摘要
星载SAR具有利用稳定重访周期来获取高分辨图像的优势,针对其获得的长时间时序图像,利用变化检测技术可以对固定区域中的变化信息进行提取。对于环境监测、灾害损失评估、生产能力评估有着重要意义。现有方法多针对较大尺寸的区域,面向目标级的变化检测方法较少。因此提出了一种基于Log-Ratio算子的星载SAR时序图像序列变化检测方法,以实现获取目标级尺寸的时序变化信息。该方法首先运用Log-Ratio算子将图像转换为对数图像,然后以图像序列中的一景为参考图像,将当前图像与参考图像作差获得变化图像,最后在变化图像上运用CFAR算法完成变化检测。所提算法利用Sentinel-1 SAR图像数据集进行了方法验正。
Spaceborne SAR has the advantage of stable revisit period to obtain high-resolution images.For the long-time time-series images,the change information in the fixed area can be extracted by using the change detection technology.It is of great significance for environmental monitoring,disaster loss assessment and production capacity assessment.Most of the existing methods are aimed at large areas,and there are few target-level change detection methods.Therefore,this paper proposes a Log-Ratio operator based change detection method using spaceborne SAR time-series images to obtain the target-level change information.In this method,one of the time-series images in the sequence is taken as the reference image,and the change image is obtained by taking logarithm of the ratio of the input and reference image.Then,the CFAR algorithm is used to complete the detection on the change image.The proposed method is verified by the Sentinel-1 dataset.
出处
《工业控制计算机》
2023年第11期98-101,共4页
Industrial Control Computer
基金
北京市教育委员会科学研究计划项目资助(KM202210009004)
国家自然科学基金重点项目(62131001)。
