基于稀疏恢复与优化的显著性目标检测算法

doi:10.11896/j.issn.1002-137X.2018.08.046

计算机科学 ›› 2018, Vol. 45 ›› Issue (8): 258-263.doi: 10.11896/j.issn.1002-137X.2018.08.046

基于稀疏恢复与优化的显著性目标检测算法

王军¹, 吴泽民¹, 杨巍², 胡磊¹, 张兆丰³, 姜青竹⁴

中国人民解放军陆军工程大学通信工程学院南京210007¹
中船重工集团公司第七二二研究所武汉 430079²
中国人民解放军61428部队北京100071³
中国人民解放军95980部队湖北襄阳442101⁴

收稿日期:2017-10-19 出版日期:2018-08-29 发布日期:2018-08-29
作者简介:王军(1995-),男,硕士生,主要研究方向为图像与视频的显著性检测; 吴泽民(1973-),男,博士,副教授,主要研究方向为信息融合、图像处理,E-mail:wuzemin_ice@163.com(通信作者); 杨巍(1983-),男,博士,主要研究方向为数据链消息处理; 胡磊(1987-),男,博士,讲师,主要研究方向为压缩感知、目标跟踪; 张兆丰(1991-),男,硕士,主要研究方向为图像处理; 姜青竹(1987-),男,硕士,主要研究方向为视频传输保障。

Salient Object Detection Algorithm Based on Sparse Recovery and Optimization

WANG Jun¹, WU Ze-min¹, YANG Wei², HU Lei¹, ZHANG Zhao-feng³, JIANG Qing-zhu⁴

College of Communications Engineering,Army Engineering University of PLA,Nanjing 210007,China¹
No.722 Research Institute,China Shipbuilding Industry Corporation,Wuhan 430079,China²
The 61428th Troops of the PLA,Beijing 100071,China³
The 95980th Troops of the PLA,Xiangyang,Hubei 442101,China⁴

Received:2017-10-19 Online:2018-08-29 Published:2018-08-29

摘要/Abstract

摘要： 针对目前基于稀疏表示的显著性检测算法中存在的边界显著性检测不足、字典表达能力不够等问题,提出一种基于稀疏恢复与优化的检测算法。首先对图像进行滤波平滑和超像素分割,并从边界与内部超像素中挑选可靠的背景种子构建稀疏字典;然后基于该字典对整幅图像进行稀疏恢复,根据稀疏恢复误差生成初始显著图;再运用改进的基于聚类的二次优化模型对初始显著图进行优化;最后经过多尺度融合得到最终显著图。在三大公开测试数据集上的实验结果表明,所提算法能够保持高效快速、无训练等优点,同时性能优于目前主流的非训练类算法,在处理边界显著性方面表现优异,具有较强的鲁棒性。

关键词: 稀疏恢复, 显著性检测, 显著性优化

Abstract: In view of the issues of boundary ambiguity and low detection accuracy in current saliency detection algorithms which employ sparse representation,this paper proposed a new saliency detection algorithm based on sparse recovery and optimization.Firstly,the RG filter is used to smooth the image.Then,the SLIC algorithm is used to segment the image,and the reliable background seed is selected from the boundary and the inside super pixel block is chosen to construct the dictionary.Based on the dictionary,the sparse recovery of the whole image is achieved,and the initial sa-liency map is generated according to the sparse recovery error.After that,the modified optimization model is used to optimize the initial saliency map.Finally,the final saliency map is obtained through multiscale fusion.Experimental results on three public benchmark datasets show that the performance of the proposed algorithm is superior to the current state-of-the-art methods.Meanwhile,it performs well in dealing with boundary saliency and has strong robustness.

Key words: Saliency detection, Saliency optimization, Sparse recovery

中图分类号:

TP393

王军, 吴泽民, 杨巍, 胡磊, 张兆丰, 姜青竹. 基于稀疏恢复与优化的显著性目标检测算法[J]. 计算机科学, 2018, 45(8): 258-263. https://doi.org/10.11896/j.issn.1002-137X.2018.08.046

WANG Jun, WU Ze-min, YANG Wei, HU Lei, ZHANG Zhao-feng, JIANG Qing-zhu. Salient Object Detection Algorithm Based on Sparse Recovery and Optimization[J]. Computer Science, 2018, 45(8): 258-263. https://doi.org/10.11896/j.issn.1002-137X.2018.08.046

