遥感影像并行分割的无缝拼接算法

A seamless mosaic algorithm for remote sensing image parallel segmentation

针对影像数据分块并行处理造成的接边问题,该文基于构建缓冲区的方法提出了一种新的拼接算法。该算法只在每一个数据分块的右侧和下侧构建缓冲区,消除拼接线的原则是保证分割边界的准确性和拓扑关系的正确性。数据分块完成后采用并行的策略对第一个块进行分割,然后将每一块的分割结果与相邻的块进行拼接,在缓冲区内按一定规则判断各块分割对象是否保留并对拓扑关系进行检查,拼接完各块后并行输出对象矢量化后的结果。通过实验验证,该算法不仅保证了分割边界的准确性,而且能够处理大影像,提高了工作效率。

Aiming at the stitching problem caused by parallel processing of image data, a new method was proposed based on data buffer. The data buffer was established just on the right side and underside of the line. The principle of seamless contiguity is to ensure the accuracy of the boundary and the correctness of topology. Firstly, each block of data was segmented respectively and then the segmentation objects and their label values were obtained. Secondly, one block（called master block）was chosen and stitched on the neighbor block（called slave block）, then a certain rule was applied to determine whether the object was re tained in buffer area and the topology was checked after stitching. Finally, the results of vector quantiza tion were output. Experimental results showed that the novel seamless contiguity algorithm provided an applicable and practical solution for efficient segmentation of large-scale remote sensing image.