Saliency detection based on superpixels clustering and stereo disparity

详细信息    查看全文

• 作者：Shan-shan Gao ; Jing Chi ; Li Li ; Ji-biao Zou…
• 关键词：Saliency detection ; superpixels ; stereo disparity ; spatial coherence
• 刊名：Applied Mathematics - A Journal of Chinese Universities
• 出版年：2016
• 出版时间：March 2016
• 年：2016
• 卷：31
• 期：1
• 页码：68-80
• 全文大小：1,701 KB
• 参考文献：[1]R Achanta, F Estrada, P Wils, et al. Salient region detection and segmentation, In: Computer Vision Systems, Springer Berlin Heidelberg, 2008, 66–75.CrossRef
  [2]R Achanta, S Hemami, F Estrada, et al. Frequency-tuned salient region detection, In: IEEE Comput Vis Pattern Recognition (CVPR), 2009, 1597–1604.
  [3]R Achanta, A Shaji, K Smith, et al. SLIC superpixels compared to state-of-the-art superpixel methods, IEEE Trans Pattern Anal Mach Intell, 2012, 34(11): 2274–2282.CrossRef
  [4]S Avidan, A Shamir. Seam carving for content-aware image resizing, ACM Trans Graph, 2007, 26(3), Article No 10.CrossRef
  [5]M Cheng, N J Mitra, X Huang, et al. Global contrast based salient region detection, IEEE Trans Pattern Anal Mach Intell, 2015, 37(3): 569–582.CrossRef
  [6]S P Du, S M Hu, R R Martin. Changing perspective in stereoscopic images, IEEE Trans Vis Comput Graph, 2013, 19(8): 1288–1297.CrossRef
  [7]L Duan, C Wu, J Miao, et al. Visual saliency detection by spatially weighted dissimilarity, In: IEEE Comput Vis Pattern Recognition (CVPR), 2011, 473–480.
  [8]S Goferman, L Zelnik-Manor, A Tal. Context-aware saliency detection, IEEE Trans Pattern Anal Mach Intell, 2012, 34(10): 1915–1926.CrossRef
  [9]J Han, K N Ngan, M Li, et al. Unsupervised extraction of visual attention objects in color images, IEEE Trans Circuits Systems Video Technol, 2006, 16(1): 141–145.CrossRef
  [10]X Hou, L Zhang. Saliency detection: A spectral residual approach, CIn: IEEE Comput Vis Pattern Recognition (CVPR), 2007, 1–8.
  [11]L Itti, P F Baldi. Bayesian surprise attracts human attention, Adv Neural Inf Process Syst, 2005, 547–554.
  [12]L Itti, C Koch, E Niebur. A model of saliency-based visual attention for rapid scene analysis, IEEE Trans Pattern Anal Mach Intell, 1998 (11): 1254–1259.CrossRef
  [13]C Koch, S Ullman. Shifts in selective visual attention: towards the underlying neural circuitry, In: Matters of Intelligence, Springer Netherlands, 1987, 115–141.CrossRef
  [14]K Koffka. Principles of Gestalt Psychology, Routledge, 2013.
  [15]A Levinshtein, S Dickinson, C Sminchisescu. Multiscale symmetric part detection and grouping, In: Proc Internat Conf Comput Vis, 2009, 2162–2169.
  [16]T Liu, Z Yuan, J Sun, et al. Learning to detect a salient object, IEEE Trans Pattern Anal Mach Intell, 2011, 33(2): 353–367.CrossRef
  [17]Y F Ma, H J Zhang. Contrast-based image attention analysis by using fuzzy growing, Proc eleventh ACM Internat Conf Multimedia, 2003, 374–381.CrossRef
  [18]J Malik. Normalized cuts and image segmentation, IEEE Trans Pattern Anal Mach Intell, 2000, 22(8): 888–905.CrossRef
  [19]S Mattoccia. Stereo vision: algorithms and applications, Technical report, University Of Bologna, 2011.
  [20]T J Mu, J J Sun, R R Martin, S M Hu. A response time model for abrupt changes in binocular disparity, Vis Comput, 2014: 1–13.
  [21]T J Mu, J H Wang, S P Du, S M Hu. Stereoscopic image completion and depth recovery, Vis Comput, 2014, 30(6-8): 833–843.CrossRef
  [22]D Parkhurst, K Law, E Niebur. Modeling the role of salience in the allocation of overt visual attention, Vis Res, 2002, 42(1): 107–123.CrossRef
  [23]A Radhakrishna, S Appu, S Kevin, L Aurelien. SLI Superpixels, EPFL Report 149300, 2010.
  [24]A Radhakrishna, S Appu, S Kevin, L Aurelien, F Pascal, S Sabine. SLIC Superpixels Compared to State-of-the-art Superpixel Methods, IEEE Trans Pattern Anal Mach Intell, 2012, 6(1).
  [25]P Reinagel, A M Zador. Natural scene statistics at the centre of gaze, Network, 1999, 10(4): 341–350.CrossRef MATH
  [26]U Rutishauser, D Walther, C Koch, et al. Is bottom-up attention useful for object recognition? In: IEEE Comput Vis Pattern Recognition (CVPR), 2004, 2: II-37–44.
  [27]D Scharstein, R Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms, Internat J Comput Vis, 2002, 47(1-3): 7–42.CrossRef MATH
  [28]R Swaminathan, S K Nayar. Nonmetric calibration of wide-angle lenses and polycameras, IEEE Trans Pattern Anal Mach Intell, 2000, 22(10): 1172–1178.CrossRef
  [29]R Tong, Y Zhang, K L Cheng. Stereopasting: interactive composition in stereoscopic images, IEEE Trans Vis Comput Graph, 2013, 19(8): 1375–1385.CrossRef
  [30]R Y Tsai. An efficient and accurate camera calibration technique for 3D machine vision, Proc IEEE Conf Comput Vis Pattern Recognition, 1986.
  [31]A Vedaldi, S Soatto. Quick shift and kernel methods for mode seeking, In: Computer VisionCECCV 2008, 2008, 705–718.CrossRef
  [32]M Wang, J Konrad, P Ishwar, et al. Image saliency: From intrinsic to extrinsic context, In: IEEE Comput Vis Pattern Recognition (CVPR), 2011, 417–424.
  [33]J Wang, C Zhang, Y Zhou, et al. Global contrast of superpixels based salient region detection, In: Computational Visual Media, Springer Berlin Heidelberg, 2012, 130–137.CrossRef
  [34]K J Yoon, I S Kweon. Adaptive support-weight approach for correspondence search, IEEE Trans Pattern Anal Mach Intell, 2006, 28(4): 650–656.CrossRef
  [35]Y Zhai, M Shah. Visual attention detection in video sequences using spatiotemporal cues, Proc 14th ACM Internat Conf Multimedia, 2006: 815–824.CrossRef
  [36]W J Zhu, S Liang, Y C Wei, J Sun. Saliency Optimization from Robust Background Detection, IEEE Conf Comput Vis Pattern Recognition, 2014, 1049–1050. 2814-2821.
  
