基于分水岭的超像素分割方法

Superpixel segmentation based on watershed

超像素算法作为一种预处理工具已在计算机视觉中得到了广泛应用,尤其在实时视觉系统中,超像素算法的高效性尤为重要。文中是基于分水岭算法而提出的高效超像素分割算法,即空间约束的分水岭算法(SCoW),SCoW算法是通过一组均匀标集来进行分水岭分割。该算法通过引入边缘预处理来确保均匀性和紧凑性之间的平衡,从而对齐超像素的图像边缘,且无任何复杂计算。文中提出的算法比传统算法所产生的超像素图像质量好且运行效率高。

As a pre-processing tool,superpixel algorithms is popularly used in many computer-vision applications. High efficiency is a desired property of superpixel algorithms,especially in real-time vision systems. In this paper,a high-efficient superpixel algorithm is developed based on the watershed algorithm,called the spatial-constrained watershed（SCoW）. SCoW performs watersheding in a markercontrolled manner,with a set of evenly placed markers. To align superpixel boundaries to image edges,an edge-preserving scheme is embedded into the SCo W,which makes a balance between the homogeneity and the compactness. Without any complex computing,the proposed superpixel algorithm is developed to produce high quality superpixels.