本文選題：加速度傳感器　切入點(diǎn)：人體行為識(shí)別　出處：《江南大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：基于加速度傳感器的人體行為識(shí)別是模式識(shí)別領(lǐng)域中的一個(gè)新興的研究方向，它的迅速發(fā)展受惠于微電子和傳感器技術(shù)的不斷進(jìn)步以及模式識(shí)別理論的深入研究。隨著人們對(duì)智能交互和健康監(jiān)護(hù)等方面需求的日益增長(zhǎng)，基于加速度傳感器的人體行為識(shí)別在醫(yī)療保健、運(yùn)動(dòng)檢測(cè)、能耗評(píng)估等領(lǐng)域受到了廣泛的關(guān)注。與基于計(jì)算機(jī)視覺(jué)的行為識(shí)別不同，基于加速度傳感器的方法更能體現(xiàn)人體運(yùn)動(dòng)的本質(zhì)，而且不受特定的場(chǎng)景和時(shí)間限制，能量消耗少，成本較低，更適合推廣應(yīng)用。 雖然近年來(lái)基于加速度傳感器的行為識(shí)別取得了極大的進(jìn)展，但仍面臨不少急需解決的問(wèn)題，包括如何提取具有較強(qiáng)表征能力的信號(hào)特征，如何面向?qū)嶋H應(yīng)用設(shè)計(jì)合理的跌倒識(shí)別方法，如何構(gòu)建高精度、泛化能力強(qiáng)的行為分類器等問(wèn)題。圍繞這些問(wèn)題，本文主要進(jìn)行了如下的研究工作： 1)總結(jié)了現(xiàn)有的行為識(shí)別方法，比較了基于計(jì)算機(jī)視覺(jué)和基于加速度傳感器兩種方法，詳細(xì)分析了基于加速度信號(hào)的行為識(shí)別具有的優(yōu)勢(shì)，系統(tǒng)研究了該類方法的實(shí)現(xiàn)過(guò)程和相關(guān)技術(shù)。 2)針對(duì)行為識(shí)別過(guò)程中的特征提取問(wèn)題，從加速度信號(hào)的時(shí)頻分析和分布特點(diǎn)的角度出發(fā)，利用小波分析等技術(shù)手段，提取了基于角度的小波能量和關(guān)鍵點(diǎn)連線斜率兩種新穎特征，從不同方面對(duì)加速度信號(hào)進(jìn)行刻畫(huà)。利用獨(dú)立檢測(cè)法和交叉驗(yàn)證法對(duì)不同特征集合的識(shí)別率進(jìn)行了比較，，表明了這兩種特征的有效性。 3)在跌倒識(shí)別方面，常用分類器往往需要大量的訓(xùn)練樣本，現(xiàn)有的方法常采用故意反復(fù)跌倒的方式獲取訓(xùn)練樣本，但對(duì)于用戶而言非常不便。針對(duì)這一問(wèn)題，提出了一種基于隱馬爾科夫模型和身體傾角的跌倒識(shí)別方法。該方法將跌倒識(shí)別問(wèn)題轉(zhuǎn)換為對(duì)已學(xué)模型的偏差問(wèn)題進(jìn)行處理，減小跌倒樣本量對(duì)識(shí)別結(jié)果的影響。而且基于時(shí)序分析的方法，可以有效保留研究對(duì)象前后的狀態(tài)信息，更加符合物理規(guī)律。 4)在日常行為識(shí)別方面，為了提高分類器的泛化能力和識(shí)別正確率，采用遞階遺傳算法訓(xùn)練RBF神經(jīng)網(wǎng)絡(luò)，對(duì)其結(jié)構(gòu)和參數(shù)同時(shí)尋優(yōu)。以降低分類器結(jié)構(gòu)復(fù)雜度和提高正確率為目的，設(shè)計(jì)了新的適應(yīng)度函數(shù)，利用四分位間距改進(jìn)參數(shù)基因的交叉方式，并結(jié)合兩種變異操作，提高尋優(yōu)效率。實(shí)驗(yàn)結(jié)果表明，采用改進(jìn)遞階遺傳算法訓(xùn)練的RBF網(wǎng)絡(luò)分類器，同時(shí)具備結(jié)構(gòu)精簡(jiǎn)和誤差較低的優(yōu)點(diǎn)，對(duì)7種行為的識(shí)別率可達(dá)91.54%。 5)從識(shí)別系統(tǒng)的底層出發(fā)，設(shè)計(jì)了一種加速度信號(hào)采集平臺(tái)，實(shí)現(xiàn)了對(duì)運(yùn)動(dòng)加速度數(shù)據(jù)的采集。
[Abstract]:Human behavior recognition based on acceleration sensor is a new research direction in the field of pattern recognition. Its rapid development has benefited from the continuous progress of microelectronics and sensor technology, as well as the in-depth study of pattern recognition theory. With the increasing demand for intelligent interaction and health monitoring, Human behavior recognition based on accelerometer has attracted wide attention in the fields of medical care, motion detection, energy consumption evaluation, etc., which is different from behavior recognition based on computer vision. The method based on acceleration sensor can reflect the essence of human motion, and it is not limited by the specific scene and time, and the energy consumption is less and the cost is lower, so it is more suitable for popularization and application. Although great progress has been made in behavior recognition based on acceleration sensors in recent years, there are still many problems that need to be solved, including how to extract signal features with strong representation ability. How to design a reasonable fall recognition method for practical application and how to construct a high precision and strong generalization behavior classifier. Around these problems, this paper mainly carried out the following research work:. 