A semi-automatic framework for highway extraction and vehicle detection based on a geometric deformable model

Road extraction and vehicle detection are two of the most important steps of traffic flow analysis from multi-frame aerial photographs. The traditional way of deriving traffic flow trajectories relies on manual vehicle counting from a sequence of aerial photographs. It is tedious and time-consuming work. To improve this process, this research presents a new semi-automatic framework for highway extraction and vehicle detection from aerial photographs. The basis of the new framework is a geometric deformable model. This model refers to the minimization of an objective function that connects the optimization problem with the propagation of regular curves. Utilizing implicit representation of two-dimensional curve, the implementation of this model is capable of dealing with topological changes during curve deformation process and the output is independent of the position of the initial curves. A seed point propagation framework is designed and implemented. This framework incorporates highway extraction, tracking, and linking into one procedure. Manually selected seed points can be automatically propagated throughout a whole highway network. During the process, road center points are also extracted, which introduces a search direction for solving possible blocking problems. This new framework has been successfully applied to highway network extraction and vehicle detection from a large orthophoto mosaic. In this research, vehicles on the extracted highway network were detected with an 83% success rate.