Please use this identifier to cite or link to this item:
Title: Computer vision for business intelligence
Authors: Lim, Chadd Zhe Xian
Keywords: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Engineering::Computer science and engineering::Software::Software engineering
Issue Date: 2020
Publisher: Nanyang Technological University
Project: SCSE19-0425
Abstract: There is a growing demand for the use of computer vision technology and the demand for such technology is expected to reach $86 billion by 2025. In the retail industry, the use of computer vision has also become more prevalent. Cameras have been used to assist in areas like detecting the footfall of customers across the floor. This project aims to equip dynamic working environments, such as pop-up events, with computer vision technologies so that people who set up stalls at these events can utilise these technologies to gain customer insights. In most cases, these events are only temporary, and this would limit the kind of hardware that can be used. This hardware has to be portable so that they can be installed and removed easily. This project handles such limitations and provides users with a complete system for collecting and processing data so that they would be able to gain customer insights. This project heavily utilises object detection and object tracking techniques to extract data from video recordings. These data would be further processed to generate trends and statistics which the users can then view from a dashboard.
Schools: School of Computer Science and Engineering 
Organisations: Agency for Science, Technology and Research (A*STAR)
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
15.09 MBAdobe PDFView/Open

Page view(s)

Updated on Sep 25, 2023

Download(s) 50

Updated on Sep 25, 2023

Google ScholarTM


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