参考文献

[1]RENSINK R,O’ REGAN K,CLARK J.To see or not to see:The need for attention to perceive changes in scene[J].Psychological Science,1997,8(5):368-373.
[2]DONOSER M,URSCHLER M,HIRZER M,et al.Saliencydriven total variation segmentation[C]∥IEEE International Conference on Computer Vision(ICCV).Xi’an,China,2009:817-824.
[3]GAO Y,SHI M,DACHENG T F,et al.Database saliency for fast image retrieval[J].IEEE Transactions on Multimedia,2015,17(3):359-369.
[4]RUTISHAUSER U,WALTHER D,KOCH C,et al.Is bottom-up attention useful for object recognition?[C]∥IEEE Confe-rence on Computer Vision and Pattern Recognition (CVPR).Washington DC,USA:IEEE,2004:37-44.
[5]SHARMA G,JURIE F,SCHMID C.Discriminative spatial sa-liency for image classification[C]∥IEEE Conference on Compu-ter Vision and Pattern Recognition (CVPR).Rhode Island,USA,2012:3506-3513.
[6]HADIZADEH H,BAJI’C I.Saliency-aware video compression[J].IEEE Transactions on Image Processing,2014,23(1):19-33.
[7]ITTI L,KOCH C,NIEBUR E.A model of saliency-based visual attention for rapid scene analysis[J].IEEE Trans.on Pattern Analysis and Machine Itelligence,1998,20(11):1254-1259.
[8]MA Y,ZHANG H.Contrast-based image attention analysis by using fuzzy growing[C]∥Proceedings of ACM Multimedia.2003:374-379.
[9]ZHAI Y,SHAH M.Visual attention detection in video se-quences using spatiotemporal cues[C]∥Proceedings of ACM Multimedia.2006:815-824.
[10]HAREL J,KOCH C,PERONA P.Graph-based visual saliency[C]∥Proceedings of Neural Information Processing Systems.2006:545-552.
[11]HOU X,ZHANG L.Saliency detection:a spectral residual approach[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Portland,USA,2007:801-808.
[12]LIU T,SUN J,ZHENG N,et al.Learning to detect a salient object[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Minneapolis,USA,2007:1-8.
[13]HOU X,ZHANG L.Dynamic visual attention:Searching forcoding length increments[J].Advances in Neural Processing System,2008,21:681-688.
[14]LAI J,MAI X.Saliency detection:Image Saliency detection with sparse representation of learnt texture atoms[C]∥IEEE International Conference on Computer Vision Workshop.2015.
[15]BORJI A,ITTI L.Exploiting Local and Global Patch Rarities for Saliency Detection[C]∥Proceeding of IEEE Conference on Computer Vision and Patter Recognition.2012:478-485.
[16]LI Y,ZHOU Y,XU L,et al.Incremental sparse saliency detection[C]∥Proceedings of IEEE International Conference on Ima-ge Processing.2009:3093-3096.
[17]HAN B,ZHU H,DING Y D.Bottom-up Saliency based onweighted sparse coding residual[C]∥Proceeding of ACM International Conference on Multimedia.2011:1117-1120.
[18]LI X,LU H,ZHANG X.et al.Saliency detection via dense and sparse reconstruction[C]∥IEEE International Conference on Computer Vision.2013:2976-2983.
[19]JIA C,QI J,LI X,et al.Saliency detection via a unified generative and discriminative model[J].Neurocomputing,2016,173(P2):406-417.
[20]WANG J,LU H,TONG N,et al.Saliency Detection via Background and Foreground Seed Selection[J].Neurocomputing,2015,152(C):359-268.
[21]ZHU W,LIANG S,WEI Y,et al.Saliency optimization from robust background detection[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Columbus,USA:IEEE,2014:2814-2821.
[22]LU S,MAHADEVAN V,VASCONCELOS N.Learning Optimal Seeds for Diffusion-Based Salient Object Detection[C]∥Computer Vision and Pattern Recognition.IEEE,2014:2790-2797.
[23]ACHANTA R,SHAJI A,SMITH K,et al.Slic superpixelscompared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2281.
[24]ZHANG Q,SHEN X,XU L,et al.Rolling Guidance Filter[M]∥Computer Vision-ECCV 2014.2014:815-830.
[25]TIBSHIRANI R.Regression shrinkage and selection via the lasso:A retrospective[J].Journal of the Royal Statistical Society,2011,73(3):267-288.
[26]LU S,MAHADEVAN V,VASCONCELOS N.Learning Optimal Seeds for Diffusion-Based Salient Object Detection[C]∥Computer Vision and Pattern Recognition.IEEE,2014:2790-2797.
[27]MARGOLIN R,TAL A,ZELNIK-MANOR L.What makes a patch distinct?[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Portland,USA,2013:1139-1146.
[28]SHEN X,WU Y.A Unified Approach to Salient Object Detection via Low Rank Matrix Recovery[J].Computer Vision and Pattern Recognition,2012,23(10):853-860.
[29]YAN J,ZHU M,LIU H,et al.Visual Saliency Detection viaSparse Pursuit[J].IEEE Signal Processing Letters,2010,17(8):739-742.
[30]QIN Y,LU H,XU Y,et al.Saliency detection viacellular au-tomata[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston,USA,2015:111-119.
[31]KIM T H,LEE K M,SANG U L.Learning Full Pairwise Affi-nities for Spectral Segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(7):1690-1703.
[32]ACHANTA R,HEMAMI S,ESTRADA F,et al.Frequency-tuned salient region detection[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Miami,USA:IEEE,2009:1597-1604.
[33]LIU T,SUN J,ZHENG N,et al.Learning to detect a salient object[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(2):353-367.
[34]ALPERT S,GALUN M,BRANDT A,et al.Image segmenta-tion by probabilistic bottom-up aggregation and cue integration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):315-327.
[35]LI G,YU Y.Visual Saliency Detection Based on Multiscale Deep CNN Features[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2016,25(11):5012-5024.
[36]LI G,YU Y.Deep Contrast Learning for Salient Object Detection[C]∥Computer Vision and Pattern Recognition.IEEE,2016:478-487.
[37]LIU N,HAN J.DHSNet:Deep Hierarchical Saliency Network for Salient Object Detection[C]∥Computer Vision and Pattern Recognition.IEEE,2016:678-686.
[38]ZHANG P,WANG D,LU H,et al.Amulet:Aggregating Multi-level Convolutional Features for Salient Object Detection[J].eprint arXiv:1708.02001.
[39]GOPALAKRISHNAN V,HU Y,RAJAN D.Random Walks onGraphs for Salient Object Detection in Images[J].IEEE Tran-sactions on Image Processing A Publication of the IEEE Signal Processing Society,2010,19(12):3232-3242.
[40]YANG C,ZHANG L,LU H,et al.Saliency Detection via Graph-Based Manifold Ranking[C]∥Computer Vision and Pattern Recognition.IEEE,2013:3166-3173.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于稀疏恢复与优化的显著性目标检测算法

