Award Date

1-1-2008

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Committee Member

Evangelos Yfantis

Number of Pages

114

Abstract

My proposed approach to the automatic detection of traffic accidents in a signalized intersection is presented here. In this method, a digital camera is strategically placed to view the entire intersection. The images are captured, processed and analyzed for the presence of vehicles and pedestrians in the proposed detection zones. Those images are further processed to detect if an accident has occurred; The mathematical model presented is a Poisson distribution that predicts the number of accidents in an intersection per week, which can be used as approximations for modeling the crash process. We believe that the crash process can be modeled by using a two-state method, which implies that the intersection is in one of two states: clear (no accident) or obstructed (accident). We can then incorporate a rule-based AI system, which will help us in identifying that a crash has taken or will possibly take place; We have modeled the intersection as a service facility, which processes vehicles in a relatively small amount of time. A traffic accident is then perceived as an interruption of that service.

Keywords

Car; Computer; Computerized; Crash; Detection; Mathematical; Model; Techniques; Vision

Controlled Subject

Computer science; Artificial intelligence; Automobiles--Design and construction

File Format

pdf

File Size

1884.16 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Permissions

If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.

Identifier

https://doi.org/10.25669/ye7b-dra3


Share

COinS