计算机科学 ›› 2018, Vol. 45 ›› Issue (10): 272-275.doi: 10.11896/j.issn.1002-137X.2018.10.050

• 图形图像与模式识别 • 上一篇    下一篇

基于被包围状态和马尔可夫模型的显著性检测

陈炳才1,2, 王西宝1, 余超1, 年梅2, 陶鑫1, 潘伟民2, 卢志茂1   

  1. 大连理工大学电子信息与电气工程学部 辽宁 大连116024 1
    新疆师范大学计算机科学技术学院 乌鲁木齐830054 2
  • 收稿日期:2017-09-05 出版日期:2018-11-05 发布日期:2018-11-05
  • 作者简介:陈炳才(1978-),男,博士,副教授,主要研究方向为图像处理、无线通信与网络,E-mail:china@dlut.edu.cn(通信作者);王西宝(1991-),男,硕士生,主要研究方向为图像处理;余 超(1985-),男,博士,副教授,主要研究方向为人工智能;年 梅(1971-),女,博士,教授,主要研究方向为图像处理、数据挖掘;陶 鑫(1992-),男,硕士生,主要研究方向为图像处理;潘伟民(1963-),男,教授,主要研究方向为数据挖掘。
  • 基金资助:
    国家自然科学基金项目(61771089),新疆师范大学校级重点学科招标课题(17SDKD1201)资助

Saliency Detection Based on Surroundedness and Markov Model

CHEN Bing-cai1,2, WANG Xi-bao1, YU Chao1, NIAN Mei2, TAO Xin1, PAN Wei-min2, LU Zhi-mao1   

  1. Faculty of Electronic Information and Electrical Engineering,Dalian University of Technology,Dalian,Liaoning 116024,China 1
    College of Computer Science and Technology,Xinjiang Normal University,Urumqi 830054,China 2
  • Received:2017-09-05 Online:2018-11-05 Published:2018-11-05

摘要: 针对图像显著性检测问题,提出一种利用被包围状态和马尔可夫模型进行图像显著性检测的方法。首先,利用被包围状态计算显著性物体的大致区域;其次,使用简单线性迭代聚类(SLIC)算法对原始图像进行处理,得到图像的超像素图,并基于超像素图建立图像的图模型;接着,将距离显著性物体大致区域最远的两条边界的超像素作为虚拟背景吸收节点,利用吸收马尔可夫链计算每个超像素的显著性值,检测出初始的显著图S1;再以计算出的显著性物体大致区域中的超像素作为虚拟前景吸收节点,利用吸收马尔可夫链检测出初始的显著性图S2;然后,融合S1S2得到最终的显著图S;最后,利用引导滤波器对显著图S进行平滑处理得到更优的显著图。在两个数据库上的实验结果表明,提出的算法优于现有大多数算法。

关键词: 背景先验, 被包围状态, 马尔可夫模型, 前景先验, 显著物体检测

Abstract: Aiming at solving the problem of saliency detection,this paper proposed a saliency detection algorithm based on surrouuundedness and markov model.Firstly,the surroundedness is used to predict the approximate region of the salient object for eye fixation.Secondly,a simple linear iterative clustering (SLIC) algorithm is used to process the ori-ginal image,and the graph model of the image is established based on the superpixels.Next,the superpixels of the two boundaries that are the furthest from the approximate region of the salient object are taken as the virtual background absorb nodes,the saliency value of each superpixel is calculated by the absorption Markov chain,and the initial saliency map S1 is detected.Then,superpixels in the approximate region of the salient object is used as the virtual foreground absorption nodes,and the initial saliency map S2 is detected by the absorption Markov chain.Then S1 and S2 are fused to get the final saliency map S.Finally,the guided filter is used to smooth the saliency maps and get a better saliency map.Experimental results based on two public datasets demonstrate that the proposed algorithm outperforms many state-of-the-art methods.

