BP-net: deep learning-based superpixel segmentation for RGB-D image

In this paper, we propose a deep learning-based su-perpixel segmentation algorithm for RGB-D image. The proposed deep neural network called BP-net is composed of boundary detection network (B-net) that exploits multiscale information from depth image to extract the geometry edge of objects, and pixel labeling network (P-net) that extracts pixel features and generates superpixels. A boundary pass filter is proposed to combine the edge information and pixel features and ensures superpixels adhere better to geometry edges. To generate regular superpixels, we design a loss function which takes the shape regularity error and superpixel accuracy into account. In addition, for providing reasonable initial seeds, a new seeds initialization strategy is proposed, in which the density of seeds is investigated from a 2-manifolds space to reduce the number of superpixels that cover multiple objects in the region of rich texture. Experimental results demonstrate that our algorithm outperforms the existing state-of-the-art algorithms in terms of accuracy and shape regularity on the RGB-D dataset.