The Visual Computer

, Volume 33, Issue 11, pp 1415–1428 | Cite as

Salient object detection in complex scenes via D-S evidence theory based region classification

  • Chunlei Yang
  • Jiexin Pu
  • Yongsheng Dong
  • Zhonghua Liu
  • Lingfei Liang
  • Xiaohong Wang
Original Article

Abstract

In complex scenes, multiple objects are often concealed in cluttered backgrounds. Their saliency is difficult to be detected by using conventional methods, mainly because single color contrast can not shoulder the mission of saliency measure; other image features should be involved in saliency detection to obtain more accurate results. Using Dempster-Shafer (D-S) evidence theory based region classification, a novel method is presented in this paper. In the proposed framework, depth feature information extracted from a coarse map is employed to generate initial feature evidences which indicate the probabilities of regions belonging to foreground or background. Based on the D-S evidence theory, both uncertainty and imprecision are modeled, and the conflicts between different feature evidences are properly resolved. Moreover, the method can automatically determine the mass functions of the two-stage evidence fusion for region classification. According to the classification result and region relevance, a more precise saliency map can then be generated by manifold ranking. To further improve the detection results, a guided filter is utilized to optimize the saliency map. Both qualitative and quantitative evaluations on three publicly challenging benchmark datasets demonstrate that the proposed method outperforms the contrast state-of-the-art methods, especially for detection in complex scenes.

Keywords

Salient object detection Complex scene D-S evidence theory Multiple feature fusion Region classification 

Notes

Acknowledgments

This work was supported in part by the International S & T Cooperation Program of China (No. 2011DFR10480), the Natural Science Foundation of China (No. 61301230), and the Key Project of Science and Technology of Henan (No. 142107000021).

