Abstract
This paper proposes a new approach for superpixel segmentation. It is formulated as finding a rooted spanning forest of a graph with respect to some roots and a path-cost function. The underlying graph represents an image, the roots serve as seeds for segmentation, each pixel is connected to one seed via a path, the path-cost function measures both the color similarity and spatial closeness between two pixels via a path, and each tree in the spanning forest represents one superpixel. Originating from the evenly distributed seeds, the superpixels are guided by a path-cost function to grow uniformly and adaptively, the pixel-by-pixel growing continues until they cover the whole image. The number of superpixels is controlled by the number of seeds. The connectivity is maintained by region growing. Good performances are assured by connecting each pixel to the similar seed, which are dominated by the path-cost function. It is evaluated by both the superpixel benchmark and supervoxel benchmark. Its performance is ranked as the second among top performing state-of-the-art methods. Moreover, it is much faster than the other superpixel and supervoxel methods.
Highlights
Superpixels have become effective alternative to pixels in the past decade
This section analyzes the effects of path-cost functions and scaling factor, and compares rooted spanning superpixel (RSS) algorithm with five state-of-the-art superpixel methods using the superpixel benchmark1 (Stutz et al 2018), which employs the Berkeley Segmentation Dataset 500 (BSDS) (Arbelaez et al 2011), Fashionista dataset (Fash) (Yamaguchi et al 2012), NYU Depth Dataset V2 (NYU) (Silberman et al 2012), Stanford Background Dataset (SBD) (Gould et al 2009) and Sun RGB-D dataset (SUN) (Song et al 2015)
This paper proposes a new approach for superpixel segmentation
Summary
Superpixels have become effective alternative to pixels in the past decade. 9. scalability supervoxel segmentation can be achieved in the same way; These characteristics follow principles of perceptual grouping and support general applications. Superpixel segmentation is application orientated in some way, some general characteristics are expected: 1. They are the criteria for developing superpixel segmentation methods. Watersheds generate superpixels of irregular sizes and shapes (Vincent and Soille 1991), which conflict with the compactness and uniformity
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