Salient Object Detection Algorithm Based on Sparse Recovery and Optimization

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

Metrics

本文评价

推荐阅读 0

[1]	刘翔宇, 蹇木伟, 鲁祥伟, 何为凯, 李晓峰, 尹义龙. 基于眼动点视觉先验与边缘优化的显著性检测 Saliency Detection Based on Eye Fixation Prediction and Boundary Optimization 计算机科学, 2021, 48(6A): 107-112. https://doi.org/10.11896/jsjkx.201100116
[2]	王教金, 蹇木伟, 刘翔宇, 林培光, 耿蕾蕾, 崔超然, 尹义龙. 基于3D全时序卷积神经网络的视频显著性检测 Video Saliency Detection Based on 3D Full ConvLSTM Neural Network 计算机科学, 2020, 47(8): 195-201. https://doi.org/10.11896/jsjkx.190600148
[3]	袁野, 和晓歌, 朱定坤, 王富利, 谢浩然, 汪俊, 魏明强, 郭延文. 视觉图像显著性检测综述 Survey of Visual Image Saliency Detection 计算机科学, 2020, 47(7): 84-91. https://doi.org/10.11896/jsjkx.190900006
[4]	温静, 李雨萌. 基于多尺度反卷积深度学习的显著性检测 Salient Object Detection Based on Multi-scale Deconvolution Deep Learning 计算机科学, 2020, 47(11): 179-185. https://doi.org/10.11896/jsjkx.190900008
[5]	鲁文超, 段先华, 徐丹, 王万耀. 基于多尺度下凸包改进的贝叶斯模型显著性检测算法 Bayesian Model Saliency Detection Algorithm Based on Multiple Scales and Improved Convex Hull 计算机科学, 2019, 46(6): 295-300. https://doi.org/10.11896/j.issn.1002-137X.2019.06.044
[6]	张兆丰,吴泽民,姜青竹,杜麟,胡磊. 基于超像素匹配的图像协同显著性检测 Co-saliency Detection via Superpixel Matching 计算机科学, 2017, 44(11): 314-319. https://doi.org/10.11896/j.issn.1002-137X.2017.11.048
[7]	许肖,顾磊. 结合显著性检测和中心分割算法的文本检测方法 Saliency Text Detection Combining Graph-based Manifold Ranking with C entral Segmentation 计算机科学, 2016, 43(4): 313-317. https://doi.org/10.11896/j.issn.1002-137X.2016.04.064
[8]	周静波,任永峰,严云洋. 基于视觉显著性的非监督图像分割 Unsupervised Image Segmentation Based on Saliency Detection 计算机科学, 2015, 42(8): 52-55.
[9]	周培云,李静,沈宁敏,庄毅. BSFCoS:基于分块与稀疏主特征提取的快速协同显著性检测 BSFCoS:Fast Co-saliency Detection Based on Block and Sparse Principal Feature Extraction 计算机科学, 2015, 42(8): 305-309.
[10]	樊强,齐春. 基于全局和局部短期稀疏表示的显著性检测 Saliency Detection Based on Global and Local Short-term Sparse Representation 计算机科学, 2014, 41(10): 80-83. https://doi.org/10.11896/j.issn.1002-137X.2014.10.018