Regularity Preserved Superpixels and Supervoxels
- 10 February 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 16 (4), 1165-1175
- https://doi.org/10.1109/tmm.2014.2305571
Abstract
Most existing superpixel algorithms ignore the spatial structure and regularity properties, which result in undesirable sizes and location relationships for the subsequent processing. In this paper, we introduce a new method to generate the regularity preserved superpixels. Starting from the lattice seeds, our method relocates them to the pixel with locally maximal edge magnitudes and treats them as the superpixel junctions. Then, the shortest path algorithm is employed to find the local optimal boundary connecting each adjacent junction pair. Thanks to the local constraints, our method obtains homogeneous superpixels with adjacency in lowly textured and uniform regions and simultaneously preserves the boundary adherence in the high contrast contents. Our method preserves the regularity property without significantly sacrificing the segmentation accuracy. Moreover, we extend this regular constraint for generating the supervoxels. Our method obtains the regular supervoxels, which preserves the structural relation on both spatial and temporal spaces of the video. Quantitative and qualitative experimental results on benchmark datasets demonstrate that our simple but effective method outperforms the existing regular superpixel methods.Keywords
This publication has 41 references indexed in Scilit:
- A spatio-temporal pyramid matching for video retrievalComputer Vision and Image Understanding, 2013
- Weakly Supervised Graph Propagation Towards Collective Image ParsingIEEE Transactions on Multimedia, 2011
- Object-Graphs for Context-Aware Visual Category DiscoveryIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- A Tree-Based Context Model for Object RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Minimizing energy functions on 4-connected lattices using eliminationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Robust higher order potentials for enforcing label consistencyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Representing shape with a spatial pyramid kernelPublished by Association for Computing Machinery (ACM) ,2007
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Image Parsing: Unifying Segmentation, Detection, and RecognitionInternational Journal of Computer Vision, 2005
- Iterative decoding of two-dimensional hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003