论文部分内容阅读
提出将Ratio梯度与交叉累积剩余熵相结合应用于SAR影像与光学影像匹配以及不同传感器拍摄的SAR影像匹配。在这种算法中,首先针对SAR影像低信噪比与乘性噪声模型的固有特性,基于均值比率算法提取Ratio梯度,然后采用交叉累积剩余熵作为相似性测度对参考影像和待匹配影像的Ratio梯度图像进行匹配。交叉累积剩余熵利用累积分布函数代替密度函数有效克服了噪声对局部极值的影响,可以取得令人满意的结果。
It is proposed that the combination of Ratio gradient and cross-cumulant residual entropy should be used to match SAR images with optical images and SAR images with different sensors. In this algorithm, first of all, according to the inherent characteristics of low SNR and multiplicative noise model of SAR images, the gradient of the ratio is extracted based on the average ratio algorithm, and then the cross-cumulated residual entropy is used as the similarity measure to measure the ratio of the reference image to the image to be matched Gradient images are matched. Cross cumulative residual entropy using cumulative distribution function instead of the density function effectively overcomes the impact of noise on the local extremum, can achieve satisfactory results.