건물 내 재실자 감지 및 시각화를 위한 딥러닝 모델

Deep Learning-Based Occupancy Detection and Visualization for Architecture and Urban Data: Towards Augmented Reality and GIS Integration for Improved Safety and Emergency Response Modeling

This study explores the potential of utilizing video-based data analysis and machine learning techniques to estimate the number of occupants within a building. The research methodology involves developing a sophisticated counting system capable of detecting and tracking individuals' entry and exit patterns. The proposed method demonstrates promising results in various scenarios; however, it also identifies the need for improvements in camera performance and external environmental conditions, such as lighting. The study emphasizes the significance of incorporating machine learning in architectural and urban planning applications, offering valuable insights for the field. In conclusion, the research calls for further investigation to address the limitations and enhance the system's accuracy, ultimately contributing to the development of a more robust and reliable solution for building occupancy estimation.