[1]陈秋凤,申群太.局部自适应输入控制的随机游走抠图[J].智能系统学报,2019,14(05):1007-1016.[doi:10.11992/tis.201809014]
 CHEN Qiufeng,SHEN Quntai.Random-walk matting with local adaptive input control[J].CAAI Transactions on Intelligent Systems,2019,14(05):1007-1016.[doi:10.11992/tis.201809014]
点击复制

局部自适应输入控制的随机游走抠图(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年05期
页码:
1007-1016
栏目:
出版日期:
2019-09-05

文章信息/Info

Title:
Random-walk matting with local adaptive input control
作者:
陈秋凤12 申群太2
1. 福建农林大学 计算机与信息学院, 福建 福州 350002;
2. 中南大学 信息科学与工程学院, 湖南 长沙 410083
Author(s):
CHEN Qiufeng12 SHEN Quntai2
1. College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, China;
2. School of Information Science and Engineering, Central South University, Changsha 410083, China
关键词:
抠图视频抠图随机游走软性约束吸收概率局部模型输入控制自适应
Keywords:
mattingvideo mattingrandom walksoft constrainedabsorption probabilitylocal modelinput controladaptive control
分类号:
TP391
DOI:
10.11992/tis.201809014
摘要:
针对传统性抠图算法中,非完全正确用户标注及不精确超像素分割造成的信息误扩散,以随机游走算法为基础,提出带软性约束的抠图算法。通过对扩展Dirichlet问题的推导,指出带软约束的随机游走与部分自吸收随机游走概率的关联性。以吸收概率为指导,在传统相似扩散所构建的图模型上,根据局部窗口内特征矩阵的秩与方差设计了输入控制矩阵,使得信息扩散的过程能够跟随图像的局部特征进行自适应扩散。最后将软约束随机游走应用到单帧双层抠图及视频抠图中。实验表明,所提算法具有信息远距传播能力和良好的容错性能,尤其在用户标注不够充分的情况下能够取得更加优良的抠图结果。
Abstract:
In traditional image-matting algorithms, incomplete user labeling and inaccurate super-pixel segmentation lead to the incorrect propagation of information. To solve this problem, we propose the use of soft constrained matting based on a random-walk algorithm. Through the derivation of the extended Dirichlet problem, we identify the relationship between a random walk with soft constraint and the probability of a partial self-absorption random walk. Guided by the absorption probability, an input control matrix is designed according to the rank and variance of the feature matrix in the local window. This is performed via a graph model that was constructed using traditional similarity diffusion such that the process of information diffusion could follow the local image features to realize adaptive diffusion. Finally, we applied the soft constrained random walk to single-frame two-layer image and video matting. The experimental results reveal that the proposed algorithm can transmit information over long distances and has good fault tolerance. In addition, it can achieve better image matting results, particularly in cases wherein user labeling is insufficient.

参考文献/References:

