利用Ratio梯度和交叉累积剩余熵进行多源遥感影像匹配

基金项目: 国家自然科学基金资助项目(40671159,40523005)

详细信息

Multi-source Remote-sensing Image Matching Based on Ratio-Gradient and Cross-Cumulative Residual Entropy

¹ State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,129 Luoyu Road,Wuhan 430079,China

Funds: 国家自然科学基金资助项目(40671159,40523005)

摘要: 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。
- 均值比率 /
- 梯度图像 /
- 互信息 /
- 交叉累积剩余熵 /
- 多源遥感影像匹配
Abstract: A novel algorithm of matching synthetic aperture radar(SAR) image to optical image and SAR got by different sensor based on ratio-gradient and cross-cumulative residual entropy is proposed.As for this algorithm,ratio-gradient is proposed to contrapose low SNR and multiplicative noise of SAR image.In addition,Ratio-Gradient is applicable for optical image.Then cross-cumulative residual entropy is used as a similarity measure based on gradient image.Cross-cumulative residual entropy substitutes living-function for density-function to overcome noise.
- ratio of averages /
- radient image /
- mutual information /
- cross-cumulative residual entropy /
- multi-source image matching