结合LiDAR与遥感影像的水域边界提取方法

Water Boundary Extraction Method Based on LiDAR and Remote Sensing Image

针对高分辨率遥感影像提取水域边界不准确、不完整的问题,提出了高分辨率遥感影像结合机载LiDAR点云数据提取水域边界的新方法。首先将配准后的LiDAR点云数据网格化,生成DSM影像,然后运用数学形态学分析获取水体的初始边界信息,最后基于活动轮廓模型的图割算法对构建的边界缓冲区进行优化分割,从而获取精确的水域边界。实验结果表明,该方法能够去除部分水域干扰噪声且能够得到比较精确的边界信息,具有较好的视觉效果和较高的工程应用价值。

Since the water boundary extraction by the high resolution remote sensing image segmentation method has the disadvantages of inaccuracy and incomplete, this paper presented a new approach for extracting the water boundary in combination of airborne Li DAR point cloud data and high resolution remote sensing image data. The LiDAR point cloud data after registration were translated into DSM images at first. And then, the mathematical morphology analysis was used to obtain the initial water boundary information. Lastly, the graph cut algorithm based on active contour model was used to segment the boundary of the buffer zones, in order to obtain the exact water boundary. The experimental result shows that the method can well extract waters boundary.