RGBD Salient Object Detection by Structured Low-Rank Matrix Recovery and Laplacian Constraint

Abstract

A structured low-rank matrix recovery model for RGBD salient object detection is proposed. Firstly, the problem is described by a low-rank matrix recovery, and the hierarchical structure of RGB image is added to the sparsity term. Secondly, the depth information is fused into the model by a Laplacian regularization term to ensure that the image regions which share similar depth value will be allocated to similar saliency value. Thirdly, a variation of alternating direction method is proposed to solve the proposed model. Finally, both quantitative and qualitative experimental results on NLPR1000 and NJU400 show the advantage of the proposed RGBD salient object detection model.

Keywords

RGBD saliency detection / Low-rank matrix recovery / Laplacian regularization / Structured sparsity

References

[1] Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows. IEEE Trans Pattern Anal Mach Intell, 2012, 34: 2189-2202.

[2] Schmid C, Jurie F, Sharma G (2012) Discriminative spatial saliency for image classification. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 3506–3513

[3] Hiremath PS, Pujari J. Content based image retrieval using color boosted salient points and shape features of an image[J]. Int J Image Process, 2008, 2: 10-17.

[4] Liu TL, Chang KY, Lai SH (2011) From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 2129–2136

[5] Chen T, Cheng MM, Tan P, et al. Sketch2Photo: internet image montage. ACM Trans Graph, 2009, 28: 124.

[6] Wang P, Wang JD, Zeng G et al (2012) Salient object detection for searched web images via global saliency. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 3194–3201

[7] Goferman S, Zelnik-Manor L, Tal A (2010) Context-aware saliency detection. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 2376–2383

[8] Ran M, Zelnik-Manor L, Tal A. Saliency for image manipulation. Vis Comput, 2013, 29: 381-392.

[9] Sun J, Ling HB. Scale and object aware image thumbnailing. Int J Comput Vision, 2013, 104: 135-153.

[10] Cheng MM, Mitra NJ, Huang XL, et al. Global contrast based salient region detection. IEEE Trans Pattern Anal Mach Intell, 2015, 37: 569-582.

[11] Wilson JL. Microsoft kinect for Xbox 360. PC Mag, 2010, 25: 145-157.

[12] Ciptadi A, Hermans T, Rehg JM (2013) An in depth view of saliency. In: Proceedings of British machine vision conference, pp 1–11

[13] Desingh K, Krishna KM, Rajan D et al (2013) Depth really matters: improving visual salient region detection with depth. In: Proceedings of British machine vision conference, pp 1–11

[14] Lang CY, Nguyen TV, Katti H et al (2012) Depth matters: influence of depth cues on visual saliency. In: Proceedings of the 12th European conference on computer vision, pp 101–105

[15] Niu YZ, Geng YJ, Li XQ et al (2012) Leveraging stereopsis for saliency analysis. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 454–461

[16] Yan JC, Zhu MY, Liu HX, et al. Visual saliency detection via sparsity pursuit. IEEE Signal Process Lett, 2010, 17: 739-742.

[17] Shen XH, Wu Y (2012) A unified approach to salient object detection via low rank matrix recovery. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 853–860

[18] Lang CY, Liu GC, Yu J, et al. Saliency detection by multitask sparsity pursuit. IEEE Trans Image Process, 2012, 21: 1327-1338.

[19] Liu GC, Lin ZC, Yan SC, et al. Robust recovery of subspace structures by low-rank representation. IEEE Trans Pattern Anal Mach Intell, 2013, 35: 171-184.

[20] Zou W B, Kpalma K, Liu Z et al (2013) Segmentation driven low-rank matrix recovery for saliency detection. In: Proceedings of British machine vision conference, pp 1–13

[21] Peng HW, Li B, Ji RR et al (2013) Salient object detection via structured matrix decomposition. In: Proceedings of AAAI conference on artificial intelligence, pp 796–802

[22] Ju R, Ge L, Geng WJ et al (2014) Depth saliency based on anisotropic center-surround difference. In: Proceedings of IEEE international conference on image processing, pp 1115–1119

[23] Achanta R, Shaji A, Smith K, et al. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell, 2012, 34: 2274-2282.

[24] Liu J, Ye JP (2010) Moreau-Yosida regularization for grouped tree structure learning. In: Proceedings of Advances in Neural Information Processing Systems, pp 1–9

[25] Peng HW, Li B, Ling HB et al (2016) Salient object detection via structured matrix decomposition. In: IEEE transactions on pattern analysis and machine intelligence, pp 1–14

[26] Lin ZC, Liu RS, Su ZX (2011) Linearized alternating direction method with adaptive penalty for low-rank representation. In: Proceedings of advances in neural information processing systems, pp 612–620

[27] Jenatton R, Mairal J, Obozinski G, et al. Proximal methods for hierarchical sparse coding. J Mach Learn Res, 2010, 12: 2297-2334.

[28] Cai D, He XF, Han J, et al. Graph regularized nonnegative matrix factorization for data representation. IEEE Trans Pattern Anal Mach Intell, 2011, 33: 1548-1560.

[29] Simoncelli EP, Freeman WT (1995) The steerable pyramid: a flexible architecture for multi-scale derivative computation. In: Proceedings of IEEE international conference on image processing, pp 444–447

[30] Feichtinger HG, Strohmer T. gabor analysis and algorithms: theory and applications, 1997, Boston: Birkhauser.

[31] Peng HW, Li B, Xiong WH et al (2014) RGBD salient object detection: a benchmark and algorithms. In: Proceedings of European conference on computer vision, pp 92–109

[32] Cheng YP, Fu HZ, Wei XX et al (2014) Depth enhanced saliency detection method. In: Proceedings of international conference on internet multimedia computing and service, pp 23–27

[33] Achanta R, Hemami S, Estrada F et al (2009) Frequency-tuned salient region detection. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 1597–1604