In the era of mass tourism, more and more people are attracted by internet-famous site. With people's demand for travel surged, tourists are getting together in one scenic spot with doubling numbers, which easily leads to high concentration of tourists with uncontrollable security risks. It needs to be highly valued by the tourism department. Monitoring and issuing warnings for crowd density in scenic areas with Highly Aggregated Tourist Crowds (HATCs) is an urgent challenge that needs to be addressed. In this paper, Highly Aggregated Tourist Crowds is taken as the research objective, and a VGGT-Count network model is proposed to forecast the density of HATCs. The experimental outcomes demonstrated a substantial improvement in counting accuracy for the ShanghaiTech B and UCF-QNRF datasets. Furthermore, the model allows for real-time monitoring of tourist attractions, enabling advanced prediction of high concentrations in scenic areas. This timely information can alert relevant authorities to implement preventive measures such as crowd control and flow regulation, thereby minimizing safety hazards.