基于分布度量和显著性信息的遥感图像拼接

Remote Sensing Image Mosaic Based on Distribution Measure and Saliency Information

为了获取无缝的宽视场高分辨率遥感图像,提出基于分布度量和显著性信息的遥感图像拼接算法,主要针对图像拼接过程中的外点剔除、最佳缝合线检测和平滑过渡融合三个方面进行改进。首先,以内点在图像重叠区域的均匀分布程度为准则选取最优内点,以增强图像间的对齐程度;其次,利用图像直线信息和引导滤波确定图像显著性信息,避免缝合线穿过明显地物;最后,通过引导滤波对图像进行双尺度融合,利用空间一致性实现缝合线两侧图像间的平滑过渡。仿真结果表明:在外点剔除阶段,所提算法的互信息相较于RANSAC算法提高了1.93%,稳定性提高了46.55%;在缝合线检测和过渡融合阶段,所提算法的结构相似度(SSIM)相较于QESE算法提高了3.21%,峰值信噪比(PSNR)提高了2.55%。最终获得了亮度均匀、无重影的高质量宽视场高分辨率遥感图像。

To obtain a seamless remote sensing image with wide field-of-view and high resolution, this study proposes a remote sensing image mosaic algorithm based on distribution measure and saliency information. Outlier removal, optimal seamline detection, and smooth transition during image mosaic are the main areas of improvement. To improve image alignment, the optimal inliers are first chosen based on the distribution quality of inliers in the overlapping area. Secondly, the saliency information of images is determined by line segments and guided filter to avoid the seamline crossing obvious features. Lastly, a two-scale image fusion is performed using a guided filter, and spatial consistency is used to achieve a smooth transition between the images on both sides of the seamline. The simulation results demonstrate that, when compared with the RANSAC algorithm, the proposed algorithm enhances the mutual information by 1.93% and the stability by 46.55% in outlier removal. In comparison to the QESE algorithm, the proposed algorithm improves structural similarity(SSIM) by 3.21% and peak signal-tonoise ratio(PSNR) by 2.55% in optimal seamline detection and smooth transition. A high-quality, wide field-ofview, and high-resolution remote sensing image is produced with uniform brightness and no ghosting.