Road extraction from high-resolution remotely sensed panchromatic image in different research scales

As a main factor of evaluating city development speed, road is one of the fast information updating element during city development. Road information extraction based on high-resolution remotely sensed images has very important significance because road affects city land use-cover change. Based on the synthetically analyzing all kinds of road extraction method from high-resolution remotely sensed images, this paper presents the road extraction method that firstly extracts parcel-units from the experimental image based on different scales, and then analyzes the parcel-units assisted by transcendental knowledge. This method can extract road information exactly by object-oriented method, and can acquire different-scale roads according to the user´s requirement. At last this paper gives the road information extraction result analysis of the experiment sample.