Human counting using low-end thermal imager

• Main Author: Seet, Jerrold
• Other Authors: Li Mo
• Format: Final Year Project
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::Computer science and engineering::Computer systems organization::Computer-communication networks
• Online Access: http://hdl.handle.net/10356/77256
• Institution: Nanyang Technological University

Human counting has been used in the market to help the company access the human traffic. It also has been to find out the effectiveness of the marketing campaign. It also can be used in the shopping mall shop to find out how well the shop is doing. The purpose of this project is to use the low cost and low power IoT device to create a human counting system and to be implemented as a prototype. Using this prototype, we will find out the accuracy of the counting system. This prototype uses a raspberry pi as a mini computer a thermal camera as the input device for the counting system. This system also can be used to find out the total number of people in the room as well. The data will be transmitted through a low power wireless technology call LoRa. The number accuracy to find out the people is around 60-70 percent, depending on the number of people entering the room as well as the temperature of the environment. When the room is at room temperature, the accuracy is lesser when compared to the aircon room. The thermal camera is able to do the number counting on a certain level of accuracy and it is suitable to find out the number of people in a room provided that the room is small. The normal camera is not used in this project as I am trying to protect the privacy of the people while tracking them.