RGBD Image Co-segmentation via Saliency Detection and Graph Cut

doi:10.16182/j.issn1004731x.joss.201807016

Abstract

Abstract: In order to solve the problem that it is difficult to accurately segment images with similar colors in the foreground, we propose a RGBD image co-segmentation algorithm that utilizes saliency detection and graph cut. Our algorithm not only achieves the co-segmentation of multiple images, but also uses depth data to solve the foreground and background confusion problem caused by color similarity. Depth is incorporated into a superpixel segmentation algorithm to change each RGBD image into a set of superpixel blocks. A graph model of superpixels is constructed and saliency detection is used to extend the seed nodes area. The co-segmentation is achieved based on the Biased Normalized Cuts. Depth information is used to further optimize the segmentation results. Extensive experiments show that our method can significantly improve the accuracy of segmentation for those scenes with similar foreground and background colors.

Key words: co-segmentation, depth, saliency detection, superpixel, graph cut

CLC Number:

TN911.73

Li Xiaoyang, Wan Lili, Li Henan, Wang Shenghui. RGBD Image Co-segmentation via Saliency Detection and Graph Cut[J]. Journal of System Simulation, 2018, 30(7): 2558-2567.

References

[1] 秦绪佳, 陈新鸿, 吴正强, 等. 基于Canny算子的水平集数字虚拟人图像分割算法[J]. 系统仿真学报, 2010, 22(7): 1674-1677.
QIN Xujia, CHEN Xinhong, WU Zhengqiang, et al.Level Set Digital Virtual Human Image Segmentation Algorithm Based on Canny Operator[J]. Journal of System Simulation, 2010, 22(7): 1674-1677.
[2] Rother C, Minka T, Blake A, et al.Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs[C]// IEEE Computer Vision and Pattern Recognition, Los Alamitos: IEEE Computer Society Press, 2006: 993-1000.
[3] Hochbaum D S, Singh V.An efficient algorithm for Cosegmentation[C]//2010 IEEE International Conference on Computer Vision. New York: IEEE, 2010: 269-276.
[4] Joulin A, Bach F, Ponce J.Discriminative clustering for image co-segmentation[C]//2010 IEEE Computer Vision and Pattern Recognition, Los Alamitos: IEEE Computer Society Press, 2010: 1943-1950.
[5] Batra D, Kowdle A, Parikh D, et al.iCoseg: Interactive co-segmentation with intelligent scribble guidance[C]// 2010 IEEE Computer Vision and Pattern Recognition, Los Alamitos: IEEE Computer Society Press, 2010: 3169-3176.
[6] 刘松涛, 殷福亮. 基于图割的图像分割方法及其新进展[J]. 自动化学报, 2012, 38(6): 911-922.
LIU Songtao, YIN Fuliang.Image Segmentation Method Based on Graph Cut and Its New Progress[J]. Acta Automatica Sinica, 2012, 38(6): 911-922.
[7] 栾悉道, 谢毓湘, 张芯, 等. 融合多特征的运动目标特征提取方法[J]. 系统仿真学报, 2017, 29(6): 1304-1310.
LUAN Xidao, XIE Yuxiang, Zhang Xin, et al.Multi-feature fusion of moving target feature extraction method[J]. Journal of System Simulation, 2017, 29(6): 1304-1310.
[8] Collins M D, Xu J, Grady L, et al.Random walks based multi-image segmentation: Quasiconvexity results and GPU-based solutions[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition, New York: IEEE, 2012: 1656-1663.
[9] Liang Q, Miao Z.Local spectral method to seeded image cosegmentation[J]. Journal of Electronic Imaging (S1017-9909), 2014, 23(2): 1709-1717.
[10] Maji S, Vishnoi N K, Malik J.Biased normalized cuts[C]//2011 IEEE Computer Vision and Pattern Recognition, New York: IEEE, 2011: 2057-2064.
[11] 余烨, 李冰飞, 张小魏, 等. 面向RGBD图像的标记分水岭分割[J]. 中国图象图形学报, 2016, 21(2): 145-154.
YU Ye, LI Bing-fei, ZHANG Xiao-wei, et al.Marking watershed segmentation for RGBD images[J]. Journal of Image and Graphics, 2016, 21(2): 145-154.
[12] Mishra A K, Shrivastava A, Aloimonos Y.Segmenting “simple” objects using RGB-D[C]//2012 IEEE International Conference on Robotics and Automation, New York: IEEE, 2012: 4406-4413.
[13] Hickson S, Birchfield S, Essa I, et al.Efficient Hierarchical Graph-Based Segmentation of RGBD Videos[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition, New York: IEEE, 2014: 344-351.
[14] Achanta R, Shaji A, Smith K, et al.SLIC Superpixels Compared to State-of-the-Art Superpixel Methods[J]. 2012 IEEE Transactions on Pattern Analysis & Machine Intelligence (S0162-8828), 2012, 34(11): 2274.
[15] Weikersdorfer D, Gossow D, Beetz M.Depth-adaptive superpixels[C]//2012 IEEE International Conference on Pattern Recognition, New York: IEEE, 2012: 2087-2090.
[16] Y Cheng, H Fu, X Wei, et al.Depth enhanced saliency detectionmethod[C]. Proceedings of International Conference on Internet Multimedia Computing and Service, 2014: 23-28.
[17] 刘毅, 黄兵, 孙怀江, 等. 利用视觉显著性与图割的图像分割算法[J]. 计算机辅助设计与图形学学报, 2013, 25(3): 402-409.
LIU Yi, HUANG Bing, SUN Huaijiang, et al.Image segmentation algorithm using visual saliency and graph cut[J]. Computer Assisted Design and Graphics, 2013, 25(3): 402-409.
[18] Levinshtein A, Stere A, Kutulakos K N, et al.TurboPixels: Fast Superpixels Using Geometric Flows[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence (S0162-8828), 2009, 31(12): 2290-2297.
[19] Geng Y.Leveraging stereopsis for saliency analysis[C]// 2012 IEEE Computer Vision and Pattern Recognition, New York: IEEE, 2009: 269-276.
[20] Shi J, Malik J.Normalized Cuts and Image Segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence (S0162-8828), 2000, 22(8): 888-905.
[21] Mahoney M W, Orecchia L, Vishnoi N K.A local spectral method for graphs: with applications to improving graph partitions and exploring data graphs locally[J]. Journal of Machine Learning Research(S1532-4435), 2012, 13(1): 2339-2365.
[22] Choi S, Zhou Q Y, Miller S, et al. A Large Dataset of Object Scans[OL]. arXiv:1602.02481, 2016.
[23] Dakua S P, Abi-Nahed J.Patient oriented graph-based image seg-mentation[J]. Biomedical Signal Processing & Control (S1746-8094), 2013, 8(3): 325-332.
[24] Li J, Levine M D, An X, et al.Visual saliency based on scale-space analysis in the frequency domain[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence (S0162-8828), 2013, 35(4): 996-1010.