【摘要】：WiFi信號(hào)作為一種工作在2.4GHz和5.8GHz頻段的無(wú)線電波,具有波長(zhǎng)小,頻率高,帶寬足的特點(diǎn),適合大量數(shù)據(jù)傳輸,因而在短距離無(wú)線通信領(lǐng)域的到廣泛應(yīng)用。隨著模式識(shí)別和人機(jī)交互技術(shù)的不斷發(fā)展,WiFi信號(hào)在目標(biāo)探測(cè)和識(shí)別方面的強(qiáng)大能力被逐漸挖掘出來(lái)。如今,研究人員借助WiFi信號(hào)已經(jīng)能夠識(shí)別出目標(biāo)的位置、人體的姿勢(shì),甚至是手勢(shì),基于WiFi信號(hào)的識(shí)別技術(shù)已然成為研究熱點(diǎn)。基于以上背景,本文對(duì)利用WiFi信號(hào)實(shí)現(xiàn)手勢(shì)識(shí)別的關(guān)鍵技術(shù)進(jìn)行了探討,構(gòu)建出了初步的手勢(shì)識(shí)別模型,并對(duì)其中涉及到的信號(hào)處理、特征提取和分類識(shí)別算法進(jìn)行了深入的剖析。當(dāng)WiFi信號(hào)在傳播過(guò)程中遇到動(dòng)態(tài)手勢(shì)時(shí),其幅度、相位和功率等傳輸特性會(huì)受到一定的影響,這種影響是由手勢(shì)的移動(dòng)特征決定的,這就意味著穿過(guò)手勢(shì)的WiFi信號(hào)在某種意義上受到了手勢(shì)的調(diào)制,包含了手勢(shì)移動(dòng)特性的信息,只要采用合理的方式將這一信息解調(diào)出來(lái),就能夠?qū)崿F(xiàn)動(dòng)作的識(shí)別。一般來(lái)說(shuō),完善的手勢(shì)識(shí)別過(guò)程首先需要通過(guò)數(shù)據(jù)采集、數(shù)據(jù)預(yù)處理來(lái)建立適合特征提取的手勢(shì)模型;其次采用特定的特征提取算法對(duì)手勢(shì)進(jìn)行特征提取以獲取相應(yīng)的特征向量;然后,構(gòu)建能夠?qū)μ卣飨蛄窟M(jìn)行有效分類的識(shí)別算法模型;最后,為了驗(yàn)證識(shí)別方法的有效性,常常需要將特征向量分為訓(xùn)練集合和測(cè)試集合,訓(xùn)練集合作為分類識(shí)別算法的輸入以訓(xùn)練識(shí)別模型,測(cè)試集合則輸入訓(xùn)練好的識(shí)別模型以獲取識(shí)別率,驗(yàn)證識(shí)別算法的有效性。在本文中,WiFi信號(hào)數(shù)據(jù)的采集由SORA軟件無(wú)線電平臺(tái)完成,本文保留802.11數(shù)據(jù)幀的長(zhǎng)前導(dǎo)部分作為原始數(shù)據(jù),通過(guò)數(shù)據(jù)預(yù)處理獲取WiFi信號(hào)的功率包絡(luò),并對(duì)該包絡(luò)進(jìn)行周期分割,把得到的周期片段作為手勢(shì)模型;為了降低原始樣本中所包含信息的維度,同時(shí)減少無(wú)關(guān)噪聲的干擾,本文采用離散小波變換(DTW)對(duì)原始樣本進(jìn)行特征提取,在保留足夠的手勢(shì)運(yùn)動(dòng)信息的條件下,大幅度壓縮了特征數(shù)據(jù)量;在分類識(shí)別階段,本文選擇支持向量機(jī)(SVM)作為建立分類識(shí)別模型的主要算法,同時(shí)采用動(dòng)態(tài)時(shí)間規(guī)整(DTW)算法對(duì)支持向量機(jī)的核函數(shù)進(jìn)行了改造,以保證支持向量機(jī)能夠適用于變長(zhǎng)特征向量的分類。仿真和測(cè)試結(jié)果表明,本文提出的基于WiFi信號(hào)的手勢(shì)識(shí)別技術(shù)的方法模型能夠在少量樣本條件下,有效識(shí)別9個(gè)預(yù)先定義的常用動(dòng)態(tài)手勢(shì),平均識(shí)別率可達(dá)94.8%,具有一定的研究?jī)r(jià)值和實(shí)用性,為相關(guān)問(wèn)題的解決提供了新的思路。
[Abstract]:As a kind of radio wave operating in 2.4GHz and 5.8GHz band, WiFi signal has the characteristics of small wavelength, high frequency and sufficient bandwidth, so it is suitable for a large number of data transmission, so it is widely used in the field of short-range wireless communication. With the development of pattern recognition and human-computer interaction technology, the powerful ability of WiFi signal in target detection and recognition is gradually excavated. Now, researchers have been able to identify the location of the target, the posture of the human body, and even the gesture with the help of the WiFi signal. The recognition technology based on the WiFi signal has become a hot research topic. Based on the above background, this paper discusses the key technology of using WiFi signal to realize gesture recognition, constructs a preliminary gesture recognition model, and processes the signal involved in it. The algorithms of feature extraction and classification recognition are deeply analyzed. When a WiFi signal encounters a dynamic gesture in the process of propagation, its transmission characteristics, such as amplitude, phase and power, will be affected to a certain extent, which is determined by the movement characteristics of the gesture. This means that the WiFi signal passing through the gesture is modulated by the gesture in a certain sense, which contains the information of the movement characteristic of the gesture. So long as the information is demodulated in a reasonable way, the motion recognition can be realized. Generally speaking, the perfect gesture recognition process first needs to establish the gesture model which is suitable for feature extraction through data acquisition and data pre-processing. Secondly, the special feature extraction algorithm is used to extract the gesture feature to obtain the corresponding feature vector, and then, the recognition algorithm model which can classify the feature vector effectively is constructed. Finally, in order to verify the effectiveness of the recognition method, it is often necessary to divide the feature vectors into training set and test set, and the training set is used as the input of the classification recognition algorithm to train the recognition model. The test sets input the trained recognition model to obtain the recognition rate and verify the effectiveness of the recognition algorithm. In this paper, the acquisition of WiFi signal data is accomplished by SORA software radio platform. In this paper, the long leading part of 802.11 data frame is retained as the original data, and the power envelope of WiFi signal is obtained by data preprocessing. The periodic segmentation of the envelope is carried out and the obtained periodic segment is used as the gesture model. In order to reduce the dimension of the information contained in the original sample and reduce the interference of irrelevant noise, the discrete wavelet transform (DTW) is used to extract the features of the original sample. The feature data is greatly compressed; In the stage of classification and recognition, support vector machine (SVM) is chosen as the main algorithm to establish the classification and recognition model. Meanwhile, the kernel function of SVM is modified by dynamic time warping (DTW) algorithm. In order to ensure that support vector machine can be applied to variable length feature vector classification. The simulation and test results show that the proposed method model of gesture recognition based on WiFi signal can effectively recognize 9 pre-defined dynamic gestures with an average recognition rate of 94.8% under a small number of samples. It has certain research value and practicability, and provides a new way to solve the related problems.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41;TN92

