Dissertation > Excellent graduate degree dissertation topics show
The Research of Gait Recognition
Author: JiShuangFeng
Tutor: HuangFengGang
School: Harbin Engineering University
Course: Applied Computer Technology
Keywords: Gait Recognition Motion detection Background subtraction Hidden Markov Models Principal Component Analysis
CLC: TP391.41
Type: Master's thesis
Year: 2008
Downloads: 68
Quote: 0
Read: Download Dissertation
Abstract
|
With the continuous development of science and technology , modern society, a higher demand for human self - identification accuracy , safety and practicality , the biometric technology is quietly rising . Gait recognition is the biometric technology emerging sub- field , by people walking posture identification and authentication of personal identity . This article will use the hidden Markov model (HMM, Hidden Markov Model) gait identification and better recognition effect . The paper first describes the current gait recognition research Difficulties and trends , and then generalize the commonly used research methods of gait recognition ; then explain in detail the the theoretical focus HMM of this chapter , including its source , involving the main algorithm to achieve in the main problem ; for three achieve part of the gait recognition system : the image sequence preprocessing, feature extraction and gait recognition , this paper gives corresponding solutions , and the final recognition result . The focus of this study Gait Extraction: outline of the movement of the human body through the pre- image the pretreatment work ( including background modeling , foreground detection and morphological processing ) , after the body contour edge points to its centroid distance and outline stride for gait characteristics ; extracted five key frames in a gait cycle , according to the K-means clustering algorithm to find the Euclidean distance between each frame and keyframe using principal component analysis feature parameters to reduce the dimension ; everyone to establish a continuous HMM, and then identify the sequence of states seeking to be established HMM output probability , take the corresponding output probability category as its class label . The proposed method can be well described in the body of the gait characteristics , the statistical nature of the HMM has good gait recognition soundness , change the speed of movement has strong robustness . The experimental results show that the HMM is an effective method in the field of gait recognition , and has a strong potential for development .
|
Related Dissertations
- Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
- Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
- The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
- Macaca mulatta palm morphological study of pattern ridge count,Q954
- Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
- Intelligent video detection technology based on the traffic lights control,TM923.5
- Research on Cultural Industrial Competitiveness of Chong Qing,F224
- The Research of Prairie Road Light Environment Effects on Physiological Indicators of Drivers,U491.254
- A Video Monitoring System for Anshan Power Supply Room,TP391.41
- Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
- Application of Motion Detection Technology in Intelligent Surveillance System,TP277
- Research on Moving Objects Detection Algorithms in Security Monitoring System,TP391.41
- Research Onamethod for Human Face Recognition Based on MMTD,TP391.41
- Research of Multimedia Enhancement Unit in the Embedded Processor,TP332
- Competitiveness’ Evaluation and Development Strategy of the Tourism Industry in Huanggang City,F592.7
- Research on Rural Information Promoting Urban-rural Integration in Jiangsu Southern Area,F127;F224
- The Design of Information System of Power Equipment Current-carrying Faults Diagnosis,TP311.52
- The Research of E-government System Performance Evaluation Index System in Linyi City Based on the Principal Component Analysis,G206
- Face recognition algorithm based on feature fusion research,TP391.41
- Humanoid identify key technology research and implementation,TP391.41
- Visual underwater target detection and recognition,TP391.41
CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net Mobile
|