Identifying Curviness of Overpass Mountain Roads from Remote Sensing Data

Curvy roads are important subjects for many applications, because of their spatial geometry. Digital curve identification is easier from continuous objects than from discrete objects, such as roads extracted from remote sensing data. Use of high spatial resolution images can lead to an increase in the accuracy of the detection , and it also gives the possibility to detect curvy segments from the road boundary. I determined the road as a curve in 2-D space, using road boundary detection for shape estimation. Alpha shapes were used for boundary identification because of their flexibility to produce different object boundaries. The obtained boundary is a polygon that was used for identification of curvy road segments. Two simple approaches were used for identifying curviness: Choosing a small window for retrieving information, one can either measure curviness parameters (single angle and deviation of a point from a straight line) in all the points in the window (approach (I)) or measure just one value in the midpoint, between the start, the middle and the end point of the window to decrease the noise (approach (II)). Both methods use a fixed size of moving window to decrease the noise, while in approach (I) accumulated angle was used for additional noise reduction. Because of the use of alpha shapes, the method is capable of identifying curves in data of different quality and spatial resolution, although a decrease in quality will lead to an increase in the radius of alpha shape circles, and therefore a decrease in the chance of detecting sharp and narrow curvy segments. Because the method can use data of different quality, it can be used for different applications.