發(fā)布時間：2019-05-14 23:03

【摘要】：人機交互系統(tǒng)就是通過人、機器與環(huán)境之間交換不同的信息、并進(jìn)行理解與反饋的系統(tǒng),如何更有效的實現(xiàn)人機溝通、理解人類成為未來人機交互的主要研究熱點和方向,人體姿態(tài)識別技術(shù)作為其核心技術(shù)也受到越來越多的關(guān)注。目前主流研究方向有兩個部分,一是專注于人體細(xì)節(jié)動作捕捉、虛擬現(xiàn)實等技術(shù)。另一類為專注于日常應(yīng)用及健康看護的人體姿態(tài)識別技術(shù),其目的在于理解人體的典型行為,從而完成人機交互。根據(jù)數(shù)據(jù)獲得方式該技術(shù)主要分為兩大類,基于圖像的識別技術(shù)與基于傳感器的識別技術(shù)�；趫D像的識別是非接觸式,適用于固定區(qū)域中的人體姿態(tài)識別,基于傳感器的識別可以跟隨目標(biāo)進(jìn)行數(shù)據(jù)采集,不受地域限制且基于當(dāng)前的可穿戴技術(shù),其傳感器不會對接觸處的節(jié)點運動產(chǎn)生影響。因此本文將設(shè)計應(yīng)用于日常情景、基于傳感器的人體姿態(tài)識別系統(tǒng)。識別的姿態(tài)包括“行走”、“跑步”、“原地劇烈運動”、“站立”、“倚坐”、“躺臥”、“摔倒”和“正常過渡狀態(tài)”。首先本文設(shè)計了一種便攜式的數(shù)據(jù)采集終端�；诨镜臄�(shù)據(jù)采集以及便攜性要求,終端共分為四個單元:傳感器單元、控制單元、存儲單元和電源管理單元。終端采集數(shù)據(jù)穩(wěn)定,待機時間長,為人體姿態(tài)識別系統(tǒng)原始數(shù)據(jù)來源。其次本次研究為了獲得較純凈的數(shù)據(jù),將對原始數(shù)據(jù)進(jìn)行進(jìn)一步的預(yù)處理及數(shù)據(jù)特征提取。預(yù)處理包括濾噪、定標(biāo)以及去除重力加速度干擾。特征提取包括時域特征提取與頻域特征提取。具體為樣本幀的均值、標(biāo)準(zhǔn)差、中位絕對偏差、四分位距、最大值、最小值、平方和均值、伯格階數(shù)為4的AR模型系數(shù)、各軸序列相關(guān)性、信息熵特征、峰值頻點、次峰值頻點、峰值帶寬、加權(quán)平均頻點、突出頻點數(shù)量特征。經(jīng)過不同樣本間的比對,評估特征的可用性。最后構(gòu)建了基于上述特征的人體姿態(tài)識別算法。首先將“行走”、“跑步”、“原地劇烈運動”定義為運動狀態(tài),將“站立”、“倚坐”、“躺臥”定義為靜止?fàn)顟B(tài),將“摔倒”和“正常過渡狀態(tài)”定義為過渡狀態(tài)。每種狀態(tài)基于其大類特征的差異而采用支持向量機以及決策樹等分類方式進(jìn)行識分類。最后構(gòu)成了較為成熟的人體姿態(tài)識別算法架構(gòu)。
[Abstract]:Human-computer interaction system is a system in which different information is exchanged between people, machines and the environment, and how to realize human-computer communication more effectively and understand human beings becomes the main research focus and direction of human-computer interaction in the future. As its core technology, human attitude recognition technology has received more and more attention. At present, there are two main research directions, one is to focus on human detail motion capture, virtual reality and other technologies. The other kind of human posture recognition technology, which focuses on daily application and health care, aims to understand the typical behavior of human body and complete human-computer interaction. According to the data acquisition mode, the technology is mainly divided into two categories: image-based recognition technology and sensor-based recognition technology. The recognition based on image is non-contact and is suitable for human attitude recognition in fixed area. The recognition based on sensor can follow the target for data acquisition, which is not limited by region and based on the current wearable technology. The sensor has no effect on the motion of the node at the contact. Therefore, this paper applies the design to the daily situation, the human body attitude recognition system based on sensor. Identified postures include "walking", "running", "strenuous exercise in situ", "standing", "sitting", "lying", "falling" and "normal transition". First of all, a portable data acquisition terminal is designed in this paper. Based on the basic data acquisition and portability requirements, the terminal is divided into four units: sensor unit, control unit, storage unit and power management unit. The terminal acquisition data is stable and the standby time is long, which is the original data source of human attitude recognition system. Secondly, in order to obtain purer data, the original data will be further preprocessed and data feature extraction will be carried out. Preprocessing includes noise filtering, calibration and removal of gravity acceleration interference. Feature extraction includes time domain feature extraction and frequency domain feature extraction. Specifically, the mean value, standard deviation, median absolute deviation, quartile distance, maximum value, minimum value, square sum mean, AR model coefficient with Berg order 4, correlation of each axis sequence, information entropy characteristics, peak frequency point, Secondary peak frequency point, peak bandwidth, weighted average frequency point, highlight the number of frequency points. After comparison between different samples, the availability of features is evaluated. Finally, a human attitude recognition algorithm based on the above features is constructed. First of all, "walking", "running" and "strenuous exercise in situ" are defined as exercise state, "standing", "leaning" and "lying" are defined as static state, and "falling" and "normal transition state" are defined as transition state. Each state is classified by support vector machine (SVM) and decision tree based on the difference of its large class features. Finally, a more mature human attitude recognition algorithm architecture is formed.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP212.9

【引證文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 任相臻;基于多運動傳感器的動態(tài)手勢識別設(shè)計與實現(xiàn)[D];河北工程大學(xué);2018年

，

本文編號：2477117