article-journal

In this article, we introduce a new segmentation method based on a superpixel approach. This method creates multitemporal superpixels, which are meaningful regions in space and time. Experimental results showed that the method performed well, achieving a good boundary agreement and obtaining high scores on the three metrics used for evaluation.

In this work, we extended our previous work, that aims to produce divisions among tiles to ensure more boundaries using non-crisp borders using graph-theory. By applying this non-crisp line cut, we avoid the post-processing of neighboring regions, and therefore speed up the segmentation.