Detection of vehicles with monolithic classifier vis-à-vis a boosted cascaded classifier

Fernando, Shehan, Udawatta, Lanka and Pathirana, Pubudu 2009, Detection of vehicles with monolithic classifier vis-à-vis a boosted cascaded classifier, in ICIIS 2009: Conference Proceedings of the Fourth International Conference on Industrial and Information Systems 2009, IEEE, New York, N.Y., pp. 586-591.

Attached Files
Name Description MIMEType Size Downloads

Title Detection of vehicles with monolithic classifier vis-à-vis a boosted cascaded classifier
Author(s) Fernando, Shehan
Udawatta, Lanka
Pathirana, Pubudu
Conference name Industrial and Information Systems Conference (4th : 2009 : Peradeniya, Sri Lanka)
Conference location Peradeniya, Sri Lanka
Conference dates 28-31 December 2009
Title of proceedings ICIIS 2009: Conference Proceedings of the Fourth International Conference on Industrial and Information Systems 2009
Editor(s) [Unknown]
Publication date 2009
Conference series Industrial and Information Systems Conference
Start page 586
End page 591
Publisher IEEE
Place of publication New York, N.Y.
Keyword(s) visual object detection
neural network
haar basis functions
Principle Component Analysis (PCA)
adaboost algorithm
Summary This paper describes the comparison of accuracy and performance of two machine learning approaches for visual object detection and tracking vehicles, from an on-road image sequence. The first is a neural network based approach. Where an algorithm of multi resolution technique based on Haar basis functions was used to obtain an image with different scales. Thereafter a classification was carried out with the multilayer feed forward neural network. Principle Component Analysis (PCA) technique was used as a dimension reduction technique to make the classification process much more efficient. The second approach is based on boosting which also yields very good detection rates. In general, boosting is one of the most important developments in classification methodology. It works by sequentially applying a classification algorithm to reweighed versions of the training data, followed by taking a weighted majority vote of the sequence of classifiers thus produced. For this work, a strong classifier was trained by the adaboost algorithm. The results of comparing the two methodologies visà-vis shows the effectiveness of the methods that have been used.
ISBN 9781424448371
Language eng
Field of Research 080104 Computer Vision
Socio Economic Objective 810103 Command, Control and Communications
HERDC Research category E1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30028356

Document type: Conference Paper
Collection: School of Engineering
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 339 Abstract Views, 7 File Downloads  -  Detailed Statistics
Created: Fri, 16 Apr 2010, 13:31:51 EST by Sandra Dunoon

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.