Detection Of Ship In SAR Image

Ship detection and surveillance is the traditional task of the seacoast country all over the world, which has grate application in military and civilian domain. Our motherland has large ocean which is full of resources. It is of grate significance in developing ship detection in Synthetic Aperture Radar (SAR) image. This article studies on the aspect of ship detection in SAR image.The precondition of ship detection in SAR image is the land segregating, so the coastline detection for sea region determined is presented firstly. The 6 coastline detection algorithms are summarized in this chapter, the differences of which are compared. Finally, the level set algorithm and the Mumford-Shah methos are adapted in this article, and the experiment result is given out.The detection in SAR image is to find out the target echo in the environment clutter, so the study of target detection includes the study of environment and the study of target. So the sea-clutter modeling and ship target modeling are introduced, the existing clutter models are summarized. The deducing and parameter estimating of K-distribution are presented in detail. The simulation method of correlated K-distributed clutter is discussed. At last, the model of ship target radar cross section is presented.Based on the work before, the ship target detection is studied. Firstly, the factors which affect the ship target detection are analyzed. Secondly, the ship target detection technologies are summarized. Finally, the ACCA-CFAR (Automatic Censored Cell Averaging-CFAR) detection with local adaptive threshold algorithm is presented in detail, and the experiment result is given out.At last, the research of the thesis is summarized and the interesting areas for future research are pointed out.