傅立成臺灣大學:資訊工程學研究所林志鴻Lin, Chih-HungChih-HungLin2010-06-092018-07-052010-06-092018-07-052009U0001-1008200913112900http://ntur.lib.ntu.edu.tw//handle/246246/185386Human gesture is commonly used in daily communication between humans, and there are more and more studies trying to utilize gestures in human computer interaction. Because the advance of wireless and accelerometer technologies, accelerometer which is constrained by the environment compared with other sensing devices is getting more and more interested in these studies. In this thesis, we introduce an accelerometer-based gesture recognition system which is composed of gesture characteristic database and continuous gesture recognition. In the gesture characteristic database, we propose a method to construct a gesture characteristic database which can handle intra-class variations of human hand gestures. In the continuous gesture recognition part, a kernel based matching method and a dynamic time warping based method are proposed to recognize gestures in human hand motions. We here design two different gesture sets in the experiments, and the experiment results show that our system can recognize continuous hand gestures quickly and accurately.口試委員審定書 #謝 i文摘要 iiBSTRACT iiiONTENTS ivIST OF FIGURES viIST OF TABLES viiihapter 1 Introduction 1.1 Motivation 1.2 Problem Description 3.3 System Overview 5.4 Organization 8.5 Related Works 8.5.1 Gesture Model Construction 9.5.2 Gesture Spotting 10.5.3 Gesture Classification 11hapter 2 Preliminary 13.1 Polar Coordinate System 13.2 Multivariate Gaussian Distribution 15.3 Agglomerative Hierarchical Clustering 16.4 Pyramid Matching Kernel 18.5 Dynamic Time Warping 21hapter 3 Gesture Characteristic Database 25.1 Overview 25.2 Feature Extraction 26.2.1 Signal Preprocessing 26.2.2 Acceleration Trajectory in Cartesian Coordinate System 28.2.3 Acceleration Trajectory in Polar Coordinate System 29.3 Gesture Characteristic Modeling 30hapter 4 Continuous Gesture Recognition 35.1 Overview 35.2 Gesture Spotting 36.2.1 Motion Detection 36.2.2 Candidate Searching 38.3 Gesture Classification 43.4 Continuous Gesture Recognition Algorithm 47hapter 5 Experiment 49.1 Environment Description 49.2 Gesture Sample Collection 50.3 Gesture Characteristic Training 51.4 Experiment Result 52.4.1 Performance of isolated gesture Recognition 53.4.2 Performance of continuous gesture Recognition 55hapter 6 Conclusion 57EFERENCE 59564406 bytesapplication/pdfen-US人機互動加速度感測器手勢辨識HCIAccelerometerGesture Recognitionthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/185386/1/ntu-98-R95922072-1.pdf