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 徐偉業(yè);;一種快速離散小波變換算法及其在語(yǔ)音信號(hào)中的應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2011年35期

2 黃國(guó)范;程小平;;基于歷史的動(dòng)態(tài)手勢(shì)識(shí)別[J];西南大學(xué)學(xué)報(bào)(自然科學(xué)版);2009年01期

3 耿冠宏;孫偉;羅培;;神經(jīng)網(wǎng)絡(luò)模式識(shí)別[J];軟件導(dǎo)刊;2008年10期

4 朱樹(shù)先;張仁杰;;支持向量機(jī)核函數(shù)選擇的研究[J];科學(xué)技術(shù)與工程;2008年16期

5 茍博;黃賢武;;支持向量機(jī)多類分類方法[J];數(shù)據(jù)采集與處理;2006年03期

6 何建新,劉真祥;SVM與DTW結(jié)合實(shí)現(xiàn)語(yǔ)音分類識(shí)別[J];貴州大學(xué)學(xué)報(bào)(自然科學(xué)版);2002年04期

7 李清水,方志剛,沈模衛(wèi),陳育偉;手勢(shì)識(shí)別技術(shù)及其在人機(jī)交互中的應(yīng)用[J];人類工效學(xué);2002年01期

8 吳江琴,高文;基于DGMM的中國(guó)手語(yǔ)識(shí)別系統(tǒng)[J];計(jì)算機(jī)研究與發(fā)展;2000年05期

9 張學(xué)工;關(guān)于統(tǒng)計(jì)學(xué)習(xí)理論與支持向量機(jī)[J];自動(dòng)化學(xué)報(bào);2000年01期

10 梁甸農(nóng),周智敏;葉簇穿透超寬帶成像雷達(dá)技術(shù)[J];國(guó)防科技參考;1999年03期

相關(guān)博士學(xué)位論文 前2條

1 翟世俊;基于UWB信號(hào)的目標(biāo)識(shí)別關(guān)鍵技術(shù)研究[D];北京郵電大學(xué);2014年

2 李玉峰;小波分析在圖像去噪與壓縮中的應(yīng)用研究[D];中國(guó)科學(xué)院研究生院（長(zhǎng)春光學(xué)精密機(jī)械與物理研究所）;2006年

相關(guān)碩士學(xué)位論文 前9條

1 龐琳;基于Sora平臺(tái)的低功耗WiFi系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];鄭州大學(xué);2014年

2 嚴(yán)志航;基于小波變換和動(dòng)態(tài)時(shí)間規(guī)整的計(jì)步器算法設(shè)計(jì)[D];南京理工大學(xué);2014年

3 王根平;基于小波變換的信號(hào)分析及處理[D];西安電子科技大學(xué);2013年

4 黃剛林;基于SORA軟件無(wú)線電平臺(tái)DTMB接收技術(shù)的實(shí)現(xiàn)[D];武漢理工大學(xué);2013年

5 常亞南;基于HMM的動(dòng)態(tài)手勢(shì)識(shí)別[D];華南理工大學(xué);2012年

6 李劍飛;基于視覺(jué)的實(shí)時(shí)手勢(shì)跟蹤與識(shí)別研究[D];北方工業(yè)大學(xué);2011年

7 張郝;基于小波變換的圖像去噪方法研究[D];北京交通大學(xué);2008年

8 王茂吉;基于視覺(jué)的靜態(tài)手勢(shì)識(shí)別系統(tǒng)[D];哈爾濱工業(yè)大學(xué);2006年

9 高寧;陀螺漂移信號(hào)的小波去噪及其誤差模型的研究[D];天津大學(xué);2004年

，

本文編號(hào)：2449074