References

  1. 1.
    Achanta, R., Hemamiz, S., Estraday, F., et al.: Frequency-tuned salient region detection. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 1597–1604 (2009)Google Scholar
  2. 2.
    Achanta, R., Shaji, A., Smith, K., et al.: Slic superpixels. Tech. rep. (2010)Google Scholar
  3. 3.
    Achanta, R., Susstrunk, S.: Saliency detection using maximum symmetric surround. In: 17th IEEE Int. Conf. on image processing (ICIP), pp. 2653–2656 (2010)Google Scholar
  4. 4.
    Ando, T.: Majorization relations for hadamard products. Linear Algebra Appl. 223–224(1), 57–64 (1995)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Baghli, I., Nakib, A., Sellam, E., et al.: Hybrid framework based on evidence theory for blood cell image segmentation. Proc. SPIE Int. Soc. Opt. Eng. 9038(3), 252–260 (2014)Google Scholar
  6. 6.
    Bhattacharya, A., Saraswat, V.K., Manimaran, P., et al.: Evidence theoretic classification of ballistic missiles. Appl. Soft Comput. 37, 479–489 (2015)CrossRefGoogle Scholar
  7. 7.
    Chen, Y., Chan, A.B., Wang, G.: Adaptive figure-ground classification. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 654–661 (2012)Google Scholar
  8. 8.
    Cheng, M.M., Mitra, N.J., Huang, X., et al.: Salientshape: group saliency in image collections. Vis. Comput. 30(4), 443–453 (2014)CrossRefGoogle Scholar
  9. 9.
    Dempster, A.P.: Upper and lower probabilities induced by a multi-valued mapping. Ann. Math. Stat. 38(2), 325–339 (1967)CrossRefMATHGoogle Scholar
  10. 10.
    Dong, G., Kuang, G.: Target recognition via information aggregation through dempstershafer’s evidence theory. Geosci. Remote Sens. Lett. IEEE 12(6), 1247–1251 (2015)CrossRefGoogle Scholar
  11. 11.
    Fan, Q., Qi, C.: Two-stage salient region detection by exploiting multiple priors. J. Vis. Commun. Image Represent. 25(8), 1823–1834 (2014)CrossRefGoogle Scholar
  12. 12.
    Frintrop, S., Werner, T., Martin Garcia, G.: Traditional saliency reloaded: a good old model in new shape. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 82–90 (2015)Google Scholar
  13. 13.
    Goferman, S., Zelnik-Manor, L., Tal, A.: Context-aware saliency detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 1915–1926 (2012)CrossRefGoogle Scholar
  14. 14.
    Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. Adv. Neural Inf. Process. Syst. 19, 545–552 (2006)Google Scholar
  15. 15.
    Hou, X., Zhang, L.: Saliency detection: a spectral residual approach. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 1–8 (2007)Google Scholar
  16. 16.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  17. 17.
    Jiang, H., Wang, J., Yuan, Z., et al.: Salient object detection: a discriminative regional feature integration approach. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 2083–2090. IEEE (2013)Google Scholar
  18. 18.
    Kaiming, H., Jian, S., Xiaoou, T.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(16), 1397–1409 (2013)Google Scholar
  19. 19.
    Li, B.C., Wang, B., Wei, J., et al.: An efficient combination rule of evidence theory. J. Data Acquis. Process. (in Chinese) 1, 33–36 (2002)Google Scholar
  20. 20.
    Li, Y., Hou, X., Koch, C., et al.: The secrets of salient object segmentation. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 280–287 (2014)Google Scholar
  21. 21.
    Liang, L., Yuanlu, X., Xiaodan, L., et al.: Complex background subtraction by pursuing dynamic spatio-temporal models. IEEE Trans. Image Process. 23(7), 3191–3202 (2014)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Lin, T.C.: Decision-based filter based on svm and evidence theory for image noise removal. Neural Comput. Appl. 21(4), 695–703 (2012)CrossRefGoogle Scholar
  23. 23.
    Lu, Y.: Learning attention map from images. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 1067–1074 (2012)Google Scholar
  24. 24.
    Margolin, R., Tal, A., Zelnik-Manor, L.: What makes a patch distinct? In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 1139–1146. IEEE, Portland (2013)Google Scholar
  25. 25.
    Margolin, R., Zelnik-Manor, L., Tal, A.: Saliency for image manipulation. Vis.Comput. 29(5), 381–392 (2013)CrossRefGoogle Scholar
  26. 26.
    Perazzi, F., Krahenbuhl, P., Pritch, Y., et al.: Saliency filters: contrast based filtering for salient region detection. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 733–740. IEEE, Providence, RI (2012)Google Scholar
  27. 27.
    Qiu, Y., Sun, X., She, M.F.: Saliency detection using hierarchical manifold learning. Neurocomputing 168, 538–549 (2015)CrossRefGoogle Scholar
  28. 28.
