基于边缘检测的溢水标记分水岭算法

针对已有标记分水岭算法存在的过分割问题,提出一种基于边缘检测的溢水标记分水岭算法。首先,对遥感影像进行相位一致边缘检测,获取边缘信息。然后,基于获取的边缘信息进行区域增长,检测对象区域的微弱边界,并改善对象边界的位置精度。最后,利用提出的溢水模型生成新标记继续增长,直到得到最终分割结果。在卫星影像和航空影像数据集上的实验结果表明,所提出的算法有效地抑制了过分割现象,能够准确的提取对象区域。

Overflow marker-based watershed segmentation algorithm based on edge detection

To remedy the over-segmentation problem of marker-based watershed segmentation , this paper proposes an overflow marker-based watershed segmentation algorithm based on edge detection. Firstly, we use the phase congruency based edge detection method to get the edge information . Then, a regional growth algorithm which based on edge information is used to detect objects with weak boundary and improving the positional accuracy of the objects boundary. Finally, we propose a overflow model for obtaining new markers and growth as above until finish segmentation. The experimental results on satellite images and aerial images datasets show that the proposed algorithm performs well in retaining the weak boundary and reducing the undesired over-segmentation.