本文選題：人體運(yùn)動(dòng)捕捉數(shù)據(jù)庫(kù)　切入點(diǎn)：SOM　出處：《大連大學(xué)》2011年碩士論文

【摘要】：運(yùn)動(dòng)捕獲技術(shù)的逐步發(fā)展和設(shè)備技術(shù)的進(jìn)步極大地促進(jìn)了大量三維人體運(yùn)動(dòng)捕捉數(shù)據(jù)的形成,其應(yīng)用領(lǐng)域也廣泛的拓展到到計(jì)算機(jī)動(dòng)畫(huà)、電影特技等。因此,目前圖形學(xué)領(lǐng)域和動(dòng)漫等應(yīng)用領(lǐng)域的研究熱點(diǎn)轉(zhuǎn)向了對(duì)于人體運(yùn)動(dòng)捕捉數(shù)據(jù)的研究。然而,在對(duì)運(yùn)動(dòng)捕捉數(shù)據(jù)進(jìn)行各種處理之前,必須能夠先從已有的人體運(yùn)動(dòng)捕捉數(shù)據(jù)庫(kù)中檢索出需要的運(yùn)動(dòng),而且要迅速、準(zhǔn)確。因此,如何有效的利用計(jì)算機(jī)技術(shù),能夠自動(dòng)地從運(yùn)動(dòng)捕捉數(shù)據(jù)庫(kù)中迅速而又準(zhǔn)確地檢索出需要的各種運(yùn)動(dòng)是一個(gè)亟待解決的問(wèn)題。 本文是在利用自組織映射神經(jīng)網(wǎng)絡(luò)(SOM)的拓?fù)涮匦詫?duì)人體運(yùn)動(dòng)捕捉數(shù)據(jù)進(jìn)行特征映射的基礎(chǔ)上,提出了基于SOM特性和主成分分析(PCA)索引相結(jié)合的三維運(yùn)動(dòng)檢索,以及基于SOM特性和加權(quán)馬氏距離相結(jié)合的三維運(yùn)動(dòng)檢索兩種算法。為了簡(jiǎn)化運(yùn)動(dòng)檢索的流程,本文利用SOM的特征映射來(lái)實(shí)現(xiàn)特征提取和數(shù)據(jù)降維的結(jié)合,而普通的SOM必須經(jīng)過(guò)拓?fù)涮匦约訌?qiáng)處理才能來(lái)進(jìn)行特征提取。利用SOM把每一種運(yùn)動(dòng)都映射到特征曲面之后,一種思路是利用PCA算法提取特征曲面的最大特征向量建立索引機(jī)制,加快檢索的速率;一種思路是在特征曲面的基礎(chǔ)上通過(guò)PCA提取主成分,然后利用主成分的貢獻(xiàn)率確定加權(quán)馬氏距離的權(quán)值,最后計(jì)算加權(quán)馬氏距離進(jìn)行相似性比較。本文對(duì)兩種算法都進(jìn)行了仿真比較,實(shí)驗(yàn)結(jié)果證明了兩種算法的有效性。
[Abstract]:The gradual development of motion capture technology and the progress of equipment technology greatly promote the formation of a large number of three-dimensional human motion capture data, and its application fields are also widely extended to computer animation, film stunts and so on.Therefore, the current research focus in graphics and animation applications has turned to the study of human motion capture data.However, before processing the motion capture data, we must be able to retrieve the required motion from the existing human motion capture database, and must be quick and accurate.Therefore, how to effectively use computer technology to automatically retrieve all kinds of motion from the motion capture database quickly and accurately is an urgent problem to be solved.Based on the feature mapping of human motion capture data based on the topological characteristics of self-organizing mapping neural network (SOM), this paper proposes a 3D motion retrieval method based on the combination of SOM characteristics and principal component analysis (PCA) indexes.And three-dimensional motion retrieval algorithm based on SOM and weighted Markov distance.In order to simplify the process of motion retrieval, the feature mapping of SOM is used to realize the combination of feature extraction and data dimensionality reduction, while the common SOM must be strengthened by topological characteristics to extract features.After using SOM to map every motion to feature surface, one idea is to use PCA algorithm to extract the maximum feature vector of feature surface and build index mechanism to accelerate the speed of retrieval.One idea is to extract the principal component by PCA on the basis of the characteristic surface, then determine the weight of the weighted Markov distance by using the contribution rate of the principal component, and finally calculate the similarity of the weighted Markov distance.The two algorithms are simulated and compared in this paper. The experimental results show that the two algorithms are effective.
【學(xué)位授予單位】：大連大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2011
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 莊越挺,吳聰苗,吳飛,劉翔;多媒體交叉參照檢索系統(tǒng)研究[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2005年04期

2 劉豐 ,莊越挺 ,吳飛 ,潘云鶴;基于例子的三維運(yùn)動(dòng)檢索[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2003年10期

3 楊占華;楊燕;;SOM神經(jīng)網(wǎng)絡(luò)算法的研究與進(jìn)展[J];計(jì)算機(jī)工程;2006年16期

4 金剛,李德華,周學(xué)泳;表演動(dòng)畫(huà)中的運(yùn)動(dòng)捕捉技術(shù)[J];中國(guó)圖象圖形學(xué)報(bào);2000年03期

相關(guān)博士學(xué)位論文 前2條

1 高巖;基于內(nèi)容的運(yùn)動(dòng)檢索與運(yùn)動(dòng)合成[D];上海交通大學(xué);2006年

2 向堅(jiān);基于三維捕獲數(shù)據(jù)的人體運(yùn)動(dòng)分析關(guān)鍵技術(shù)研究[D];浙江大學(xué);2007年

，

本文編號(hào)：1724351