The low-rank decomposition of correlation-enhanced superpixels for video segmentation
- 56 Downloads
Low-rank decomposition (LRD) is an effective scheme to explore the affinity among superpixels in the image and video segmentation. However, the superpixel feature collected based on colour, shape, and texture may be rough, incompatible, and even conflicting if multiple features extracted in various manners are vectored and stacked straight together. It poses poor correlation, inconsistence on intra-category superpixels, and similarities on inter-category superpixels. This paper proposes a correlation-enhanced superpixel for video segmentation in the framework of LRD. Our algorithm mainly consists of two steps, feature analysis to establish the initial affinity among superpixels, followed by construction of a correlation-enhanced superpixel. This work is very helpful to perform LRD effectively and find the affinity accurately and quickly. Experiments conducted on datasets validate the proposed method. Comparisons with the state-of-the-art algorithms show higher speed and more precise in video segmentation.
KeywordsVideo segmentation LRD The enhanced superpixel
This work was supported by National Natural Science Foundation of China (Nos. 61602397, 61841103), The Natural Science Foundation of Hunan Province (2017JJ2251, 2017JJ3315), and Chinese Scholar-ship Council of the Ministry of Education.
Compliance with ethical standards
Conflict of interest
All authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S (2010) Slic superpixels. In Technical report, EPFLGoogle Scholar
- Brox T, Malik J (2010) Object segmentation by long term analysis of point trajectories. In: Proceedings of European conference on computer vision. https://doi.org/10.1007/978-3-642-15555-0_21
- Chen L, Zhu Y, Papandreou G, et al (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. Preprint arXiv:1802.02611
- Cheng B, Liu G, Wang J, et al (2011). Multi-task low-rank affinity pursuit for image segmentation. In Proceedings of IEEE international conference on computer vision, pp 2439–2446Google Scholar
- Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 886–893Google Scholar
- Duta I, Uijlings J, Nguyen T, et al (2016) Histograms of motion gradients for real-time video classification. In: International workshop on content-based multi-media indexing. https://doi.org/10.1109/cbmi.2016.7500260
- Farnoush Z, Borislav A, Jan S (2018). Superpixel-based road segmentation for real-time systems using CNN. In: Proceedings of the 13th international joint conference on computer vision, imaging and computer graphics theory and applications (VISIGRAPP), pp 257–265Google Scholar
- Galasso F, Cipolla R, Schiele B (2012) Video segmentation with superpixels. In: Proceedings of the Asian conference on computer vision, pp 760–774Google Scholar
- Galasso N, Nagaraja J, Cardenas T, Brox B, Schiele A (2013) Unified video segmentation benchmark: annotation, metrics and analysis. In: International conference on computer vision. https://doi.org/10.1109/iccv.2013.438
- Grundmann M, Kwatra V, Han M, et al (2010) Efficient hierarchical graph-based video segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition, pp 2141–2148Google Scholar
- Konstantinos G (2008) The bhattacharyya. Measure, Version 1.0, March 20Google Scholar
- Li C, Lin L, Zuo W, Wang W, Tang J,Yan S (2015) SOLD: sub-optimal low-rank decomposition for efficient video segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition, Boston, MA, USA, pp 5519–5527. https://doi.org/10.1109/cvpr.2015.7299191
- Liu R, Lin Z, Torre F, Su Z (2012) Fixed-rank representation for unsupervised visual learning. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 598–605Google Scholar
- Luc P, Couprie C, Chintala S, et al (2016) Semantic segmentation using adversarial networks. In: NIPS-2016 NIPS workshop on adversarial training, Barcelona, Spain. arXiv:1611.08408
- Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. Med Image Comput Comput-Assist Interv (MICCAI) 9351:234–241Google Scholar
- Das A, Ghosh S, Sarkhel R, et al. (2018) Combining multi-level contexts of superpixel using convolutional neural networks to perform natural scene labeling. arXiv:1803.05200
- Wen Z, Yin W, Zhang Y (2010) Solving a low-rank factorization model for matrix completion by a non-linear successive over-relaxation algorithm. Rice CAAM Tech Report TR10-07Google Scholar
- Xu C, Corso J (2012). Evaluation of super-voxel methods for early video processing. In: Proceedings of IEEE conference on computer vision and pattern recognition. https://doi.org/10.1109/cvpr.2012.6247802
- Zhang T, Ghanem B, Liu S, et al (2013) Low-rank sparse coding for image classification. In Proceedings of IEEE international conference on computer vision, pp 281–288Google Scholar