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.
Similar content being viewed by others
References
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)
Achanta, R., Shaji, A., Smith, K., et al.: Slic superpixels. Tech. rep. (2010)
Achanta, R., Susstrunk, S.: Saliency detection using maximum symmetric surround. In: 17th IEEE Int. Conf. on image processing (ICIP), pp. 2653–2656 (2010)
Ando, T.: Majorization relations for hadamard products. Linear Algebra Appl. 223–224(1), 57–64 (1995)
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)
Bhattacharya, A., Saraswat, V.K., Manimaran, P., et al.: Evidence theoretic classification of ballistic missiles. Appl. Soft Comput. 37, 479–489 (2015)
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)
Cheng, M.M., Mitra, N.J., Huang, X., et al.: Salientshape: group saliency in image collections. Vis. Comput. 30(4), 443–453 (2014)
Dempster, A.P.: Upper and lower probabilities induced by a multi-valued mapping. Ann. Math. Stat. 38(2), 325–339 (1967)
Dong, G., Kuang, G.: Target recognition via information aggregation through dempstershafer’s evidence theory. Geosci. Remote Sens. Lett. IEEE 12(6), 1247–1251 (2015)
Fan, Q., Qi, C.: Two-stage salient region detection by exploiting multiple priors. J. Vis. Commun. Image Represent. 25(8), 1823–1834 (2014)
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)
Goferman, S., Zelnik-Manor, L., Tal, A.: Context-aware saliency detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 1915–1926 (2012)
Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. Adv. Neural Inf. Process. Syst. 19, 545–552 (2006)
Hou, X., Zhang, L.: Saliency detection: a spectral residual approach. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 1–8 (2007)
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)
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)
Kaiming, H., Jian, S., Xiaoou, T.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(16), 1397–1409 (2013)
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)
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)
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)
Lin, T.C.: Decision-based filter based on svm and evidence theory for image noise removal. Neural Comput. Appl. 21(4), 695–703 (2012)
Lu, Y.: Learning attention map from images. In: IEEE Conf. on computer vision and pattern recognition (CVPR), pp. 1067–1074 (2012)
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)
Margolin, R., Zelnik-Manor, L., Tal, A.: Saliency for image manipulation. Vis.Comput. 29(5), 381–392 (2013)
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)
Qiu, Y., Sun, X., She, M.F.: Saliency detection using hierarchical manifold learning. Neurocomputing 168, 538–549 (2015)
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)
Shafer, G.: A mathematical theory of evidence. Technometrics 20(1), 242 (1978)
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)
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)
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)
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)
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)
Sun, Q., Ye, X.Q., Gu, W.K.: A new combination rules of evidence theory. Chin. J. Electron. 28(8), 116–119 (2000)
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
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)
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)
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)
Tong, N., Lu, H., Zhang, L., et al.: Saliency detection with multi-scale superpixels. IEEE Signal Process. Lett. 21(9), 1035–1039 (2014)
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
Wei, Y., Wen, F., Zhu, W., et al.: Geodesic saliency using background priors. In: European conference on computer vision, pp. 29–42 (2012)
Xu, M., Zhang, H.: Saliency detection with color contrast based on boundary information and neighbors. Vis. Comput. 31(3), 355–364 (2015)
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)
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)
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)
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)
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)
Zhang, Y., Mao, Z., Li, J., et al.: Salient region detection for complex background images using integrated features. Inf. Sci. 281, 586–600 (2014)
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)
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)
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).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yang, C., Pu, J., Dong, Y. et al. Salient object detection in complex scenes via D-S evidence theory based region classification. Vis Comput 33, 1415–1428 (2017). https://doi.org/10.1007/s00371-016-1288-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-016-1288-y