access icon free Salient object detection via reciprocal function filter

Salient object detection (SOD) has been attracting a lot of interest, and recently many computational models have been developed. Here, the authors formulate a SOD model, in which saliency map is computed as a combination of the colour, its distribution-based saliency and orientation saliency. Similar to traditional SODs, the proposed method is based on super-pixel segmentation and super-pixel utilises both colour and its distribution-based saliency to generate a coarse saliency map. However, distinct from traditional SODs, authors further use orientation contrast to optimise the coarse saliency map to obtain an improved saliency map. Authors’ contributions are twofold. First, the authors combine colour uniqueness and its distribution with local orientation information (LOI) used in Itti's model to effectively improve profiles of salient regions. Second, a reciprocal function is defined to substitute the Gabor function used in LOI, and the authors have proved that the substitution could detect relatively homogeneous and uniform regions at the boundary of salient object, whereas it is what the traditional models lack. Authors’ approach significantly outperforms state-of-the-art methods on four benchmark datasets, while the authors demonstrate that the proposed method runs as fast as most existing algorithms.

Inspec keywords: feature extraction; image segmentation; object detection; image resolution; image colour analysis; filtering theory

Other keywords: SOD model; colour uniqueness; Itti's model; traditional models lack; local orientation information; Gabor function; salient regions; salient object detection; improved saliency map; distribution-based saliency; orientation saliency; super-pixel segmentation; coarse saliency map; orientation contrast; reciprocal function filter

Subjects: Filtering methods in signal processing; Optical, image and video signal processing; Computer vision and image processing techniques

