Exploiting Hierarchical Prior Estimation for Salient Object Detection
-
摘要: 有效的显著性目标检测在计算机视觉领域一直是具有挑战性的问题.本文首先对图像进行树滤波处理,采用Quick shift方法将其分解为超像素,再通过仿射传播聚类把超像素聚集为代表性的类.与以往方法不同,本文提出根据各类中拥有的超像素的类内和类间的空间离散程度及其位于图像边界的数目,自适应地估计先验背景,并提取条状背景区域;由目标性度量(Objectness measure)粗略地描述前景范围后,通过与各类之间的空间交互信息,估计先验前景;再经过连通区域优化前景与背景信息.最后,综合考虑各超像素与先验背景和前景在CIELab颜色空间的距离,并进行显著性中心加权,得到显著图.在MSRA-1000和复杂的SOD数据库上的实验结果表明,本文算法能准确、完整地检测出显著性目标,优于21种State-of-the-art算法,包括基于部分类似原理的方法.Abstract: Effective salient object detection is still a challenging problem in computer vision. In this paper, images are processed by tree filter firstly. Then quick shift is adopted to decompose images into perceptually homogeneous superpixels. This is followed by using affinity propagation clustering to aggregate all the superpixels into representative clusters. Different from previous methods, this paper proposes a novel adaptive background prior estimation strategy. The intra-cluster and inter-cluster spatial variances of superpixels owned by some cluster are calculated, and the numbers of superpixels located along the image boundary are counted to complete the processing. Also, the strip regions of background are extracted. The objectness measure is employed to get a coarse foreground scope, which is then used to compute the spatial interactive information with all the clusters, so as to get the foreground prior. After the optimization based on connected regions, A final foreground and background prior are confirmed. A saliency map is generated by measuring the differences of CIELab color space between all the superpixels and the background and foreground prior, enhanced by salient center weighting. Experimental results on MSRA-1000 and complicated SOD databases show that the proposed method can accurately detect the whole salient object. It is superior to the 21 state-of-the-art methods, including the methods partially based on similar principles.
-
[1] Borji A, Itti L. State-of-the-art in visual attention modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1):185-207 [2] [2] Borji A, Sihite D, Itti L. Quantitative analysis of human-model agreement in visual saliency modeling:a comparative study. IEEE Transactions on Image Processing, 2013, 22(1):55-69 [3] [3] Koch C, Ullman S. Shifts in selective visual attention:towards the underlying neural circuitry. Human Neurobiology, 1985, 4(4):219-227 [4] [4] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11):1254-1259 [5] [5] Ma Y F, Zhang H J. Contrast-based image attention analysis by using fuzzy growing. In:Proceedings of the 11th ACM International Conference on Multimedia. Berkeley, USA:ACM, 2003. 374-381 [6] [6] Achanta R, Estrada F, Wils P, Ssstrunk S. Salient region detection and segmentation. In:Proceedings of the 6th International Conference on Computer Vision Systems. Santorini, Greece:Springer, 2008. 66-75 [7] [7] Rahtu E, Kannala J, Salo M, Heikkil J. Segmenting salient objects from images and videos. In:Proceedings of the 11th European Conference on Computer Vision. Heraklion, Greece:Springer, 2010. 366-379 [8] [8] Hou X D, Zhang L Q. Saliency detection:a spectral residual approach. In:Proceedings of the 2007 IEEE International Conference on Computer Vision and Pattern Recognition. Minneapoils, USA:IEEE, 2007. 1-8 [9] [9] Achanta R, Hemami S, Estrada F, Ssstrunk S. Frequency-tuned salient region detection. In:Proceedings of the 2009 IEEE International Conference on Computer Vision and Pattern Recognition. Miami, USA:IEEE, 2009. 1597-1604 [10] Cheng M M, Zhang G X, Mitra N J, Huang X, Hu S M. Global contrast based salient region detection. In:Proceedings of the 2011 IEEE International Conference on Computer Vision and Pattern Recognition. Providence, USA:IEEE, 2011. 409-416 [11] Cheng M M, Jonathan W, Lin W Y, Zheng S, Vineet V, Crook N. Efficient salient region detection with soft image abstraction. In:Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney, Australia:IEEE, 2013. 1529-1536 [12] Shen X, Wu Y. A unified approach to salient object detection via low rank matrix recovery. In:Proceedings of the 2012 IEEE International Conference on Computer Vision and Pattern Recognition. Providence, USA:IEEE, 2012. 