Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/61155
Title: Vehicle type classification using low-cost web cameras
Authors: Thu, Kaung Myat
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Issue Date: 2014
Abstract: Classification of vehicles becomes an important task for the enforcement of traffic laws for taxing or pollution monitoring. Vision based approach is one of the most popular techniques used in traffic flow surveillance. The objective of this project is design and develop vision based vehicle type classification system for low-cost web camera. The system was developed in C++ language using OpenCV library functions for image processing. The system is robust against shadows and gradual illumination changes in the scene. The system is capable of classifying vehicle into three general categories: two wheels, light vehicle and heavy vehicle. The system is also capable of counting the vehicle according their types and the lane number they are in. The performance of the system was tested and verify using image sequences recorded in high density traffic scene and low density traffic at four different interval of a day. The outcomes indicated that the system has the peak detection, classification and counting accuracy of 80% during day operations. However, the results indicated that the accuracy dropped to 50% during night operations. Overall results indicated that the system can perform decent quality traffic analysis during day operations.
URI: http://hdl.handle.net/10356/61155
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Final Report by Kaung Myat Thu.pdf
  Restricted Access
Vehicle Type Classification using Low-Cost Web Cameras1.74 MBAdobe PDFView/Open

Page view(s) 50

182
checked on Sep 30, 2020

Download(s) 50

12
checked on Sep 30, 2020

Google ScholarTM

Check

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