超像素能够捕获图像冗余信息, 降低后续处理任务复杂度, 已受到了国内外研究者的日益关注。首先分析了超像素分割领域的发展现状, 以基于图论的方法和基于梯度下降的方法为视角, 对现有超像素分割方法进行归纳和论述。在此基础上, 就目前常用的超像素分割算法进行了实验对比, 分析各自的优势和不足。最后, 对超像素分割技术的最新应用进行了介绍和展望。
Superpixel can capture redundancy of the image and reduce the complexity of subsequent processing tasks. These advantages make it receive more and more attentions from researchers at home and abroad. This paper first analyzed the deve-lopment of the superpixel segmentation, and summarized the state-of-the-art superpixel segmentation algorithms in the view of graph-based and gradient-ascent-based methods. Then, it compared several superpixel segmentation algorithms by experiments, and illustrated their strengths and weaknesses respectively. At last, it introduced the latest applications of superpixel segmentation techniques with prospects.