[1] YAO Guilin, ZHAO Zhijie, LIU Shaohui. A comprehensive survey on sampling-based image matting[J]. Computer graphics forum, 2017, 36(8):613-628.
[2] ZHU Qingsong, SHAO Ling, LI Xuelong, et al. Targeting accurate object extraction from an image:a comprehensive study of natural image matting[J]. IEEE transactions on neural networks and learning systems, 2015, 26(2):185-207.
[3] KARACAN L, ERDEM A, ERDEM E. Alpha matting with KL-divergence-based sparse sampling[J]. IEEE transactions on image processing, 2017, 26(9):4523-4536.
[4] XU Ning, PRICE B, COHEN S, et al. Deep image matting[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA, 2017:311-320.
[5] SHI Yongfang, AU O C, PANG Jiahao, et al. Color clustering matting[C]//Proceedings of 2013 IEEE International Conference on Multimedia and Expo. San Jose, USA, 2013:1-6.
[6] JIN Meiguang, KIM B K, SONG W J. Adaptive propagation-based color-sampling for alpha matting[J]. IEEE transactions on circuits and systems for video technology, 2014, 24(7):1101-1110.
[7] HE Bei, WANG Guijin, ZHANG Cha. Iterative transductive learning for automatic image segmentation and matting with RGB-D data[J]. Journal of visual communication and image representation, 2014, 25(5):1031-1043.
[8] JOHNSON J, VARNOUSFADERANI E S. Sparse coding for alpha matting[J]. IEEE transactions on image processing, 2016, 25(7):3032-3043.
[9] LI Xuelong, LIU Kang, DONG Yongsheng, et al. Patch alignment manifold matting[J]. IEEE transactions on neural networks and learning systems, 2018, 29(7):3214-3226.
[10] LEVIN A, LISCHINSKI D, WEISS Y. A closed-form solution to natural image matting[J]. IEEE transactions on pattern analysis and machine intelligence, 2008, 30(2):228-242.
[11] ZHENG Yuanjie, KAMBHAMETTU C. Learning based digital matting[C]//Proceedings of the 12th International Conference on Computer Vision (ICCV). Kyoto, Japan, 2009:889-896.
[12] CHEN Qifeng, LI Dingzeyu, TANG C K. KNN matting[J]. IEEE transactions on pattern analysis and machine intelligence, 2013, 35(9):2175-2188.
[13] TSENG C Y, WANG S J. Learning-based hierarchical graph for unsupervised matting and foreground estimation[J]. IEEE transactions on image processing, 2014, 23(12):4941-4953.
[14] GONG Minglun, QIAN Yiming, CHENG Li. Integrated foreground segmentation and boundary matting for live videos[J]. IEEE transactions on image processing, 2015, 24(4):1356-1370.
[15] LEE S Y, YOON J C, LEE I K. Temporally coherent video matting[J]. Graphical models, 2010, 72(3):25-33.
[16] SHAHRIAN E, PRICE B, COHEN S, et al. Temporally coherent and spatially accurate video matting[J]. Computer graphics forum, 2014, 33(2):381-390.
[17] LI Dingzeyu, CHEN Qifeng, TANG C K. Motion-aware KNN Laplacian for video matting[C]//Proceedings of 2013 IEEE International Conference on Computer Vision (ICCV). Sydney, Australia, 2013:3599-3606.
[18] SINDEEV M, KONUSHIN A, ROTHER C. Alpha-flow for video matting[C]//Proceedings of the 11th Asian Conference on Computer Vision. Daejeon, Korea, 2012:438-452.
[19] CHO D, KIM S, TAI Y W, et al. Automatic trimap generation and consistent matting for light-field images[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(8):1504-1517.
[20] CHO H W, CHO Y R, SONG W J, et al. Image matting for automatic target recognition[J]. IEEE transactions on aerospace and electronic systems, 2017, 53(5):2233-2250.
[21] GRADY L. Random walks for image segmentation[J]. IEEE transactions on pattern analysis and machine intelligence, 2006, 28(10):1768-1783.
[22] WU Xiaoming, LI Zhenguo, SO A M C, et al. Learning with partially absorbing random walks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS). Lake Tahoe, USA, 2012:3077-3085.
[23] SINGARAJU D, ROTHER C, RHEMANN C. New appearance models for natural image matting[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Miami Beach, USA, 2009:659-666.
[24] ACHANTA R, SHAJI A, SMITH K, et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE transactions on pattern analysis and machine intelligence, 2012, 34(11):2274-2282.
[25] MUJA M, LOWE D G. Fast approximate nearest neighbors with automatic algorithm configuration[C]//Proceedings of the International Conference on Computer Vision Theory and Applications. Lisbon, Portugal, 2009:331-340.
[26] BAKER S, SCHARSTEIN D, LEWIS J P, et al. A database and evaluation methodology for optical flow[J]. International journal of computer vision, 2011, 92(1):1-31.
[27] BROX T, BRUHN A, PAPENBERG N, et al. High accuracy optical flow estimation based on a theory for warping[C]//Proceedings of the 8th European Conference on Computer Vision (ECCV). Prague, Czech Republic, 2004:25-36.
[28] RHEMANN C, ROTHER C, WANG Jue, et al. A perceptually motivated online benchmark for image matting[EB/OL].(2009-06)[2018-09-11] http://www.alphamatting.com/.
[29] CHUANG Y Y, AGARWALA A, CURLESS B, et al. Video matting of complex scenes[EB/OL]. (2002-07)[2018-09-11] http://grail.cs.washington.edu/projects/digital-matting/video-matting/.

备注/Memo

备注/Memo:
收稿日期:2018-09-11。
基金项目:国家自然科学基金项目(61473318,60974048).
作者简介:陈秋凤,女,1983年生,讲师,博士,主要研究方向为图像处理、智能控制。发表学术论文12篇;申群太,男,1944年生,教授,博士生导师,主要研究方向为人工智能、工业控制。曾获湖南省科技进步三等奖及国家科技进步二等奖、湖南省技术创新先进个人。发表学术论文200余篇。
通讯作者:陈秋凤.E-mail:chenqiufeng0204@126.com
更新日期/Last Update: 1900-01-01