利用分水岭分割的多分辨率遥感图像融合算法

对全色图像和多光谱图像进行融合可以获得更加清晰的图像信息。提出了一种基于分水岭分割和小波变换的多分辨率图像融合算法。利用正交小波变换得到原图像的小波金字塔表示。对近似图像进行分水岭分割，并且用小波逆变换把原始分割结果逐步映射回更高的分辨率层。通过联合区域分析，得到各层的联合区域分割图，并用此图来指导各层小波系数的融合。对融合系数进行小波逆变换，得到融合的图像。实验结果表明，该法对遥感图像的融合十分有效，能很好地兼顾融合图像的光谱质量和空间清晰度。

Algorithm on Multiresolution Remote Image Fusion with Watershed Segmentation

Confusing panchromatic image and multispectral image can obtained clearer image the maltispectral image alone. A multiresolution image fusion algorithm based on watershed segmentation and wavelet transform is proposed. Firstly, we obtain the wavelet pyramid using the orthogonal wavelet transform. Then, watershed segmentation of the approximation image is computed, and the inverse wavelet transform is used to project this original segmentation up to the higher resolutions. After joint region analyzed, the joint region segmentation map is obtained, which is further used to guide the fusion of the wavelet coefficients. Finally, the inverse transform of the fused coefficients is implemented in order to obtain the final fusion image. The experimental results indicate that the algorithm is effective for the remote sensing image fusion, which can give consideration well to the spectral quality and spatial definition.