Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/53077
Title: Vision-based system for qualitative road traffic data analysis
Authors: Zhang, Chenyu
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2013
Abstract: According to the UK National Transport Ministry, road traffic was projected to increase by 44% more, compared with the Figure in 2011, by the year of 2035. As the pace of the modrn life escalated the demand of transport needed to be dealt with. Currently, surveillance cameras were the most common devices deployed to monitor road traffic. Statistics would be gathered for post investigation. However, the process involves ineffective manual counting. With the help of vision-based traffic supervision tool more precise road traffic information can be provided in time for speculation.The project was aimed to improve the quality of the traffic supervision software. Therefore various enhancing techniques were compared and contrasted. MATLAB was used to build the GUI and run the programs to achieve functions designated to traffic analysis. Results obtained were analysed in parallel with one another to determine the superiority. Real time image acquisition, dynamic background extraction, shadow and highlight detection by calculating the distortion, image reconstruction and fuzzy logic classification were applied to achieve a better result. The software was enabled to apply to more practical situations where various weather conditions occur, traffic be congested or other traffic abnormalities.
URI: http://hdl.handle.net/10356/53077
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 
EA3104.pdf
  Restricted Access
Final Report1.55 MBAdobe PDFView/Open

Page view(s) 50

140
checked on Oct 29, 2020

Download(s) 50

13
checked on Oct 29, 2020

Google ScholarTM

Check

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