SMURFS: Superpixels from Multi-scale Refinement of Super-regions

Imanol Luengo, Mark Basham and Andrew French

Abstract

Recent applications in computer vision have come to rely on superpixel segmentation as a pre-processing step for higher level vision tasks, such as object recognition, scene labelling or image segmentation. Here, we present a new algorithm, Superpixels from MUlti-scale ReFinement of Super-regions (SMURFS), which not only obtains state-of-the-art superpixels, but can also be applied hierarchically to form what we call n-th order super-regions. In essence, starting from a uniformly distributed set of super-regions, the algorithm iteratively alternates graph-based split and merge optimization schemes which yield superpixels that better represent the image. The split step is performed over the pixel grid to separate large super-regions into different smaller superpixels. The merging process, conversely, is performed over the superpixel graph to create 2nd-order super-regions (super-segments). Iterative refinement over two scale of regions allows the algorithm to achieve better over-segmentation results than current state-of-the-art methods, as experimental results show on the public Berkeley Segmentation Dataset (BSD500).

Session

Segmentation

Files

Extended Abstract (PDF, 462K)
Paper (PDF, 10M)

DOI

10.5244/C.30.4
https://dx.doi.org/10.5244/C.30.4

Citation

Bibtex

        @inproceedings{BMVC2016_4,
        	title={SMURFS: Superpixels from Multi-scale Refinement of Super-regions},
        	author={Imanol Luengo, Mark Basham and Andrew French},
        	year={2016},
        	month={September},
        	pages={4.1-4.12},
        	articleno={4},
        	numpages={12},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.4},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.4}
        }