Adaptive Split-and-Merge Segmentation Based on Piecewise Least-Square Approximation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
Ship detection in inhomogeneous regions using synthetic aperture radar (SAR) imagery is usually confronted with the severe heterogeneities of the oceans; this paper proposes a new detection scheme to overcome this problem. At first, an object-oriented segmentation algorithm is employed to partition the whole SAR image into several uniform regions. Then, for each partitioned region within water areas, the Kolmogorov-Smirnov test is applied to select the optimal background distribution model, and ship detection is carried out using the adaptive constant false alarm rate (CFAR) detector based on the selected probability density function. Finally, the detection results of each region are merged. An experiment based on an ENVISAT ASAR image of the Yangtze estuary show that the proposed strategy can effectively deal with heterogeneous scenarios in inhomogenous regions and greatly improves the detection results.