Automatic Selection of Optimal Segmentation Scale of High-resolution Remote Sensing Images

With the increasing of spatial resolution of imaging sensors, object-oriented feature information extraction technology is developing rapidly. The advantages of object-based classification over the traditional pixel-based approach are well documented. Image segmentation is a key step to realize the object-oriented classification. The choice of scale parameter is very important and has a great influence on the segmentation effectiveness,but the choice of scale parameter is still decided by the repeated attempts and subjective judgments of operator,which are lacking in stability and reliability. Thus, an objective and unsupervised method is proposed for selecting optimal parameter for image segmentation to ensure best quality results. In this paper, WorldView 2 as data source, a new method based on principal component transform is introduced to choose an optimal parameter for image segmentation. We choose principal component images as the editor of image segmentation and eigenvalues as the weights of heterogeneity f and segmentation global score. Segmentation images, ranging from 20 to200 scale, step by 10, are created in Definiens Professional 8.7. Then, the global intra-segment and inter-segment heterogeneity indexes are taken into account to identify the optimal segmentation scale(i. e. the highest GS value) by using the cubic spline interpolation function method. After comparison with the results of image segmentation based on traditional three bands, image segmentation effect obtained by principal component transform has obvious advantages. As a result, the method in this paper can effectively avoid the subjectivity of the artificial segmentation, one-sidedness and inefficiency, improve the quality of high-resolution image segmentation.The method also makes a good preprocessing work for later image classification and information extraction.