本文關(guān)鍵詞： 基于內(nèi)容 多特征 骨架運(yùn)動(dòng)檢索　出處：《山東大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：近幾年來,隨著三維游戲一系列的創(chuàng)作產(chǎn)品不斷地興起,計(jì)算機(jī)不僅在在文化創(chuàng)作(例如廣告設(shè)計(jì)、電影創(chuàng)作、動(dòng)畫特效)、人機(jī)交互、游戲創(chuàng)作、廣告娛樂等應(yīng)用中發(fā)揮著不可替代的影響,還廣泛應(yīng)用于教育事業(yè)以及國防建設(shè)、衛(wèi)星研發(fā)等科技領(lǐng)域。計(jì)算機(jī)圖形學(xué)技術(shù)以及計(jì)算機(jī)軟硬件的迅猛發(fā)展更是讓計(jì)算機(jī)有能力開發(fā)出這些產(chǎn)品,并且提供了更加便捷的途徑。隨著大規(guī)模的三維人體運(yùn)動(dòng)數(shù)據(jù)庫的不斷建立,我們需要從復(fù)雜的人體運(yùn)動(dòng)序列中找到可以準(zhǔn)確代表整個(gè)運(yùn)動(dòng)序列的屬性描述符,需要對(duì)人體運(yùn)動(dòng)數(shù)據(jù)進(jìn)行高效合理地分析與處理,以及檢索出符合用戶需求的目標(biāo)運(yùn)動(dòng)序列,這些工作都是任重而道遠(yuǎn)的。我們針對(duì)基于多特征的人體骨架運(yùn)動(dòng)數(shù)據(jù)的檢索提出了一種高效的解決方案。第一個(gè)主要的亮點(diǎn)在于我們利用不同的分步提取標(biāo)準(zhǔn),從運(yùn)動(dòng)序列中提取并描述多種特征。另外,為了更加便利高效地進(jìn)行特征匹配,我們通過主成分分析法和聚類分析法對(duì)特征描述符進(jìn)行降維,并且利用多運(yùn)動(dòng)直方圖來表示每種特征中的一個(gè)運(yùn)動(dòng)序列。最后,通過測(cè)度并排序查詢序列和數(shù)據(jù)庫中的目標(biāo)序列的運(yùn)動(dòng)直方圖的相似度,得到最終的檢索結(jié)果。多次的對(duì)比實(shí)驗(yàn)表明我們提出的算法性能和效率較為突出。其中,我們工作的主要貢獻(xiàn)在于以下四點(diǎn)：1、運(yùn)動(dòng)數(shù)據(jù)的多種特征提取。考慮到人體骨架的幾何特征可以比較真實(shí)地反映出運(yùn)動(dòng)的本質(zhì)特性,因此選取四種具有代表性的幾何特征來更加準(zhǔn)確地描述運(yùn)動(dòng)序列以提高檢索的精確度。傳統(tǒng)的二維幾何特征提取只是顯示三維人體骨架運(yùn)動(dòng)的局部幾何特征,但是在我們提出的基于多特征的人體骨架運(yùn)動(dòng)數(shù)據(jù)的檢索算法中提取基于三維空間的位置關(guān)系的特征是從全局的角度出發(fā),來表示出人體運(yùn)動(dòng)的幾何特征。這樣既可以有效精準(zhǔn)地顯示出每個(gè)關(guān)節(jié)點(diǎn)自身的獨(dú)立運(yùn)動(dòng)特征,又可以清楚明確地反映出各個(gè)關(guān)節(jié)點(diǎn)之間相互作用的運(yùn)動(dòng)特征。2、運(yùn)動(dòng)特征描述符的降維。由于我們提取出來的三維人體骨架運(yùn)動(dòng)特征描述符的維數(shù)很高,為了避免所謂的維數(shù)災(zāi)難問題,達(dá)到精準(zhǔn)的運(yùn)動(dòng)序列查詢和檢索目的,本文通過主成分分析法和聚類分析法等技術(shù)對(duì)特征描述符進(jìn)行降維來方便后續(xù)分析和處理,爭(zhēng)取以最少的代價(jià)達(dá)到更高精度的特征匹配。3、運(yùn)動(dòng)數(shù)據(jù)的特征匹配。本文針對(duì)三維人體骨架運(yùn)動(dòng)數(shù)據(jù)進(jìn)行降維、聚類分析等預(yù)處理之后,提出來利用運(yùn)動(dòng)直方圖來對(duì)處理結(jié)果進(jìn)行分析表示,也就是說可以通過計(jì)算每個(gè)類別出現(xiàn)的頻率建立出運(yùn)動(dòng)直方圖,并求得兩兩直方圖之間的歐氏距離來對(duì)查詢序列和數(shù)據(jù)庫中目標(biāo)序列進(jìn)行匹配和檢索。4、實(shí)驗(yàn)效果的評(píng)價(jià)測(cè)度。本文對(duì)查詢序列和數(shù)據(jù)庫中的每一個(gè)目標(biāo)序列的運(yùn)動(dòng)直方圖的相似度使用MAP和P@n的評(píng)價(jià)指標(biāo)進(jìn)行實(shí)驗(yàn)效果的度量,對(duì)檢索結(jié)果的性能進(jìn)行評(píng)判。
[Abstract]:In recent years, with the continuous rise of a series of creative products of 3D games, computers are not only in the cultural creation (such as advertising design, film creation, animation special effects, human-computer interaction, game creation. Advertising entertainment and other applications play an irreplaceable role, but also widely used in education and national defense construction. The rapid development of computer graphics technology and computer software and hardware makes the computer have the ability to develop these products. With the establishment of large-scale three-dimensional human motion database, we need to find attribute descriptors from complex human motion sequences that can accurately represent the entire motion sequence. It is necessary to analyze and process the human motion data efficiently and reasonably, and to retrieve the target motion sequence that meets the needs of users. We