References

    1. 1)
      • 41. Li, G., Yu, Y.: ‘Visual saliency based on multiscale deep features’, Proc. of the IEEE conf. on computer vision and pattern recognition, Boston, USA, 2015, pp. 54555463.
    2. 2)
      • 5. Parkhurst, D., Law, K., Niebur, E.: ‘Modeling the role of salience in the allocation of overt visual attention’, Vis. Res., 2002, 42, (1), pp. 107123.
    3. 3)
      • 30. Wang, P., Wang, J., Zeng, G., et al: ‘Salient object detection for searched web images via global saliency’. IEEE Conf. on Computer Vision and Pattern Recognition, Providence, Rhode Island, USA, 2012, pp. 31943201.
    4. 4)
      • 4. Chen, T., Cheng, M.-M., Tan, P., et al: ‘Sketch2photo: internet image montage’, ACM Trans. Graph., 2009, 28, (5), pp. 110.
    5. 5)
      • 39. 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, (11), p. 2274.
    6. 6)
      • 33. Jiang, H., Cheng, M.M., Li, S.J., et al: ‘Joint salient object detection and existence prediction’, Front. Comput. Sci., 2017, pp. 111.
    7. 7)
      • 38. Hou, Q., Cheng, M.M., Hu, X., et al: ‘Deeply supervised salient object detection with short connections’. 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) IEEE, Honolulu, Hawaii, USA, 2017, pp. 53005309.
    8. 8)
      • 25. Khuwuthyakorn, P., Robles-Kelly, A., Zhou, J.: ‘Object of interest detection by saliency learning’. European Conf. on Computer Vision, Crete, Greece, 2010.
    9. 9)
      • 7. Cheng, M.M., Zhang, G.X., Mitra, N.J.: ‘Global contrast based salient region detection’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 37, (3), pp. 569582.
    10. 10)
      • 13. Chang, K.-Y., Liu, T.-L., Chen, H.-T., et al: ‘Fusing generic objectness and visual saliency for salient object detection’. Int. Conf. on Computer Vision, Barcelona, Spain, 2011.
    11. 11)
      • 31. Moosmann, F., Larlus, D., Jurie, F.: ‘Learning saliency maps for object categorization’. Int. Workshop on The Representation and Use of Prior Knowledge in Vision (in ECCV'06), Graz, Austria, 2006.
    12. 12)
      • 17. Girshick, R., Donahue, J., Darrell, T., et al: ‘Rich feature hierarchies for accurate object detection and semantic segmentation’. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, Ohio, USA, 2014.
    13. 13)
      • 44. Wang, L., Lu, H., Ruan, X., et al: ‘Deep networks for saliency detection via local estimation and global search’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Boston, USA, 2015, pp. 31833192.
    14. 14)
      • 12. Perazzi, F., Krahenbuhl, P., Pritch, Y., et al: ‘Saliency filters: contrast based filtering for salient region detection’. IEEE Conf. on Computer Vision and Pattern Recognition, Providence, Rhode Island, USA, 2012.
    15. 15)
      • 32. Huang, F., Qi, J., Lu, H., et al: ‘Salient object detection via multiple instance learning’, IEEE Trans. Image Process., 2017, 26, (4), pp. 19111922.
    16. 16)
      • 29. Carreira, J., Sminchisescu, C.: ‘Constrained parametric min-cuts for automatic object segmentation’. IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, California, USA, 2010, pp. 32413248.
    17. 17)
      • 23. Li, X., Lu, H., Zhang, L., et al: ‘Saliency detection via dense and sparse reconstruction’. IEEE Int. Conf. on Computer Vision IEEE, Sydney, Australia, 2013, pp. 29762983.
    18. 18)
      • 43. Achanta, R., Hemami, S., Estrada, F., et al: ‘Frequency-tuned salient region detection’. IEEE Conf. on Computer Vision and Pattern Recognition, 2009. CVPR 2009 IEEE, Boston, USA, 2009, pp. 15971604.
    19. 19)
      • 27. Kim, J., Han, D., Tai, Y.-W., et al: ‘Salient region detection via high-dimensional colour transform’. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, Ohio, USA, 2014.
    20. 20)
      • 6. Itti, L., Koch, C.: ‘Computational modelling of visual attention’, Nat. Rev. Neurosci., 2001, 2, (3), pp. 194203.
    21. 21)
      • 28. Mehrani, P., Veksler, O.: ‘Saliency segmentation based on learning and graph cut refinement’. British Machine Vision Conf., Wales, UK, 2010.
    22. 22)
      • 35. Li, X., Zhao, L., Wei, L., et al: ‘Deepsaliency: multi-task deep neural network model for salient object detection’, IEEE Trans. Image Process., 2016, 25, (8), pp. 39193930.
    23. 23)
      • 3. Kanan, C., Cottrell, G.W.: ‘Robust classification of objects, faces, and flowers using natural image statistics’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, San Francisco, California, USA, 2010, pp. 24722479.
    24. 24)
      • 8. Liu, T., Yuan, Z., Sun, J., et al: ‘Learning to detect a salient object’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (2), p. pp. 353367.
    25. 25)
      • 24. Zhu, W., Liang, S., Wei, Y., et al: ‘Saliency optimization from robust background detection’. IEEE Conf. on Computer Vision and Pattern Recognition. IEEE Computer Society, Columbus, Ohio, USA, 2014, pp. 28142821.
    26. 26)
      • 1. Donoser, M., Urschler, M., Hirzer, M., et al: ‘Saliency driven total variation segmentation’. Int. Conf. on Computer Vision, Kyoto, Japan, 2009.
    27. 27)
      • 42. Jiang, P., Ling, H., Yu, J., et al: ‘Salient region detection by ufo: uniqueness, focusness and objectness’. 2013 IEEE Int. Conf. on Computer Vision (ICCV), Sydney, Australia, 2013, pp. 19761983.
    28. 28)
      • 16. He, K., Zhang, X., Ren, S., et al: ‘Spatial pyramid pooling in deep convolutional networks for visual recognition’. European Conf. on Computer Vision, Zurich, Switzerland, 2014.
    29. 29)
      • 34. He, S, Lau, R.W., Liu, W., et al: ‘SuperCNN: a super-pixelwise convolutional neural network for salient object detection’, Int. J. Comput. Vis., 2015, 115, (3), pp. 330344.
    30. 30)
      • 36. Li, G., Yu, Y.: ‘Deep contrast learning for salient object detection’, Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016, pp. 478487.
    31. 31)
      • 18. Itti, L., Koch, C., Niebur, E.: ‘A model of saliency-based visual attention for rapid scene analysis’, Pattern Anal. Mach. Intell., 1998, 20, (11), pp. 12541259.
    32. 32)
      • 14. Li, Y., Hou, X., Koch, C., et al: ‘The secrets of salient object segmentation’. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, Ohio, USA, 2014.
    33. 33)
      • 22. Jiang, B., Zhang, L., Lu, H., et al: ‘Saliency detection via absorbing markov chain’. IEEE Int. Conf. on Computer Vision, IEEE Computer Society, Sydney, Australia, 2013, pp. 16651672.
    34. 34)
      • 11. Wei, Y., Wen, F., Zhu, W., et al: ‘Geodesic saliency using background priors’. European Conf. on Computer Vision, Florence, Italy, 2012.
    35. 35)
      • 10. Han, J., Zhang, D., Hu, X., et al: ‘Background prior-based salient object detection via deep reconstruction residual’, IEEE Trans. Circuits Syst. Video Technol., 2015, 25, (8), pp. 13091321.
    36. 36)
      • 21. Yan, Q., Xu, L., Shi, J., et al: ‘Hierarchical saliency detection’. Computer Vision and Pattern Recognition IEEE, Portland, Oregon, USA, 2013, pp. 11551162.
    37. 37)
      • 26. Lu, S., Mahadevan, V., Vasconcelos, N.: ‘Learning optimal seeds for diffusion-based salient object detection’. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, Ohio, USA, 2014.
    38. 38)
      • 20. Borji, A., Cheng, M.M., Jiang, H., et al: ‘Salient object detection: a survey’, Eprint Arxiv, 2014, 16, (7), p. 3118.
    39. 39)
      • 19. Borji, A., Sihite, D.N., Itti, L.: ‘Salient object detection: a benchmark’, IEEE Trans. Image Process., 2015, 24, (12), pp. 414429.
    40. 40)
      • 15. LeCun, Y., Bottou, L., Bengio, Y., et al: ‘Gradient-based learning applied to document recognition’, Proc. IEEE, 1998, 86, (11), pp. 22782324.
    41. 41)
      • 2. Itti, L.: ‘Automatic foveation for video compression using a neurobiological model of visual attention’, IEEE Trans. Image Process., 2004, pp. 13041318.
    42. 42)
      • 45. Cheng, M.M., Warrell, J., Lin, W.Y., et al: ‘Efficient salient region detection with soft image abstraction’. IEEE Int. Conf. on Computer Vision. IEEE Computer Society, Sydney, Australia, 2013, pp. 15291536.
    43. 43)
      • 9. Yang, C., Zhang, L., Lu, H., et al: ‘Saliency detection via graph-based manifold ranking’. Proc. IEEE Conf. CVPR, Portland, Oregon, USA, 2013, pp. 31663173.
    44. 44)
      • 37. Liu, N., Han, J.: ‘DHSNet: deep hierarchical saliency network for salient object detection’. Computer Vision and Pattern Recognition. IEEE, Las Vegas, USA, 2016, pp. 678686.
    45. 45)
      • 40. Collins, R.T.: ‘Mean-shift blob tracking through scale space’. IEEE Conf. on Computer Vision and Pattern Recognition, Madison, Wisconsin, USA, 2003, vol. 2, pp. 234240.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2018.5722
Loading

Related content

content/journals/10.1049/iet-ipr.2018.5722
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading