论文部分内容阅读
合成孔径雷达(Synthetic Aperture Radar,SAR)图像是遥感目标检测与分割等研究的重要数据源。提出了一种渐进核图割分割方法,该方法通过迭代进行二类聚类分割,自动实现合成孔径雷达SAR图像中多目标的分割。实验结果表明,该方法能够有效地实现复杂场景SAR图像的多目标分割。
Synthetic Aperture Radar (SAR) image is an important data source for the research of remote sensing target detection and segmentation. A progressive kernel segmentation method is proposed. This method performs iterative clustering for the second class and automatically performs multi-target segmentation in synthetic aperture radar (SAR) images. Experimental results show that this method can effectively achieve multi-target segmentation of complex scene SAR images.