propose an efficient solution for the retrieval of human skeleton motion data based on multiple features. The first major highlight is that we use different step-by-step extraction criteria. . In addition, in order to improve the efficiency of feature matching, we reduce the dimension of feature descriptors by principal component analysis and clustering analysis. And the multi-motion histogram is used to represent a motion sequence in each feature. Finally, the similarity of the motion histogram between the query sequence and the target sequence in the database is measured and sorted. Many experiments show that the performance and efficiency of the proposed algorithm are outstanding. The main contribution of our work lies in the following four points: 1. Taking into account the geometric features of human skeleton, we can truly reflect the essential characteristics of motion. Therefore, four representative geometric features are selected to describe the motion sequence more accurately to improve the retrieval accuracy. The traditional two-dimensional geometric feature extraction is only the local geometric feature of the three-dimensional human skeleton motion. But the feature of position relation based on three-dimensional space is extracted from the global point of view in the retrieval algorithm of human skeleton motion data based on multi-feature proposed by us. In order to represent the geometric characteristics of human motion, it can effectively and accurately display the independent motion characteristics of each node itself. It can also clearly reflect the movement characteristics of the interaction between different nodes. 2, the dimension reduction of motion feature descriptor. Because we extracted the dimension of three-dimensional human skeleton motion descriptor is very high. In order to avoid the so-called dimension disaster, accurate motion sequence query and retrieval can be achieved. In this paper, the principal component analysis and clustering analysis are used to reduce the dimension of the feature descriptors to facilitate the subsequent analysis and processing, and to achieve a higher accuracy of feature matching at the least cost. Feature matching of motion data. After dimensionality reduction, clustering analysis and so on, the motion histogram is proposed to analyze and express the processing results. That is to say, the motion histogram can be established by calculating the frequency of each category, and the Euclidean distance between the two histograms can be obtained to match and retrieve the query sequence and the target sequence in the database. The similarity of the motion histogram of the query sequence and each target sequence in the database is measured by using the evaluation index of MAP and Pkinn. The performance of retrieval results was evaluated.
【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 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

2 沈軍行 ,孫守遷 ,潘云鶴;從運(yùn)動(dòng)捕獲數(shù)據(jù)中提取關(guān)鍵幀[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2004年05期

，

本文編號(hào)：1482743