Motion detection and simulation study on human walking behavior

Loon, Cheong Wai (2012) Motion detection and simulation study on human walking behavior. Masters thesis, Universiti Malaysia Sarawak, (UNIMAS).

PDF (Please get the password by email to repository@unimas.my , or call ext: 3914 / 3942 / 3933) Cheong Wai Loon.pdf Restricted to Registered users only Download (52MB)

Abstract

~uman walking behaviour modelling is an important topic in different area of studies. Architects, interior designer and transport engineers want to design and integrated a good building and facilities with particular emphasis on safety issues for pedestrians especially during evacuation scenario when emergency. The objective of this project is to analyse the human walking behaviour from video data, and develop an algorithm for human walking behaviour and emergency evacuation simulatioy The motion detection system were developed using Video and Image Processing Blockset in MAT LAB to collect the centroid coordinate of the pedestrians from the video to analyse the human walking behaviour. The walking speed and acceleration of the pedestrian are calculated and implemented into the simulation. The buildings in the simulation are designed in 3D World Studio. The simulation is developed using DarkBasic Professional with the additional extension of Dark AI. There are two categories of human in the simulation which are adult and elderly with different walking speed. Two types of environments are developed in the simulation to study the human walking behaviour which are empty space and building simulation. The analysis ofthe simulation is the time travel for each entity to reach destination and total evacuation time in building simulation. The bottleneck in the building design can be identified from the observation ofthe building simulation.

Actions (For repository members only: login required)

View Item