本文選題：Kinect + 手型分割��； 參考：《南京理工大學(xué)》2017年碩士論文

【摘要】：隨著人機(jī)交互技術(shù)的不斷發(fā)展,各種新奇的人機(jī)交互方式層出不窮,手勢(shì)識(shí)別技術(shù)以其學(xué)習(xí)成本低、靈活性好、實(shí)用性強(qiáng)等特點(diǎn),近年來成為研究的熱點(diǎn)�；谝曈X技術(shù)的手勢(shì)識(shí)別受光照、噪聲等因素的影響較大,限制了對(duì)手勢(shì)識(shí)別技術(shù)的應(yīng)用。Kinect傳感器能夠在獲取二維圖像的同時(shí)獲得空間的三維深度信息,為手勢(shì)識(shí)別的研究帶來了新的方向,本文利用Kinect2.0深度傳感器,對(duì)具有手型變化的動(dòng)態(tài)復(fù)雜手勢(shì)的進(jìn)行識(shí)別。主要包括手型圖像的分割、手型特征和手勢(shì)運(yùn)動(dòng)特征的提取、手勢(shì)的分類識(shí)別等步驟。首先對(duì)于手型圖像的分割,采用了 Kinect骨骼跟蹤技術(shù)和深度信息相結(jié)合的方法,有效的消除背景和光照對(duì)手型圖像分割的影響。對(duì)獲得的手型二值圖像進(jìn)行形態(tài)學(xué)的處理,并采用邊緣跟蹤算法來實(shí)現(xiàn)手型圖像輪廓的提取。然后是手勢(shì)特征的提取,具體包括靜態(tài)手型的特征和運(yùn)動(dòng)軌跡特征。提出對(duì)靜態(tài)手型輪廓提取Hu特征并利用K-means聚類算法進(jìn)行特征編碼的方法;對(duì)于運(yùn)動(dòng)軌跡提取方向角特征,并進(jìn)行球面14方向的量化編碼,得到方向角特征編碼,手型特征編碼和方向角特征編碼分別組合起來得到手勢(shì)的手型特征序列和軌跡方向角特征序列。最后對(duì)手勢(shì)進(jìn)行分類識(shí)別,將隱馬爾科夫模型和樸素貝葉斯模型相結(jié)合,提出了一種HMM-NBC模型進(jìn)行手勢(shì)的訓(xùn)練與識(shí)別。對(duì)于自定義的10種動(dòng)態(tài)手勢(shì),平均識(shí)別率達(dá)到了 88.4%。
[Abstract]:With the continuous development of human-computer interaction technology, a variety of novel human-computer interaction methods emerge in endlessly. Gesture recognition technology has become a hot research topic in recent years because of its low learning cost, good flexibility, strong practicability and so on. Gesture recognition based on visual technology is greatly affected by illumination, noise and other factors, which limits the application of gesture recognition technology. Kinect sensor can obtain three-dimensional depth information of space while obtaining two-dimensional images. It brings a new direction to the research of hand gesture recognition. In this paper, we use the Kinect2.0 depth sensor to recognize the dynamic and complex hand gesture with the change of hand shape. It mainly includes the segmentation of hand image, the extraction of hand shape feature and gesture motion feature, the recognition of hand gesture classification and so on. Firstly, Kinect bone tracking technique and depth information are used to effectively eliminate the influence of background and illumination on hand image segmentation. The obtained binary image is processed by morphology and edge tracking algorithm is used to extract the contour of the hand image. Then the gesture features are extracted, including static hand features and motion trajectory features. A method of extracting Hu features from static hand contours and using K-means clustering algorithm to encode features is proposed. Hand feature coding and directional angle feature coding are combined to obtain hand gesture feature sequence and trajectory direction angle characteristic sequence respectively. Finally, a HMM-NBC model is proposed to train and recognize gestures by combining hidden Markov model with naive Bayes model. For the 10 kinds of dynamic gestures, the average recognition rate is 88. 4%.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張毅;姚圓圓;羅元;;基于B參數(shù)的改進(jìn)HMM動(dòng)態(tài)手勢(shì)識(shí)別算法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2015年S1期

2 蔡娟;蔡堅(jiān)勇;廖曉東;黃海濤;丁僑俊;;基于卷積神經(jīng)網(wǎng)絡(luò)的手勢(shì)識(shí)別初探[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2015年04期

3 郭文爽;王雪芳;;基于HOG和SVM的手勢(shì)檢測(cè)技術(shù)[J];電子科技;2014年08期

4 晏浩;張明敏;童晶;潘志庚;;基于Kinect的實(shí)時(shí)穩(wěn)定的三維多手指跟蹤算法[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2013年12期

5 王先軍;白國振;楊勇明;;復(fù)雜背景下BP神經(jīng)網(wǎng)絡(luò)的手勢(shì)識(shí)別方法[J];計(jì)算機(jī)應(yīng)用與軟件;2013年03期

6 曹雛清;李瑞峰;趙立軍;;基于深度圖像技術(shù)的手勢(shì)識(shí)別方法[J];計(jì)算機(jī)工程;2012年08期

7 王書朋;姬紅兵;;利用團(tuán)塊模型進(jìn)行目標(biāo)跟蹤[J];西安電子科技大學(xué)學(xué)報(bào);2008年05期

8 王西穎;戴國忠;張習(xí)文;張鳳軍;;基于HMM-FNN模型的復(fù)雜動(dòng)態(tài)手勢(shì)識(shí)別[J];軟件學(xué)報(bào);2008年09期

9 解凱,郭恒業(yè),張?zhí)镂?一種具有徑向畸變校正的圖像整合算法[J];電子學(xué)報(bào);2004年10期

10 張良國,吳江琴,高文,姚鴻勛;基于Hausdorff距離的手勢(shì)識(shí)別[J];中國圖象圖形學(xué)報(bào);2002年11期

，

本文編號(hào)：1775427