Open Access Open Access  Restricted Access Subscription or Fee Access

Video Monitoring of Tourist Density in Cultural Heritage Sites



Cultural heritage sites are of great significance to human and they are the important treasures of mankind. They convey the culture of each nation and country. Therefore, protecting their safety and carrying on cultural inheritance has farreaching significance. At the present time, as the universality of surveillance systems continues to increase, almost all cultural heritage sites are equipped with surveillance cameras. These surveillance cameras allow the administrator to view a display screen at a specific place for remote monitoring. However, currently, in most of cultural heritage sites, the videos captured by these surveillance cameras are monitored artificially and considering the fatigue of people, this method is less efficient. In recent years, with the powerful support of big data and GPU, artificial intelligence technology with deep learning as the core has developed rapidly and has been widely used in many fields. Therefore, this paper proposes to apply the computer vision based on convolutional neural network (CNN) to monitor the number of tourists in an exhibition hall of the Forbidden City by analyzing the surveillance video and then calculate the tourist density in this exhibition hall. After applying the method to every open area in the Forbidden City, by comparing the distribution of the tourist density in each open area, the tourists can better plan their visiting routes and the managers can schedule personnel more easily. The deep learning algorithm used in this paper is You Only Look Once (YOLO) v3. One of the advantages of YOLO v3 is that it has a fast computing speed and the requirements for running platforms is relatively low, which can even be run on mobile terminals. And its accuracy is sufficient for human recognition


Full Text: