Tourism and transportation generally have an inseparable association. However, there are still many limitations in the existing research on it. For example, most scholars only adopt one single model method, which fails to consider geospatial elements. Moreover, some researchers simply use socioeconomic data for analysis and research and ignore the solid spatial characteristics between tourism and transportation, which leads to deviations in the results. To solve these problems, this article proposed a spatiotemporal association model by comprehensively using coupling coordination degree, gravity center model, and spatial coincidence degree. Based on the tourism economic and attraction spatial data, and the transportation and its network spatial data, the association between tourism and transportation can be revealed by the proposed model. This study conducted a quantitative analysis on the tourism and transportation industry in Jiangxi Province, China, from 2005 to 2019, and the results show that: (1) the coupling coordination degree of tourism and transportation increases year by year; (2) the change in gravity center of tourism and transportation is subtle. The mean value of spatial overlap is 80.33 km, while the mean value of inter-annual variation consistency is 0.56; (3) the spatial coincidence degree of tourism and transportation in Jiangxi Province indicates a steady upward trend and reaches 0.78 in 2019; and (4) based on the evolution trend in the coupling coordination degree, gravity center coupling model, and spatial coincidence degree of tourism and transportation, it can be seen that the slopes of their trend functions are similar and consistent—the slopes are 0.0239, 0.0253, and 0.0319, respectively—and the standard deviation of the slopes of the three is only 0.000018.

With the continuous development of remote sensing(RS) technology, the surface information can be collected conveniently and quickly by using the popular unmanned aerial vehicle(UAV). The application of UAV low altitude RS technology in road safety in intelligent area has certain practical significance. It can provide safety warning for most drivers, and provide auxiliary decision-making for the road supervision department. Through the collection, processing, calculation and analysis of the road image, the UAV can find out the road obstacles with potential safety hazards, identify the road pit, calculate the radius and depth of the road pit through the digital mapping system, predict the accident risk according to different speed and provide scientific basis for the road safety monitoring. At the same time, UAV can provide repair scheme for damaged roads, estimate the quantity of materials needed for repair, and achieve the target of resource saving and efficiency improvement. The experimental results show that the UAV can not only provide scientific prediction information for driving safety, but also provide relatively accurate material consumption for road repair.