• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.187-188
• /
• 2021

최근 COVID19 상황에서 생활 속 거리두기가 강조되면서 관광지나 다중이용시설 등의 이용객 수와 밀집도를 파악하는 것이 중요해지고 있다. 따라서, CCTV 영상을 활용하여 저렴한 비용으로 다중이용시설의 출입자수에 대한 정보를 실시간으로 모니터링할 수 있는 시스템이 필요하다. 이를 위해 본 논문에서는 딥러닝 실시간 객체인식기술을 활용한 출입자의 수와 동선을 측정하여 출입자에 대한 통계정보를 웹브라우저를 통해 제공하는 시스템을 개발하였다. 실시간 객체인식기술인 YOLOv4와 YOLOv4-tiny 알고리즘을 Nvidia사의 Jetson AGX Xavier 와 데스크톱PC에 적용하여 각 알고리즘의 FPS와 객체 인식률을 비교 분석 하여 알고리즘을 적용하였다.

• Korean Association of Arts Management
• /
• no.59
• /
• pp.73-99
• /
• 2021

Free admission policies have been gradually extended for the public to use cultural facilities free of charge, which lowered the barriers to use those facilities and has a great effect on increasing visitor demands. However, the annual number of visitors which is open to the public isn't quite accurate and varies from institution to institution, which means just a head count. Especially people counter overestimates the number of visitors because it counts visitors in duplicate. Therefore, the purpose of this study is to prepare effective way of grasping the number of visitors using cultural infrastructure. First, comparable number of visitors should be measured by defining the notion of visitor clearly, which has been measured vaguely. Secondly, the problem of duplicate count, which is considered the most problematic, should be solved. Thirdly, the various analysis of visitor behavior should be conducted to provide a high-quality service. To work out the problems above, new measurement will be presented here. This study suggests a state-of-the-art wireless signal-based measurement that could eliminate the duplicate data by collecting MAC address -smart device's distinct signal value. And it also could analyze diverse visitor behaviors by understanding a flow of visitor traffic, duration of stay and revisitation. I would like to examine the possibility and effectiveness of this new measurement by testing it.