Hierarchical Superpixel Segmentation by Parallel CRTrees Labeling

This paper proposes a hierarchical superpixel segmentation by representing an image as a hierarchy of 1-nearest neighbor (1-NN) graphs with pixels/superpixels denoting the graph vertices. The 1-NN graphs are built from the pixel/superpixel adjacent matrices to ensure connectivity. To determine the next-level superpixel hierarchy, inspired by FINCH clustering, the weakly connected components (WCCs) of the 1-NN graph are labeled as superpixels. We reveal that the WCCs of a 1-NN graph consist of a forest of cycle-root-trees (CRTrees). The forest-like structure inspires us to propose a two-stage parallel CRTrees labeling which first links the child vertices to the cycle-roots and then labels all the vertices by the cycle-roots. We also propose an inter-inner superpixel distance penalization and a Lab color lightness penalization base on the property that the distance of a CRTree decreases monotonically from the child to root vertices. Experiments show the parallel CRTrees labeling is several times faster than recent advanced sequential and parallel connected components labeling algorithms. The proposed hierarchical superpixel segmentation has comparable performance to the best performer ETPS (state-of-the-arts) on the BSDS500, NYUV2, and Fash datasets. At the same time, it can achieve 200FPS for 480P video streams.

Automated summary

This paper proposes a hierarchical superpixel segmentation method based on the 1-nearest neighbor (1-NN) graph of pixels/superpixels. The method ensures connectivity by building 1-NN graphs from pixel/superpixel adjacent matrices. The weakly connected components (WCCs) of the 1-NN graph are labeled as superpixels to determine the next-level hierarchy. The paper also introduces a two-stage parallel labeling method based on the forest-like structure of the WCCs. Experimental results show that the proposed method has comparable performance and is several times faster than other algorithms.