access icon free Objectness to assist salient object detection

© The Institution of Engineering and Technology
Received 29/07/2015, Accepted 21/12/2015, Revised 27/11/2015, Published 01/05/2016

When dealing with salient object that contains several regions with different appearances, salient object detection can be a difficult task as often only parts of the salient object are highlighted and consistency between the salient regions is poor. This study tackles this problem by introducing objectness to assist the salient object detection. Rather than treating objectness in the same manner as other low-level cues (e.g. uniqueness, location etc.) for the determination of regional saliency values, the authors emphasise that objectness should also play a significant role in tuning the consistency between salient regions. The authors integrate objectness, uniqueness and centre bias to find potential salient regions and then enforce consistency between these regions using a full-connected Gaussian Markov random field with the weights determined by the objectness score. Experimental results on public benchmark datasets indicate that the authors’ method performs well on many images which cannot be well detected traditionally.

Inspec keywords: Gaussian processes; Markov processes; object detection

Other keywords: full-connected Gaussian Markov random field; salient object detection; low-level cues; objectness score; public benchmark datasets

Subjects: Markov processes; Markov processes; Computer vision and image processing techniques; Optical, image and video signal processing

References

    1. 1)
    2. 2)
      • 6. Rutishauser, U., Walther, D., Koch, C., et al: ‘Is bottom-up attention useful for object recognition?’. IEEE Conf. Computer Vision and Pattern Recognition, 2004, pp. 37–44.
    3. 3)
      • 7. Borji, A., Cheng, M.-M., Jia, H.-Z., et al: ‘Salient object detection: a survey’, arXiv eprint, 2014.
    4. 4)
      • 11. Klein, D.A., Frintrop, S.: ‘Center-surround divergence of feature statistics for salient object detection’. IEEE Int. Conf. on Computer Vision, 2011, pp. 2214–2219.
    5. 5)
      • 5. Avidan, S., Shamir, A.: ‘Seam carving for content aware image resizing’, ACM Trans. Graph., 2007, 3, (26), pp. 267–276.
    6. 6)
      • 23. Cheng, M.-M., Zhang, Z.-M., Lin, W.-Y., et al: ‘BING: binarized normed gradients for objectness estimation at 300fps’. IEEE Conf. Computer Vision and Pattern Recognition, 2014, pp. 3286–3293.
    7. 7)
      • 17. Yan, Q., Xu, L., Shi, J.-P., et al: ‘Hierarchical saliency detection’. IEEE Conf. Computer Vision and Pattern Recognition, 2013, pp. 1155–1162.
    8. 8)
      • 31. Alpert, S., Galun, M., Brandt, A., et al: ‘Image segmentation by probabilistic bottom-up aggregation and cue integration’, IEEE Conf. Comput. Vis. Pattern Recognit., 2007, 34, (2), pp. 1–8.
    9. 9)
      • 29. Borji, A.: ‘What is a salient object?. A dataset and a baseline model for salient object detection’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 24, (2), pp. 742–756.
    10. 10)
      • 3. Hiremath, P., Pujari, J.: ‘Content based image retrieval using color boosted salient points and shape features of an image’, Int. J. Image Process., 2008, 1, (2), pp. 10–17.
    11. 11)
      • 26. Tatler, B.: ‘The central fixation bias in scene viewing: Selecting an optimal viewing position independently of motor biases and image feature distributions’, J. Vis., 2007, 14, (7), pp. 4.1–4.17.
    12. 12)
      • 4. Chang, K.-Y., Liu, T.-L., Lai, S.-H.: ‘From co-saliency to co-segmentation: an efficient and fully unsupervised energy minimization model’. IEEE Conf. Computer Vision and Pattern Recognition, 2011, pp. 2129–2136.
    13. 13)
      • 12. Cheng, M.-M., Mitra, N.J., Huang, X., et al: ‘Global contrast based salient region detection’. IEEE Conf. Computer Vision and Pattern Recognition, 2011, pp. 409–416.
    14. 14)
      • 2. Navalpakkam, V., Itti, L.: ‘An integrated model of top-down and bottom-up attention for optimizing detection speed’. IEEE Conf. Computer Vision and Pattern Recognition, 2006, pp. 2049–2056.
    15. 15)
      • 1. Palmer, S.: ‘Vision science: Photons to phenomenology’ (MIT Press Cambridge, 1999).
    16. 16)
      • 32. Margolin, R., Manor, L.Z., Tal, A.: ‘How to evaluate foreground maps?’. IEEE Conf. on Computer Vision and Pattern Recognition, 2014, pp. 248–255.
    17. 17)
    18. 18)
      • 19. Jia, Y., Han, M.: ‘Category-independent object-level saliency detection’. IEEE Int. Conf. Computer Vision, 2013, pp. 1761–1768.
    19. 19)
      • 16. Cheng, M.-M., Warrell, J., Lin, W.-Y., et al: ‘Efficient salient region detection with soft image abstraction’. IEEE Int. Conf. Computer Vision, 2013, pp. 1529–1536.
    20. 20)
    21. 21)
      • 27. Everingham, M., Van Gool, L., Williams, C., et al: ‘The PASCAL visual object classes challenge 2007’, 2007.
    22. 22)
      • 20. Jiang, P., Ling, H., Yu, J., et al: ‘Salient region detection by UFO: uniqueness, focusness and objectness’. IEEE Int. Conf. Computer Vision, 2013, pp. 1976–1983.
    23. 23)
      • 10. Achanta, R., Hemami, S., Estrada, F., et al: ‘Frequency-tuned salient region detection’. IEEE Conf. Computer Vision and Pattern Recognition, 2009, pp. 1597–1604.
    24. 24)
      • 25. Gonzalez, R., Woods, R.: ‘Digital image processing’ (Prentice Hall Press, 2002).
    25. 25)
    26. 26)
      • 28. Cheng, M.-M., Mitra, N.J., Huang, X., et al: ‘Salient object detection and segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 37, (3).
    27. 27)
      • 18. Zhang, J., Sclaroff, S.: ‘Saliency detection: a Boolean map approach’. IEEE Int. Conf. Computer Vision, 2013, pp. 153–160.
    28. 28)
      • 13. Perazzi, F., Krahenbuhl, P., Pritch, Y., et al: ‘Saliency filters: contrast based filtering for salient region detection’. IEEE Conf. Computer Vision and Pattern Recognition, 2012, pp. 733–740.
    29. 29)
      • 15. Li, J., Tian, Y., Duan, L., et al: ‘Estimating visual saliency through single image optimization’, IEEE Signal Process. Lett., 2013, 9, (20), pp. 845–848.
    30. 30)
    31. 31)
      • 30. Yang, C., Zhang, L., Lu, H., et al: ‘Saliency detection via graph-based manifold ranking’, IEEE Conf. Comput. Vis. Pattern Recognit., 2013, 9, (4), pp. 3166–3173.
    32. 32)
      • 24. Zitnick, C.L., Dollar, P.: ‘Edge boxes: locating object proposals from edges’. European Conf. Computer Vision, 2014, pp. 391–405.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2015.0487
Loading

Related content

content/journals/10.1049/iet-ipr.2015.0487
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading