Please use this identifier to cite or link to this item:
Title: Automated human gait recognition based on micro-doppler signature
Authors: Zhao, Jing
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2017
Abstract: As a new emerging biometric technology, gait recognition, has become one of the most attractive method in the research of security and surveillance. Gait information can be get without human’s attention and cooperation. In this report, a well-organized human gait database with 98 human samples is developed and experiment participants are recognized based on micro-Doppler signature. After collecting human gait data with EM radar, the raw data is processed with Short-Time Fourier Transform. Then normalization and feature extraction methods are applied in the project later. In the recognition phase, Principle Component Analysis (PCA) and Support Vector Machines (SVM) algorithms are applied. The data collection, data processing, data normalization and data recognition are the significant parts in the project. In the end, with the suitable dimensions, the highest human gait recognition rate could be 84.47%. Some recommendations are made for the further human gait recognition projects at the end of the report.
Schools: School of Electrical and Electronic Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.13 MBAdobe PDFView/Open

Page view(s)

Updated on Jul 20, 2024


Updated on Jul 20, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.