Highlight Target Extraction Method based on X-band Shipborne Radar Image

Shipborne radar is an indispensable target detection instrument during navigation. Based on the shipborne radar image collected by the Yukun teaching-training ship of Dalian Maritime University, a highlight targets extraction method is proposed here. First, the original shipborne radar image is transformed from polar coordinate system into Cartesian coordinate system. Second, the improved Sobel operator is used to convolute the shipborne radar image in Cartesian coordinate system. Third, Otsu threshold is used to segment the convoluted image and extract the co-frequency interference noises. Fourth, the distance weighted linear filter is used to suppress the co-frequency interference noises. Fifth, the gray correction matrix is used to adjust the overall gray level of the image. Then, the threshold method is used to get the rough highlight targets segmentation. After that, the speckle noises are suppressed by the pixel number threshold. Finally, the result image is transformed back to the polar coordinate system. Experimental results show that our method can effectively segment the highlighted targets in the original shipborne radar image.