• 作者单位：Shan-shan Gao (1) (3)
  Jing Chi (1) (3)
  Li Li (1) (3)
  Ji-biao Zou (2)
  Cai-ming Zhang (1) (2)
  
  1. School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan, 250014, China
  3. Shandong Provincial Key Laboratory of Digital Media Technology, Jinan, 250014, China
  2. School of Computer Science and Technology, Shandong University, Jinan, 250100, China
  
• 刊物类别：Mathematics and Statistics
• 刊物主题：Mathematics
  Mathematics
  Applications of Mathematics
  Chinese Library of Science
  
• 出版者：Editorial Committee of Applied Mathematics - A Journal of Chinese Universities
• ISSN：1993-0445

文摘

Reliable saliency detection can be used to quickly and effectively locate objects in images. In this paper, a novel algorithm for saliency detection based on superpixels clustering and stereo disparity (SDC) is proposed. Firstly, we use an improved superpixels clustering method to decompose the given image. Then, the disparity of each superpixel is computed by a modified stereo correspondence algorithm. Finally, a new measure which combines stereo disparity with color contrast and spatial coherence is defined to evaluate the saliency of each superpixel. From the experiments we can see that regions with high disparity can get higher saliency value, and the saliency maps have the same resolution with the source images, objects in the map have clear boundaries. Due to the use of superpixel and stereo disparity information, the proposed method is computationally efficient and outperforms some state-of-the-art colorbased saliency detection methods.