Date of Publication

4-2012

Document Type

Master's Thesis

Degree Name

Master of Science in Mechanical Engineering

Subject Categories

Mechanical Engineering

College

Gokongwei College of Engineering

Department/Unit

Mechanical Engineering

Thesis Adviser

Alvin Y. Chua

Defense Panel Chair

Laurence A. Gan Lim

Defense Panel Member

Edwin Sybingco
Isidro V. Marfori

Abstract/Summary

Pedestrian detection systems are valuable in a variety of applications including advanced driver assistance systems and advanced robots. This study aims to develop a vision-based pedestrian detection system for moving platforms. It uses Histogram of Oriented Gradients (HOG) as feature descriptor, AdaBoost and Linear Support Vector Machines (SVM) as a classifiers and Optical Flow for discerning the pedestrians direction. The entire system is tested and evaluated in both publicly available databases and personally acquired videos. The pedestrian detection system has been tested and results show that it can detect pedestrians. Experiments showed that the system is up 20% faster than default detector.

Abstract Format

html

Language

English

Format

Electronic

Electronic File Format

MS WORD

Accession Number

CDTG005130

Shelf Location

Archives, The Learning Commons, 12F Henry Sy Sr. Hall

Physical Description

88 leaves : ill. ; 1 computer optical disc

Keywords

Pedestrians

Upload Full Text

wf_yes

Share

COinS