Abstract
Co-saliency detection aims at discovering common and salient objects in a group of related images, which is useful to variety of visual tasks. We propose a novel co-saliency detection framework via sparse reconstruction and co-salient object discovery. By taking advantage of the common background in-formation, we first reconstruct images with the common background bases and computer sparse reconstruction error. Second, we discover the common salient objects using high-level and low-level features. Then the reconstruction errors are refined using co-salient object information to get the superpixel-level co-saliency. Third, pixel-level saliency is computed by an integration of multi-scale superpixel-level co-saliency maps, with the help of intra-saliency propagation and Gaussian refinement. The quantitative and subjective experimental results on two benchmark datasets show that our method outperforms both the state-of-art saliency detection methods and co-saliency detection methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Patt. Anal. Mach. Intell. 20(11), 1254–1259 (1998)
Jacobs, D., Goldman, D., Shechtman, E.: Cosaliency: where people look when comparing images. In: Proceedings of ACM UIST, pp. 219–228, October 2010
Cheng, M.M., Mitra, N.J., Huang, X., Hu, S.M.: SalientShape: group saliency in image collections. Vis. Comput. 30, 443–453 (2013). https://doi.org/10.1007/s00371-013-0867-4
Chang, K., Liu, T., Lai, S.: From co-saliency to co-segmentation: an efficient and fully unsupervised energy minimization model. In: Proceedings of IEEE CVPR, pp. 2129–2136, June 2011
Xue, J., Wang, L.: Automatic salient object extraction with contextual cue and its applications to recognition and alpha matting. Pattern Recognit. 46(11), 2874–2889 (2013)
Zhang, L., Huang, H.: Hierarchical narrative collage for digital photo album. Comput. Graph. Forum 31(7), 2173–2181 (2012)
Fu, H., Cao, X., Tu, Z.: Cluster-based co-saliency detection. IEEE Trans. Image Process. (TIP) 22(10), 3766–3778 (2013)
Li, H., Ngan, K.: A co-saliency model of image pairs. IEEE Trans. Image Process. 20(12), 3365–3375 (2011)
Cao, X., Tao, Z., Zhang, B., Fu, H., Feng, W.: Self-adaptively weighted co-saliency detection via rank constraint. IEEE TIP 23, 4175–4186 (2014)
Lu, H., Li, X., Zhang, L., Ruan, X., Yang, M.H.: Dense and sparse reconstruction error based saliency descriptor. IEEE Trans. Image Process. 25(4), 1592–1603 (2016)
Li, Y., Fu, K., Liu, Z., Yang, J.: Efficient saliency-model-guided visual co-saliency detection. IEEE Signal Process. Lett. 22(5), 588–592 (2015)
Zhang, D., Han, J., Li, C., et al.: Detection of co-salient objects by looking deep and wide. Int. J. Comput. Vis. 120(2), 215–232 (2016)
Alexe, B., Deselaers, T.: What is an object? In: Proceedings of IEEE CVPR, pp. 73–80, June 2010
Chang, K., Liu, T., Chen, H., Lai, S.: Fusing generic objectness and visual saliency for salient object detection. In: Proceedings of IEEE ICCV, pp. 914–921, November 2011
Jiang, P., Ling, H., Yu, J., Peng, J.: Salient region detection by UFO: uniqueness, focusness and objectness. In: Proceedings of IEEE ICCV, pp. 1976–1983, December 2013
Jia, Y., Han, M.: Category-independent object-level saliency detection. In: Proceedings of IEEE ICCV, pp. 1761–1768, December 2013
Zhu, W., et al.: Saliency optimization from robust background detection. In: Proceedings of IEEE CVPR (2014)
Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: SLIC superpixels. Technical report 149300. EPFL (2010)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)
Batra, D., Kowdle, A., Parikh, D., Jie, L., Chen, T.: iCoseg: interactive co-segmentation with intelligent scribble guidance. In: CVPR (2010)
Winn, J., Criminisi, A., Minka, T.: Object categorization by learned universal visual dictionary. In: ICCV (2005)
Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: CVPR (2009)
Shen, X., Wu, Y.: A unified approach to salient object detection via low rank matrix recovery. In: CVPR (2012)
Acknowledgements
This work was supported by National High Technology Research and Development Program of China (No. 2007AA01Z334), National Natural Science Foundation of China (Nos. 61321491 and 61272219), Innovation Fund of State Key Laboratory for Novel Software Technology (Nos. ZZKT2013A12 and ZZKT2016A11), and Program for New Century Excellent Talents in University of China (NCET-04-04605).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Li, B., Sun, Z., Hu, J., Xu, J. (2018). Co-saliency Detection via Sparse Reconstruction and Co-salient Object Discovery. In: Zeng, B., Huang, Q., El Saddik, A., Li, H., Jiang, S., Fan, X. (eds) Advances in Multimedia Information Processing – PCM 2017. PCM 2017. Lecture Notes in Computer Science(), vol 10736. Springer, Cham. https://doi.org/10.1007/978-3-319-77383-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-77383-4_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77382-7
Online ISBN: 978-3-319-77383-4
eBook Packages: Computer ScienceComputer Science (R0)