A Unified Approach of Object-Level Saliency Detection in Images and Videos

Abstract:

Object-level saliency detection is an important branch of visual saliency. In this paper, we propose a novel method which can conduct object-level saliency detection in both images and videos in a unified way. We employ a more effective spatial compactness assumption to measure saliency instead of the popular contrast assumption. In addition, we present a combination framework which integrates multiple saliency maps generated in different feature maps. The proposed algorithm can automatically select saliency maps of high quality according to the quality evaluation score we define. The experimental results demonstrate that the proposed method outperforms all state-of-the-art methods on both of the datasets of still images and video sequences.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 1401-1405
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.1401
• Online since: September 2013
• Authors: Chi Zhang, Wei Qiang Wang
• Keywords: Saliency Detection, Salient Object Detection

References

[1] L. Itti, C. Koch, and E. Niebur, A model of saliencybased visual attention for rapid scene analysis, TPAMI, vol. 20, no. 11, pp.1254-1259, (1998).

DOI: 10.1109/34.730558

[2] N.D.B. Bruce and J.K. Tsotsos, Saliency based on information maximization, in NIPS, (2005).

[3] U. Rutishauser, D. Walther, C. Koch, and P. Perona, Is bottom-up attention useful for object recognition?, in CVPR, (2004).

DOI: 10.1109/cvpr.2004.1315142

[4] A. Santella, M. Agrawala, D. DeCarlo, D. Salesin, and M. Cohen, Gaze-based interaction for semi-automatic photo cropping, in Proceedings of the SIGCHI conference on Human Factors, (2006).

DOI: 10.1145/1124772.1124886

[5] H. Wu, Y.S. Wang, K.C. Feng, T.T. Wong, T.Y. Lee, and P.A. Heng, Resizing by symmetry-summarization, ACM Trans. Graph., vol. 29, no. 6, p.159: 1–159: 10, (2010).

DOI: 10.1145/1882261.1866185

[6] D. Comaniciu and P. Meer, Mean shift: A robust approach toward feature space analysis, TPAMI, vol. 24, no. 5, pp.603-619, (2002).

DOI: 10.1109/34.1000236

[7] R. Achanta, S. Hemami, F. Estrada, and Sabine Ssstrunk, Frequency-tuned salient region detection, in CVPR, (2009).

DOI: 10.1109/cvpr.2009.5206596

[8] Esa Rahtu, Juho Kannala, Mikko Salo, and Janne Heikkila, Segmenting salient objects from images and videos, in ECCV, (2010).

DOI: 10.1007/978-3-642-15555-0_27

[9] Stas Goferman, Lihi Zelnik-Manor, and Ayellet Tal, Context-aware saliency detection, in CVPR, (2010).

DOI: 10.1109/cvpr.2010.5539929

[10] T. Liu, Z.J. Yuan, J. Sun, J.D. Wang, N.N. Zheng, X.O. Tang, and H.Y. Shum, Learning to detect a salient object, TPAMI, vol. 33, no. 2, pp.353-367, (2011).

DOI: 10.1109/tpami.2010.70

[11] M.M. Cheng, G.X. Zhang, N.J. Mitra, X. L Huang, and S. M Hu, Global contrast based salient region detection, in CVPR, (2011).

DOI: 10.1109/cvpr.2011.5995344

[12] Yulin Xie, Huchuan Lu, and Ming-Hsuan Yang, Bayesian saliency via low and mid level cues, TIP, vol. 22 , no. 2, pp.1689-1698, (2012).

DOI: 10.1109/tip.2012.2216276

[13] F. Perazzi, P. Krahenbul, Y. Pritch and A. Hornung, Saliency filters: contrast based filtering for salient region detection, in: CVPR, (2012).

DOI: 10.1109/cvpr.2012.6247743

[14] X. H Shen and Y. Wu, A unified approach to salient object detection via low rank matrix recovery, in: CVPR, (2012).

DOI: 10.1109/cvpr.2012.6247758

[15] Ali Borji, Dicky N. Sihite, and Laurent Itti, Salient Object Detection: A Benchmark, in: ECCV, (2012).

[16] Benjamin W. Tatler, The central fixation bias in scene viewing: Selecting an optimal viewing position independently of motor biases and image feature distributions, Journal of Vision, vol. 7, no. 14, p.1 – 17, (2007).

DOI: 10.1167/7.14.4

[17] David Tsai, Matthew Flagg and James M. Rehg, Motion coherent tracking with multi-label MRF optimization, in BMVC, (2010).

DOI: 10.5244/c.24.56

[18] C. Liu, Beyond pixels: exploring new representations and applications for motion analysis, Doctoral Thesis, Massachusetts Institute of Technology, (2009).