The Design And Application Of An Image-based Road Network Model

Geographical Information Systems for Transportation (GIS-T) is the application of Geographical Information Systems (GIS) in transportation research field. Nowadays, the increasing advances of positioning and communication technologies make it possible to collect high frequency and accuracy GIS-T data (e.g. the locational information of moving objects in a road network) in an efficient and effective fashion. Meanwhile, the locational information can be used to augment data collected with other sensors (e.g. image sensor). One of them is to collect geo-referenced images in a road network and replay them in a virtual-reality fashion to make users feel as if they are driving a car to explore the network in a virtual tour. Under this background, an image-based road network model is defined, and several algorithms are proposed to fulfill its construction, such as equidistantly extracting images, integrating road network with images, creating an image group file structure, and reconstituting images.In order to verify the proposed model, an experiment of partial road network of Chongming district in Shanghai is conducted. On the basis of the trajectory data and images collected with high-accuracy positioning devices and digital video camera, an image-based road network model is then built. With this model as the fundamental part, a prototype is developed to implement a virtual tour in a road network. As regards its configuration, a stationary bicycle, a personal computer, a smartphone embedded with gravity sensor and a wireless mouse are employed for a better human-computer interaction. Different from most existing methods, the proposed approach and algorithms can facilitate building the image-based road network model as well as developing the prototype efficiently and conveniently with the aid of developed positioning technologies.