1) summarizing the existing behavior recognition methods, comparing the two methods based on computer vision and acceleration sensor, and analyzing the advantages of behavior recognition based on acceleration signal in detail. The realization process and related technology of this kind of method are studied systematically. 2) aiming at the problem of feature extraction in the process of behavior recognition, from the point of view of time-frequency analysis and distribution characteristics of acceleration signal, wavelet analysis and other technical means are used. Two novel features of wavelet energy based on angle and slope of key points are extracted and the acceleration signals are depicted from different aspects. The recognition rates of different feature sets are compared by using independent detection method and cross-validation method. The validity of these two features is demonstrated. 3) in the aspect of fall recognition, the common classifier often needs a large number of training samples. The existing methods often use the method of intentional repeated fall to obtain the training sample, but it is very inconvenient for the user. A fall recognition method based on Hidden Markov Model (hmm) and body inclination angle is proposed in this paper. Based on the method of time series analysis, the state information before and after the study object can be effectively retained, which is more in line with the physical law. 4) in the aspect of daily behavior recognition, in order to improve the generalization ability and recognition accuracy of classifier, hierarchical genetic algorithm is used to train RBF neural network. In order to reduce the structural complexity and improve the accuracy of the classifier, a new fitness function is designed. The crossover of parameter genes is improved by using quartile spacing, and two mutation operations are combined. The experimental results show that the RBF classifier trained by improved hierarchical genetic algorithm has the advantages of simple structure and low error, and the recognition rate of seven behaviors can reach 91.54. 5) from the bottom of the recognition system, an acceleration signal acquisition platform is designed to collect the acceleration data.
【學(xué)位授予單位】：江南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP212;TN911.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 姚成玉;趙佳偉;陳毅強(qiáng);;基于嵌入式系統(tǒng)的室內(nèi)人體跌倒行為檢測(cè)方法的實(shí)現(xiàn)[J];燕山大學(xué)學(xué)報(bào);2008年06期

2 李圣怡,劉宗林,吳學(xué)忠;微加速度計(jì)研究的進(jìn)展[J];國(guó)防科技大學(xué)學(xué)報(bào);2004年06期

3 肖玲;李仁發(fā);羅娟;;體域網(wǎng)中一種基于壓縮感知的人體動(dòng)作識(shí)別方法[J];電子與信息學(xué)報(bào);2013年01期

4 李蕊;李仁發(fā);;上下文感知計(jì)算及系統(tǒng)框架綜述[J];計(jì)算機(jī)研究與發(fā)展;2007年02期

5 石欣;張濤;;一種可穿戴式跌倒檢測(cè)裝置設(shè)計(jì)[J];儀器儀表學(xué)報(bào);2012年03期

相關(guān)博士學(xué)位論文 前3條

1 薛洋;基于單個(gè)加速度傳感器的人體運(yùn)動(dòng)模式識(shí)別[D];華南理工大學(xué);2011年

2 劉蓉;人體運(yùn)動(dòng)信息獲取及物理活動(dòng)識(shí)別研究[D];華中科技大學(xué);2009年

3 何衛(wèi)華;人體行為識(shí)別關(guān)鍵技術(shù)研究[D];重慶大學(xué);2012年

本文編號(hào)：1557051