本文選題：加速度傳感器 + 人體姿態(tài)識(shí)別　； 參考：《長(zhǎng)沙理工大學(xué)》2016年碩士論文

【摘要】：近些年來(lái),隨著微型機(jī)電系統(tǒng)(MEMS)技術(shù)的飛速發(fā)展和模式識(shí)別理論研究的不斷深入,基于加速度傳感器的人體姿態(tài)識(shí)別已經(jīng)成為了人體姿態(tài)識(shí)別領(lǐng)域中一個(gè)重要的研究方向,在運(yùn)動(dòng)分析、醫(yī)療監(jiān)護(hù)、體感游戲和能耗評(píng)估等領(lǐng)域受到了廣泛的關(guān)注。相比于基于圖像分析的人體姿態(tài)識(shí)別,該方法不受環(huán)境約束,成本低,能耗少,擁有更為廣闊的應(yīng)用前景。當(dāng)前,基于加速度傳感器的人體姿態(tài)識(shí)別研究仍處在一個(gè)比較基礎(chǔ)的階段,由于客觀環(huán)境的多樣性和人體運(yùn)動(dòng)的復(fù)雜性使得基于加速度傳感器的人體姿態(tài)識(shí)別研究還存在很多急需解決的問(wèn)題,其中包括如何提取具有更強(qiáng)表征能力的數(shù)據(jù)特征,如何設(shè)計(jì)高效、精確的分類器等。圍繞這些問(wèn)題和難點(diǎn),本文針對(duì)基于加速度傳感器的人體姿態(tài)識(shí)別技術(shù)展開(kāi)了一系列的研究,主要的工作如下:(1)、總結(jié)了現(xiàn)有的人體姿態(tài)識(shí)別方法,比較了基于圖像分析和基于加速度傳感器的兩種方法,系統(tǒng)地對(duì)數(shù)據(jù)采集、數(shù)據(jù)預(yù)處理、特征提取和選取、分類算法等模塊進(jìn)行了分析。(2)、提出了一種基于改進(jìn)粒子群(PSO)優(yōu)化神經(jīng)網(wǎng)絡(luò)的人體姿態(tài)識(shí)別算法。首先在常用特征集的基礎(chǔ)上,加入離散系數(shù)和曲線積分這兩種能夠反映加速度變化趨勢(shì)和速度變化量的特征作為神經(jīng)網(wǎng)絡(luò)的輸入;然后在利用PSO優(yōu)化神經(jīng)網(wǎng)絡(luò)參數(shù)的同時(shí),通過(guò)控制概率,自適應(yīng)地對(duì)粒子進(jìn)行遺傳操作,增強(qiáng)了粒子跳出局部極小值的能力,并利用訓(xùn)練得到的分類模型對(duì)6種人體姿態(tài)進(jìn)行識(shí)別,實(shí)驗(yàn)結(jié)果發(fā)現(xiàn)改進(jìn)PSO優(yōu)化神經(jīng)網(wǎng)絡(luò)的收斂速度和全局尋優(yōu)能力得到了提高,與其他經(jīng)典分類算法相比識(shí)別精度更高。(3)、提出了一種基于窗口相似度的人體姿態(tài)識(shí)別算法。首先采用曲線擬合對(duì)離散加速度數(shù)據(jù)進(jìn)行處理,并利用粒子群算法優(yōu)化關(guān)鍵參數(shù)后得到其擬合曲線;然后計(jì)算不同擬合曲線之間的窗口相似度,并以窗口相似度作為距離度量,采用K近鄰分類算法來(lái)識(shí)別人體姿態(tài)。通過(guò)實(shí)驗(yàn)對(duì)比說(shuō)明該算法的計(jì)算量較小,且能準(zhǔn)確地識(shí)別6種人體姿態(tài)�？偠灾�,基于加速度傳感器的人體姿態(tài)識(shí)別仍處在發(fā)展階段,該課題的研究具有很大的理論價(jià)值和實(shí)際需要,值得人們?nèi)ミM(jìn)行更深入、細(xì)致的研究。
[Abstract]:In recent years, with the rapid development of MEMS technology and the development of pattern recognition theory, human attitude recognition based on acceleration sensor has become an important research direction in the field of human attitude recognition. Sports analysis, medical monitoring, somatosensory games and energy consumption evaluation have received extensive attention. Compared with the human body attitude recognition based on image analysis, this method is not subject to environmental constraints, low cost, less energy consumption, and has a wider application prospect. At present, the research of human body attitude recognition based on acceleration sensor is still in a relatively basic stage. Due to the diversity of objective environment and the complexity of human motion, there are still many problems that need to be solved in the research of human attitude recognition based on acceleration sensor, including how to extract the data features with stronger representation ability. How to design efficient and accurate classifiers. Focusing on these problems and difficulties, this paper has carried out a series of research on the technology of human body attitude recognition based on acceleration sensor. The main work is as follows: 1. The existing methods of human body attitude recognition are summarized. Two methods based on image analysis and acceleration sensor are compared. Data acquisition, data preprocessing, feature extraction and selection are systematically compared. The classification algorithm and other modules are analyzed, and a human body attitude recognition algorithm based on improved particle swarm optimization (PSO) neural network is proposed. Firstly, the discrete coefficient and curve integral, which can reflect the trend of acceleration and the variation of velocity, are added as the input of neural network on the basis of common feature sets, and then the parameters of neural network are optimized by using PSO. By controlling probability and adaptively genetic manipulation of particles, the ability of particles to jump out of local minimum is enhanced, and six kinds of human posture are recognized by the trained classification model. The experimental results show that the convergence speed and global optimization ability of the improved PSO optimization neural network are improved and the recognition accuracy is higher than other classical classification algorithms. A human body attitude recognition algorithm based on window similarity is proposed. Firstly, the discrete acceleration data are processed by curve fitting, and the key parameters are optimized by particle swarm optimization algorithm to get the fitting curve, then the window similarity between different fitting curves is calculated, and the window similarity is taken as the distance measure. K nearest neighbor classification algorithm is used to recognize human posture. The experimental results show that the algorithm is less computational and can accurately identify six human body postures. In a word, the attitude recognition of human body based on acceleration sensor is still in the development stage, the research of this subject has great theoretical value and practical need, and it is worth people to carry out more in-depth and detailed research.
【學(xué)位授予單位】：長(zhǎng)沙理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41;TP212

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張雨晨;金心宇;沈劍峰;;可穿戴健康監(jiān)測(cè)設(shè)備現(xiàn)狀和技術(shù)分析[J];醫(yī)學(xué)信息學(xué)雜志;2015年09期

2 劉磊;楊鵬;劉作軍;;基于多源信息和粒子群優(yōu)化算法的下肢運(yùn)動(dòng)模式識(shí)別[J];浙江大學(xué)學(xué)報(bào)(工學(xué)版);2015年03期

3 劉宇;江宏毅;王仕亮;王伊冰;陳燕蘋;;基于加速度時(shí)域特征的實(shí)時(shí)人體行為模式識(shí)別[J];上海交通大學(xué)學(xué)報(bào);2015年02期

4 王忠民;王斌;;多頻段時(shí)域分解的行為識(shí)別特征優(yōu)選方法[J];計(jì)算機(jī)應(yīng)用研究;2015年07期

5 陳國(guó)良;張言哲;楊洲;;一種基于手機(jī)傳感器自相關(guān)分析的計(jì)步器實(shí)現(xiàn)方法[J];中國(guó)慣性技術(shù)學(xué)報(bào);2014年06期

6 李東潔;李君祥;張?jiān)?曾y，

本文編號(hào)：1894996