本文選題：目標(biāo)檢測(cè) + 手勢(shì)分割�。� 參考：《南京理工大學(xué)》2017年碩士論文

【摘要】：科技進(jìn)步使人機(jī)交互方式朝著更加自然、人性化的方向發(fā)展,傳統(tǒng)的交互方式已不能滿足人們的需求。近年來(lái)增強(qiáng)現(xiàn)實(shí)和虛擬現(xiàn)實(shí)技術(shù)發(fā)展迅速,推動(dòng)了基于手勢(shì)識(shí)別的交互技術(shù)的發(fā)展,除此之外,手勢(shì)識(shí)別在無(wú)人機(jī)控制、智能家居和手語(yǔ)識(shí)別等眾多領(lǐng)域都有廣泛應(yīng)用,在此背景下,本文對(duì)手勢(shì)識(shí)別算法進(jìn)行研究,并最終模擬鼠標(biāo)功能,實(shí)現(xiàn)了單目視覺(jué)下自然人手的人機(jī)交互。本文所實(shí)現(xiàn)交互系統(tǒng)由手勢(shì)分割、手勢(shì)跟蹤、手勢(shì)識(shí)別、系統(tǒng)實(shí)現(xiàn)等模塊組成。在手勢(shì)分割模塊中,針對(duì)固定閾值的膚色分割方法不能適應(yīng)實(shí)際復(fù)雜多變環(huán)境的問(wèn)題,提出了對(duì)人手進(jìn)行現(xiàn)場(chǎng)膚色建模,并利用此模型進(jìn)行后續(xù)手勢(shì)的分割,實(shí)驗(yàn)結(jié)果顯示能有效地從復(fù)雜背.景中分割出手勢(shì)。在手勢(shì)跟蹤模塊,使用核相關(guān)濾波器跟蹤手勢(shì)目標(biāo),針目標(biāo)跟蹤丟失的問(wèn)題,提出了2種目標(biāo)再檢測(cè)機(jī)制。在跟蹤前需要對(duì)目標(biāo)初始化,本文使用支持向量機(jī)和滑動(dòng)窗口檢測(cè)人手,但滑動(dòng)窗口遍歷整幅圖片,帶來(lái)巨大的時(shí)間開(kāi)銷(xiāo),針對(duì)人手的運(yùn)動(dòng)特性以及背景靜止的特點(diǎn),提出了檢測(cè)之前先利用改進(jìn)的幀間差分法檢測(cè)運(yùn)動(dòng)區(qū)域,縮小檢測(cè)范圍,該方法使檢測(cè)區(qū)域減少到原來(lái)的四分之一,顯著提高了檢測(cè)速率。在手勢(shì)識(shí)別模塊,使用傅里葉描述子作為手勢(shì)特征,選擇k最近鄰法對(duì)靜態(tài)手勢(shì)進(jìn)行識(shí)別,在動(dòng)態(tài)手勢(shì)識(shí)別中,提出了更簡(jiǎn)潔的統(tǒng)計(jì)計(jì)數(shù)識(shí)別方法,此算法完全滿足系統(tǒng)實(shí)時(shí)性要求。系統(tǒng)實(shí)現(xiàn)模塊調(diào)用應(yīng)用程序接口函數(shù)實(shí)現(xiàn)對(duì)鼠標(biāo)的模擬,并利用MFC開(kāi)發(fā)了一個(gè)對(duì)話框程序,對(duì)手勢(shì)識(shí)別結(jié)果進(jìn)行直觀的展示。
[Abstract]:The progress of science and technology makes the human-computer interaction more natural and humanized. The traditional way of interaction can not meet the needs of people. In recent years, the rapid development of augmented reality and virtual reality technology has promoted the development of interactive technology based on gesture recognition. In addition, gesture recognition has been widely used in many fields, such as UAV control, smart home and sign language recognition, etc. Under this background, this paper studies the gesture recognition algorithm, and finally simulates the mouse function, realizes the man-machine interaction of natural hand under monocular vision. The interactive system is composed of gesture segmentation, gesture tracking, gesture recognition, system implementation and so on. In the hand gesture segmentation module, aiming at the problem that the fixed threshold skin color segmentation method can not adapt to the actual complex and changeable environment, a skin color modeling method is proposed for the human hand, and the following hand gesture segmentation is carried out using this model. The experimental results show that it is effective from the complex back. Cut out the gestures in the scene. In the hand gesture tracking module, the kernel correlation filter is used to track the gesture target, and the problem of missing needle target tracking is discussed. Two kinds of target re-detection mechanisms are proposed. It is necessary to initialize the target before tracking. Support vector machine and sliding window are used to detect the human hand, but the sliding window traverses the whole picture, which brings huge time cost, aiming at the movement characteristics of the hand and the static background. Before detection, the improved inter-frame differential method is used to detect the motion area and reduce the detection range. This method reduces the detection area to 1/4, and improves the detection rate significantly. In the gesture recognition module, the Fourier descriptor is used as the gesture feature, and the k-nearest neighbor method is selected to recognize the static gesture. In dynamic gesture recognition, a more concise statistical counting recognition method is proposed. This algorithm fully meets the real-time requirement of the system. The system realizes the simulation of mouse by calling the application program interface function, and develops a dialog program with MFC to show the result of gesture recognition intuitively.
【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(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 路莉;;未來(lái)必勝的虛擬現(xiàn)實(shí)技術(shù)[J];中國(guó)發(fā)明與專(zhuān)利;2016年02期

2 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

3 羅元;謝_g;張毅;;基于Kinect傳感器的智能輪椅手勢(shì)控制系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[J];機(jī)器人;2012年01期

4 湯勇;顧宏斌;周來(lái);;交互系統(tǒng)中實(shí)時(shí)手勢(shì)分割及指尖檢測(cè)方法[J];光電工程;2010年07期

5 陶霖密,彭振云,徐光yP;人體的膚色特征[J];軟件學(xué)報(bào);2001年07期

6 吳江琴;高文;陳熙霖;;基于數(shù)據(jù)手套輸入的漢語(yǔ)手指字母的識(shí)別[J];模式識(shí)別與人工智能;1999年01期

7 曾芬芳,李精文,歸寶琪,袁野,陳良貴;手模型分析及手勢(shì)識(shí)別[J];華東船舶工業(yè)學(xué)院學(xué)報(bào);1998年05期

，

本文編號(hào)：2005281