An adaptively polygonal generalization algorithm for High Spatial Resolution Remote Sensing Imagery segmentation contours

Abstract

The contours of polygons generated by image segmentation technology show jagged outlines and a large amount of redundant points. Therefore, the original segmentation contours hardly conform to GIS data producing standards without generalisation. For the complexity of High Spatial Resolution Remote Sensing Imagery (HSRRSI) data, the variable size of geographic features and their different distributive pattern, it is hard to build a global contour optimization parameter model to guide parameters setting in large scale regions effectively. Furthermore, it is also difficult to automatically give a unique set of parameters per object simultaneously. In order to meet the actual requirements for GIS data producing, we present an Adaptively Improved algorithm based on Douglas-Peucker, named AIDP, which integrated criterions of vertical and radial distance restriction, and design a corresponding parameter adaptive acquisition method. The proposed method AIDP was evaluated by comparing with the most widely used Douglas-Peucker algorithm implemented in the ArcGIS through visual inspection, quantitative measures and applications in water body contours. The experimental results showed AIDP not only can acquire generalisation parameters automatically, but also greatly speed up the data processing workflow with acceptable results.