Website development of crowdedSG

• Main Author: Teng, Harold Ze Chie
• Other Authors: Dusit Niyato
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: https://hdl.handle.net/10356/148136
• Institution: Nanyang Technological University

The world is going through one of the worse pandemics that has ever existed with many countries experiencing high death rate and high number of infections due to the Covid-19 virus. Strict safe distancing measures and limiting crowds in public area have been the cornerstone of mitigating the spread of the Covid-19 virus in Singapore. An important aspect of ensuring social distancing is to keep track of the crowdedness of indoor and outdoor points of interest. This project aims to provide a website application to users to produce crowd counts of areas around Nanyang Technological University (NTU) whereby crowdsourced images and Unmanned Aerial Vehicles (UAV) are used for data collection. Based on the data collected, state of the art deep learning algorithms that is being implemented in the AI engine performs analysis to produce the crowd counts. This will allow users to avoid going to crowded areas around NTU so as to minimize the spread of Covid-19 in Singapore as well as to allow users to plan and make better decisions. Huge amount of efforts and thoughts are used to deal with the challenges and difficulties to provide users with better information and better user experience. This report serves to document the breakdown of the problem and detailed explanation of the platform’s technical implementation.