-L高斯黎曼流形判別的人臉識(shí)別[J];計(jì)算機(jī)工程;2016年09期

3 翁國(guó)慶;;基于有序樣本聚類(lèi)分析法和Logistic模型的閩楠苗高年生長(zhǎng)規(guī)律研究[J];安徽農(nóng)學(xué)通報(bào);2016年16期

4 王淑俠;張茜;王守霞;王關(guān)峰;高滿(mǎn)屯;;基于速度特征的在線(xiàn)手繪筆畫(huà)快速分割方法[J];西北工業(yè)大學(xué)學(xué)報(bào);2016年02期

5 胡圓圓;干宗良;陳昌紅;崔子冠;劉峰;;監(jiān)控視頻中基于運(yùn)動(dòng)目標(biāo)顯著性的關(guān)鍵幀提取方法[J];南京郵電大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年01期

6 沈晴;班曉娟;常征;郭靖;;基于視頻的人機(jī)交互中動(dòng)作在線(xiàn)發(fā)現(xiàn)與時(shí)域分割[J];計(jì)算機(jī)學(xué)報(bào);2015年12期

7 吳鵬;李雯霖;宋文龍;;基于C-V模型無(wú)關(guān)曲率方向的快速分割算法[J];哈爾濱工程大學(xué)學(xué)報(bào);2015年12期

8 李新華;趙娟;袁振宇;王晨e，

本文編號(hào)：1834329