论文标题
Super-BPD：快速图像分割的超边界对像素方向
Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation
论文作者
论文摘要
图像分割是许多应用程序的基本视觉任务，也是关键步骤。在本文中，我们提出了一种基于新型超级边界对像素方向（Super-BPD）和具有SuperBPD的定制分割算法的快速图像分割方法。确切地说，我们将每个像素上的BPD定义为一个二维单位向量，该单元向量从其最近的边界指向像素。在BPD中，来自不同区域的附近像素彼此相反，并且在同一区域中的相邻像素的方向指向对方或彼此（即围绕内侧点）。我们利用此类属性将图像划分为Super-BPD，这是新颖的信息性超级像素，具有可靠的方向相似性，可将其快速分组为分割区域。 BSDS500和PASCAL环境的广泛实验结果证明了所提出的Super-BPD在分割图像中的准确性和效率。实际上，提议的Super-BPD在〜25fps和0.07fps的情况下以MCG的形式达到了可比性或出色的性能。 Super-BPD还表现出对看不见的场景的值得注意的转移性。该代码可在https://github.com/jianqiangwan/super-bpd上公开获取。
Image segmentation is a fundamental vision task and a crucial step for many applications. In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD. Precisely, we define BPD on each pixel as a two-dimensional unit vector pointing from its nearest boundary to the pixel. In the BPD, nearby pixels from different regions have opposite directions departing from each other, and adjacent pixels in the same region have directions pointing to the other or each other (i.e., around medial points). We make use of such property to partition an image into super-BPDs, which are novel informative superpixels with robust direction similarity for fast grouping into segmentation regions. Extensive experimental results on BSDS500 and Pascal Context demonstrate the accuracy and efficency of the proposed super-BPD in segmenting images. In practice, the proposed super-BPD achieves comparable or superior performance with MCG while running at ~25fps vs. 0.07fps. Super-BPD also exhibits a noteworthy transferability to unseen scenes. The code is publicly available at https://github.com/JianqiangWan/Super-BPD.
