Adaptive Algorithm for Automated Polygonal Approximation of High Spatial Resolution Remote Sensing Imagery Segmentation Contours

The contours of polygons generated by the image segmentation technique show jagged outlines and a large number of redundant points. Therefore, the original segmentation contours hardly conform to geographic information system (GIS) data-producing standards without generalization. With the complexity of high spatial resolution remote sensing imagery data, with variable sizes of geographic features and their different distributive patterns, it is hard to build a global contour optimization parameter model to guide parameter settings in large 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 of GIS data production, we present an adaptively improved algorithm based on the Douglas-Peucker (DP) algorithm, named AIDP, that integrates the criteria of vertical and radial distance restriction, and design a corresponding parameter-adaptive acquisition method. The proposed AIDP method is evaluated by comparing it with the most widely used DP algorithm implemented in the ArcGIS through visual inspection, quantitative measurements, and applications to water body contours. The experimental results show that AIDP can not only acquire generalization parameters automatically but also greatly speed up the data processing workflow with acceptable results.