853-860 [13] Perazzi F, Krhenbhl P, Pritch Y, Hornung A. Saliency filters:contrast based filtering for salient region detection. In:Proceedings of the 2012 IEEE International Conference on Computer Vision and Pattern Recognition. Providence, USA:IEEE, 2012. 733-740 [14] Achanta R, Shaji A, Smith K. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282 [15] Margolin R, Tal A, Zelnik-Manor L. What makes a patch distinct? In:Proceedings of the 2013 IEEE International Conference on Computer Vision and Pattern Recognition. Sydney, Australia:IEEE, 2013. 1139-1146 [16] Wei Y C, Wen F, Zhu W J, Sun J. Geodesic saliency using background priors. In:Proceedings of the 2012 European Conference on Computer Vision. Florence, Italy:Springer, 2012. 29-42 [17] Goferman S, Zelnik-Manor L, Tal A. Content-aware saliency detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(10):1915-1926 [18] Borji A, Sihite D N, Itti L. Salient object detection:a benchmark. In:Proceedings of the 2012 European Conference on Computer Vision. Florence, Italy:Springer, 2012. 414-429 [19] Xie Y L, Lu H C, Yang M H. Bayesian saliency via low and mid level cues. IEEE Transactions on Image Processing, 2013, 22(5):1689-1698 [20] Alex B, Deselaers T, Ferrari V. Measuring the objectness of image windows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2189-2202 [21] Chang K Y, Liu T L, Chen H T, Lai S H. Fusing generic objectness and visual saliency for salient object detection. In:Proceedings of the 2011 IEEE International Conference on Computer Vision. Barcelona, Spain:IEEE, 2011. 914-921 [22] Bao L C, Song Y B, Yang Q X, Yuan H, Wang G. Tree filtering:efficient structure-preserving smoothing with a minimum spanning tree. IEEE Transactions on Image Processing, 2014, 23(2):555-569 [23] Vedaldi A, Soatto S. Quick shift and kernel methods for mode seeking. In:Proceedings of the 2008 European Conference on Computer Vision. Marseille, France:Springer, 2008. 705-718 [24] Frey B J, Dueck D. Clustering by passing message between data points. Science, 2007, 315(5814):972-976 [25] Xu D, Tang Z M, Xu W. Salient object detection based on regional contrast and relative spatial compactness. KSⅡ Transactions on Internet and Information Systems, 2013, 7(11):2737-2753 [26] Jiang B W, Zhang L H, Lu H C, Yang C, Yang M H. Saliency detection via absorbing Markov chain. In:Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney, Australia:IEEE, 2013. 1665-1672 [27] Jiang H Z, Wang J D, Yuan Z J, Liu T, Zheng N N, Li S P. Automatic salient object segmentation based on context and shape prior. In:Proceedings of the 2011 British Machine Vision Conference. Dundee, UK:BMVA, 2011.110.1-110.12 [28] Zhang L, Tong M H, Marks T K, Shan H, Cottrell G W. Sun:a Bayesian framework for saliency using natural statistics. Journal of Vision, 2008, 8(7):32.1-32. 20 [29] Harel J, Koch C, Perona P. Graph-based visual saliency. In:Proceedings of the 12th Conference on Neural Information Processing Systems. Vancouver, Canada:MIT, 2007. 545-552 [30] Zhai Y, Shah M. Visual attention detection in video sequences using spatiotemporal cues. In:Proceedings of the 14th ACM International Conference on Multimedia. Santa Barbara, USA:ACM, 2006. 815-824 [31] Ma Ru-Ning, Tu Xiao-Po, Ding Jun-Di, Yang Jing-Yu. To evaluate salience map towards popping out visual objects. Acta Automatica Sinica, 2012, 38(5):870-876(马儒宁, 涂小坡, 丁军娣, 杨静宇. 视觉显著性凸显目标的评价. 自动化学报, 2012, 38(5):870-876) [32] Li X, Li Y, Shen C H, Dick A, Van Den Hengel A. Contextual hypergraph modelling for salient object detection. In:Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney, Australia:IEEE, 2013. 3328-3335 [33] Guo Ying-Chun, Yuan Hao-Jie, Wu Peng. Image saliency detection based on local and regional features. Acta Automatica Sinica, 2013, 39(8):1214-1224(郭迎春, 袁浩杰, 吴鹏. 基于Local特征和Regional特征的图像显著性检测. 自动化学报, 2013, 39(8):1214-1224) [34] Jiang Xiao-Lian, Li Cui-Hua, Li Xiong-Zong. Saliency based tracking method for abrupt motions via two-stage sampling. Acta Automatica Sinica, 2014, 40(6):1098-1107(江晓莲, 李翠华, 李雄宗. 基于视觉显著性的两阶段采样突变目标跟踪算法. 自动化学报, 2014, 40(6):1098-1107) [35] Mai L, Niu Y Z, Liu F. Saliency aggregation:a data-driven approach. In:Proceedings of the 2013 IEEE International Conference on Computer Vision and Pattern Recognition. Sydney, Australia:IEEE, 2013. 1131-1138
点击查看大图
计量
- 文章访问数: 2096
- HTML全文浏览量: 80
- PDF下载量: 1815
- 被引次数: 0