Literature Review of People Counting

Abstract

People counting systems can provide statistical trend information used for human behavior analysis. Intuitively people counting system works based on sequence detection, tracking, and counting. However, with active research activities in Artificial Intelligence in Computer Vision, there are many alternatives available for implementing a people counting system. A systematic literature review is used to obtain the latest research information that accurately following the requirements of the system being designed as well as the gap areas that arise in implementation. The gap areas found are in the design of an implementation that suits your needs and increases the accuracy of the counters who enter or leave the frame. Several strategies can be done to achieve this goal by conducting head detection and training with a pretrained model in the object detection and tracking framework. This strategy is expected to increase accuracy through stabilizing object detection and tracking.