计算机科学 ›› 2017, Vol. 44 ›› Issue (5): 308-313.doi: 10.11896/j.issn.1002-137X.2017.05.057
李青,袁家政,刘宏哲
LI Qing, YUAN Jia-zheng and LIU Hong-zhe
摘要： 提出了一种基于目标识别与显著性检测的图像场景多对象分割方法。该方法的步骤包括:在图像训练集上训练语义对象的检测器,用来检测输入图像中对象的位置,标定对象的包围盒；对输入的图像进行过分割处理,得到超像素集合,根据包围盒的位置和超像素的语义概率值计算兴趣区域；在3种稠密尺度上进行场景显著性检测,得到输入图像的显著图；在兴趣区域内计算超像素的邻接关系,形成邻接矩阵,构建条件随机场模型,将多对象分割问题转化成多类别标记问题,每一个对象是一种类别；以每个超像素作为场模型的节点,超像素的邻接关系对应场模型中节点之间的连接关系,将显著性和图像特征转化为节点和边的权重值；利用图割算法,在条件随机场模型上进行优化,迭代终止时得到像素的对象标记结果,从而实现对多个对象的分割。实验结果表明该方法效果较好。
| [1] SHOTTON J,WINN J M,ROTHER C,et al.Textonboost for image understanding:Multi-class object recognition and segmentation by jointly modeling texture,layout,and context[J].International Journal of Computer Vision,2009,1(1):2-23. [2] XIAO J,QUAN L.Multiple view semantic segmentation forstreet view images [C]∥The 12th International Conference on Computer Vision.2009:686-693. [3] YAO J,FIDLER S,URTASUN R.Describing the scene as a whole:Joint object detection,scene classification and semantic segmentation [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2012:702-709. [4] REN X,BO L,FOX D.RGB-(D) scene labeling:Features andalgorithms [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2012:2759-2766. [5] LIU C,YUEN J,TORRALBA A.Nonparametric scene parsing:Label transfer via dense scene alignment [C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2009:1972-1979. [6] ZHANG H,XIAO J,QUAN L.Supervised label transfer for semantic segmentation of street scenes [C]∥Proceedings of European conference on Computer Vision.2010:561-574. [7] TIGHE J,LAZEBNIK S.Superparsing:Scalable nonparametric image parsing with superpixels [C]∥Proceedings of European Conference on Computer Vision.2010:352-365. [8] CHEN X,LI Q,SONG Y,et al.Supervised geodesic propagation for semantic label transfer[C]∥Proceedings of European conference on Computer Vision.2012:553-565. [9] ZHANG H,FANG T,CHEN X,et al.Partial similarity basednonparametric scene parsing in certain environment [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2011:2241-2248. [10] PRICE B L,MORSE B S,COHEN S.Geodesic graph cut for interactive image segmentation [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2010:3161-3168. [11] WU J,ZHAO Y,ZHU J,et al.Milcut:A sweeping line multiple instance learning paradigm for interactive image segmentation [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2014:256-263. [12] ROTHER C,MINKA T P,BLAKE A,et al.Cosegmentation of image pairs by histogram matching-incorporating a global constraint into mrfs [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2006:993-1000. [13] VICENTE S,KOLMOGOROV V,ROTHER C.Cosegmenta-tion revisited:Models and optimization [C]∥11th European Conference on Computer Vision.2010:465-479. [14] VICENTE S,ROTHER C,KOLMOGOROV V.Object coseg-mentation [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2011:2217-2224. [15] BATRA D,KOWDLE A,PARIKH D,et al.Interactively co-segmentating topically related images with intelligent scribble guidance [J].International Journal of Computer Vision,2011,93(3):273-292. [16] BAI X,WANG J,SAPIRO G.Dynamic Color Flow:A Motion-Adaptive Color Model for Object Segmentation in Video[C]∥Proceedings of European Conference on Computer Vision.2010:617-630. [17] BAI X,WANG J,SAPIRO G.Towards temporally-coherent video matting[C]∥International Conference on Computer Vision/Graphics Collaboration Techniques and Applications.Mirage 2011:63-74. [18] HE X,GOULD S.An exemplar-based CRF for multi-instanceobject segmentation [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2014:296-303. [19] TIGHE J,LAZEBNIK S.Finding things:Image parsing with regions and per-exemplar detectors [C]∥IEEE Conference on Computer Vision and Pattern Recognition.2013:3001-3008. [20] MALISIEWICZ T,GUPTA A,EFROS A A.Ensemble of exemplar-SVMs for object detection and beyond[C]∥IEEE International Conference on Computer Vision.2011:89-96. [21] ARBELAEZ P,MAIRE M,FOWLKES C,et al.Contour Detection and Hierarchical Image Segmentation[J] IEEE TPAMI,2011,3(5):898-916. [22] GOFERMAN S,ZELNIK-MANOR L,TAL A.Context-Aware Saliency Detection[J].IEEE Trans.Pattern Anal.Mach.Intell.,2012,4(10):1915-1926. [23] CHENG M,MITRA N J,HUANG X,et al.Global Contrast Based Salient Region Detection[J].IEEE Trans.Pattern Anal.Mach.Intell.,2015,7(3):569-582. [24] BOYKOV Y,VEKSLER O,ZABIH R.Efficient ApproximateEnergy Minimization via Graph Cuts[J].IEEE TPAMI,2001,20(12):1222-1239. [25] BOYKOV Y,KOLMOGOROV V.An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision[J].IEEE TPAMI,2004,26(9):1124-1137. |
| No related articles found! |
|
||
首页