SMURFS: Superpixels from multi-scale refinement of super-regions

Luengo, Imanol; Basham, Mark; French, Andrew P.

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).

Citation

Luengo, I., Basham, M., & French, A. P. (2016, September). SMURFS: Superpixels from multi-scale refinement of super-regions. Presented at British Machine Vision Conference (BMVC 2016), York, UK

• Presentation Conference Type: Edited Proceedings
• Conference Name: British Machine Vision Conference (BMVC 2016)
• Start Date: Sep 19, 2016
• End Date: Sep 22, 2016
• Acceptance Date: Jul 14, 2016
• Publication Date: Sep 20, 2016
• Deposit Date: Sep 21, 2016
• Publicly Available Date: Sep 21, 2016
• Peer Reviewed: Peer Reviewed
• Book Title: Proceedings of the British Machine Vision Conference 2016
• ISBN: 1-901725-59-6
• DOI: https://doi.org/10.5244/C.30.4
• Keywords: Segmentation, Super pixels
• Public URL: https://nottingham-repository.worktribe.com/output/816801
• Publisher URL: http://www.bmva.org/bmvc/2016/papers/paper004/index.html
• Related Public URLs: http://www.bmva.org/bmvc/2016/toc.html
• Contract Date: Sep 21, 2016