Paper—Development of Automated People Counting System using Object Detection and Tracking Development of Automated People Counting System using Object Detection and Tracking https://doi.org/10.3991/ijoe.v19i06.38515 Chee Jia Hong, Muhammad Hazli Mazlan (*) Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Johor, Malaysia mhazli@uthm.edu.my Abstract—The emergence of automation in the current economic trend promotes the usage of computer vision systems in various applications. Counting people in a specified area or on the street can bring many benefits in terms of security and marketing. The people counting system is one of the applications that utilize the computer vision system to count people with higher reliability and accuracy. Thus, this project is to develop an offline automated people counting system based on captured video file input using MATLAB software and a notification system to update and send notifications about the number of occu- pants in a target area using ThingSpeak. For project development, simulation and development of coding for object detection that involves deep learning approach, object tracking and counting, and development of notification system have been done. Three videos were taken to be used for three trials to evaluate the function- ality and performance of the developed system. Based on the results and analysis, the system can perform people detection, people tracking and people counting on the recorded input videos with high accuracy of 94.45%, visualize the data on the ThingSpeak platform and send notifications through Twitter. Keywords—people counting, MATLAB, ThingSpeak, deep learning, object detection, object tracking, Mask R-CNN 1 Introduction Nowadays, computer vision is introduced to duplicate human vision abilities to understand and process digital images and video [1]. Image and video processing algorithms have recently become more mature with lots of new technologies and their usage has been growing rapidly. This causes the emergence of the necessity for the development of tools to analyze digital imagery content [2]. People counting is also one of the common applications of computer vision systems [3]. A people counter is an electronic device that counts and monitors people entering a building or estimates the total number of people within a specific area [4]. The system is widely applied at the entrance of a building to record the total number of visitors. Besides, people counting systems are widely used and beneficial for security, tracking, and marketing research. The crowd population density can also be known using the system [5]. 18 http://www.i-joe.org