Object-Oriented Port Detection Based on Mean Shift Segmentation

Abstract

In this paper, we propose a new method for port detection using remote sensing image. This technique is a combination of image segmentation and object-oriented detection. We use mean shift method to initially segment the remote sensing image. Based on the initial segmentation map we build the spatial adjacency relation of the regions. Significant department has been observed in object-oriented detection. Generally, ports have inherent characteristic of half close region of seawater. Convex polygon created by centers of land region along the coastline. The land region is controlled within a certain range. Port detection is implemented according to water areas within the convex polygon. The advantages of this method are the robustness and its affine invariance with respect to translation, scaling, rotation and skewing. The effectiveness of this algorithm is demonstrated using two remote sensing images.

On the Splitting Algorithm Based on Multi-target Model for Image Segmentation

“…The algorithm based on image segmentation which cleverly combines the regional color and edge information has recently become a hot research. The graph cut algorithm applying to the image is completed in 1989 by Greig et al [4][5][6], and subsequent studies have used a binary image, but its importance has not been in a very long time until the beginning of this century, Boykov et al [7][8][9], defined the definition of graph cut algorithm applying to image map and determined weights, and proposed a more efficient algorithm for solving the maximum flow based on the maximum flow algorithm of augmenting path algorithm. Their pioneering work led to the hot of image segmentation once again, and the algorithm based on image segmentation is endless.…”