A new detection method of oil rigs in SAR imagery

摘要

It's difficult for simple space-borne SAR to identify oil rigs effectively in single pass SAR image. One method of oil rig detection is using multi-temporal SAR images. Some papers had do some research on it. In this paper, we use interferometry SAR image to detect the oil rigs. We get the correlation coefficient image from the In-SAR data, and using the histogram of correlation coefficient image, A Constant False Alarm Rate (CFAR) algorithm is imported to detect the oil rigs. The Probabilistic Neural Network (PNN) is used to get the threshold of detection. The test result shows that sea coherent target detection in the coherent coefficient image is efficacious.