    Scharfenberger, C., Wong, A., Fergani, K., et al.: Statistical textural distinctiveness for salient region detection in natural images. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 979–986. IEEE, Portland (2013)Google Scholar
  29. 29.
    Shafer, G.: A mathematical theory of evidence. Technometrics 20(1), 242 (1978)Google Scholar
  30. 30.
    Sharon, A., Meirav, G., Achi, B., et al.: Image segmentation by probabilistic bottom-up aggregation and cue integration. IEEE Trans. Pattern Anal. Mach. Intell. 34(2), 1–8 (2007)Google Scholar
  31. 31.
    Shi, J., Yan, Q., Xu, L., et al.: Hierarchical image saliency detection on extended cssd. IEEE Trans. Pattern Anal. Mach. Intell. 9(4), 1 (2014)Google Scholar
  32. 32.
    Shi, K., Wang, K., Lu, J., et al.: Pisa: Pixelwise image saliency by aggregating complementary appearance contrast measures with spatial priors. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 2115–2122. IEEE, Portland (2013)Google Scholar
  33. 33.
    Shi, Y., Yi, Y., Yan, H., et al.: Region contrast and supervised locality-preserving projection-based saliency detection. Vis. Comput. 31(9), 1191–1205 (2015)CrossRefGoogle Scholar
  34. 34.
    Song, M., Chen, C., Wang, S., et al.: Low-level and high-level prior learning for visual saliency estimation. Inf. Sci. 281, 573–585 (2014)CrossRefGoogle Scholar
  35. 35.
    Sun, Q., Ye, X.Q., Gu, W.K.: A new combination rules of evidence theory. Chin. J. Electron. 28(8), 116–119 (2000)Google Scholar
  36. 36.
    Tang, H., Chen, C., Bie, Y.: Prediction of human eye fixation by a single filter. J. Signal Process. Syst., 1–6 (2016). doi: 10.1007/s11265-016-1131-8
  37. 37.
    Tang, R.D., Yu, C.R., Qian, S.H., et al.: Saliency detection integrated with depth information. In: Int. Conf. on computer information systems and industrial applications (CISIA), ACSR-Advances in comptuer science research, vol. 18, pp. 663–665 (2015)Google Scholar
  38. 38.
    Tilke, J., Ehinger, K., Durand, F., et al.: Learning to predict where humans look. In: IEEE Int. Conf. on computer vision (ICCV), pp. 2106–2113 (2009)Google Scholar
  39. 39.
    Tong, N., Lu, H., Xiang, R., et al.: Salient object detection via bootstrap learning. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 1884–1892 (2015)Google Scholar
  40. 40.
    Tong, N., Lu, H., Zhang, L., et al.: Saliency detection with multi-scale superpixels. IEEE Signal Process. Lett. 21(9), 1035–1039 (2014)CrossRefGoogle Scholar
  41. 41.
    Wang, X., Zhang, L., Lin, L., et al.: Deep joint task learning for generic object extraction. Adv. Neural Inf. Process. Syst., 523–531 (2015). arXiv preprint arXiv:1502.00743
  42. 42.
    Wei, Y., Wen, F., Zhu, W., et al.: Geodesic saliency using background priors. In: European conference on computer vision, pp. 29–42 (2012)Google Scholar
  43. 43.
    Xu, M., Zhang, H.: Saliency detection with color contrast based on boundary information and neighbors. Vis. Comput. 31(3), 355–364 (2015)MathSciNetCrossRefGoogle Scholar
  44. 44.
    Yang, C., Zhang, L., Lu, H.: Graph-regularized saliency detection with convex-hull-based center prior. IEEE Signal Process. Lett. 20(7), 637–640 (2013)CrossRefGoogle Scholar
  45. 45.
    Yang, C., Zhang, L., Lu, H., et al.: Saliency detection via graph-based manifold ranking. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 3166–3173 (2013)Google Scholar
  46. 46.
    Ye, Q., Wu, X.P., Song, Y.X.: Evidence combination method based on the weight coefficients and the confliction probability distribution. Syst. Eng. Electron. (in Chinese) 28(7), 1014–1016 (2006)MATHGoogle Scholar
  47. 47.
    Yu, H., Li, J., Tian, Y., et al.: Automatic interesting object extraction from images using complementary saliency maps. In: Proc. ACM Int. Conf. on multimedia, pp. 891–894. ACM, New York (2010)Google Scholar
  48. 48.
    Zadeh, L.A.: A simple view of the dempster-shafer theory of evidence and its implication for the rule of combination. AI Mag. 7(2), 85–90 (1986)Google Scholar
  49. 49.
    Zhang, Y., Mao, Z., Li, J., et al.: Salient region detection for complex background images using integrated features. Inf. Sci. 281, 586–600 (2014)CrossRefGoogle Scholar
  50. 50.
    Zhu, S.S., Yung, N.H.C.: Sub-scene generation: a step towards complex scene understanding. In: IEEE Int. Conf. on multimedia, pp. 1–6 (2011)Google Scholar
  51. 51.
    Zhu, W., Liang, S., Wei, Y., et al.: Saliency optimization from robust background detection. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 2814–2821 (2014)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Henan University of Science and TechnologyLuoyangChina

Personalised recommendations