Key words: Background prior, Foreground prior, Markov model, Saliency object detection, Surroundedness

中图分类号: 

  • TP391
[1]BORJI A,CHENG M M,JIANG H Z,et al.Salient Object Detection:A Benchmark[J].IEEE Transactions on Image Proces-sing,2015,24(12):5706-5722.
[2]XIE Y L,LU H C,YANG M S.Bayesian saliency via low and mid level cues[J].IEEE Transactions on Image Processing,2013,22(5):1689-1698.
[3]SUN J G,LU H C,LIU X P.Saliency Region Detection Based on Markov Absorption Probabilities[J].IEEE Transactions on Image Processing,2015,24(5):1639-1649.
[4]TONG N,LU H C,ZHANG Y,et al.Salient object detection via global and local cues[J].Pattern Recognition,2015,48(10):3258-3267.
[5]ALEXE B,DESELAERS T,FERRARI V.What is an object? [C]∥Computer Vision and Pattern Recognition.San Francisco,CA,USA,2010:73-80.
[6]LI G B,YU Y Z.Visual Saliency Detection Based on Multiscale Deep CNN Features[J].IEEE Transactions on Image Proces-sing, 2016,25(11):5012-5024.
[7]LU H C,TONG N,ZHANG X N,et al.Co-bootstrapping Sa- liency[J].IEEE Transactions on Image Processing, 2016,25(11):5012-5024.
[8]FU K R,GU H,YANG J.Saliency Detection by Fully Learning a Continuous Conditional Random Field[J].IEEE Transactions on Multimedia,2017,19(7):1531-1544.
[9]LU H C,LI X H,ZHANG L H,et al.Dense and Sparse Recon- struction Error Based Saliency Descriptor[J].IEEE Transactions on Image Processing,2016,25(4):1592-1603.
[10]YANG C,ZHANG L H,LU H C,et al.Saliency Detection via Graph-Based Manifold Ranking[C]∥Computer Vision and Pattern Recognition.Portland,Oregon,2013:3166-3173.
[11]ZHANG J M,SCLAROFF S.Exploiting Surroundedness for Saliency Detection:A Boolean Map Approach [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(5):889-902.
[12]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.
[13]HE K M,SUN J,TANG X O.Guided image filtering [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[14]TOMASI C,MANDUCHI R.Bilateral filtering for gray and co- lor images [C]∥IEEE International Conference on Computer Vision.1998:839-846.
[15]SHI J P,YAN Q,XU L,et al.Hierarchical image saliency detection on Extended CSSD [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(4):717-729.
[16]ACHANTA R,HEMAMI S S,ESTRADA F J,et al.Frequency-tuned salient region detection [C]∥IEEE Conference on Computer Vision and Pattern Recognition.Miami,Florida,USA,2009:1597-1604.
[17]TONG N,LU H C,ZHANG L H,et al.Saliency detection with multi-scale superpixels [J].IEEE Signal Processing Letters,2014,21(9):1035-1039.
[18]YAN Q,XU L,SHI J P,et al.Hierarchical Saliency Detection[C]∥Computer Vision and Pattern Recognition.Portland,Oregon,2013:1155-1162.
[19]ZHU W J,LIANG S,WEI Y C,et al.Saliency Optimization from Robust Background Detection[C]∥Computer Vision and Pattern Recognition.Columbus,OH,USA,2014:2814-2821.
[1] 费星瑞, 谢逸.
基于HMM-NN的用户点击流识别
Click Streams Recognition for Web Users Based on HMM-NN
计算机科学, 2022, 49(7): 340-349. https://doi.org/10.11896/jsjkx.210600127
[2] 王欣, 向明月, 李思颖, 赵若成.
基于隐马尔可夫模型的铁路出行团体关系预测研究
Relation Prediction for Railway Travelling Group Based on Hidden Markov Model
计算机科学, 2022, 49(6A): 247-255. https://doi.org/10.11896/jsjkx.210500001
[3] 谢柏林, 黎琦, 邝建.
基于隐半马尔可夫模型的微博流行信息检测方法
Microblog Popular Information Detection Based on Hidden Semi-Markov Model
计算机科学, 2022, 49(6A): 291-296. https://doi.org/10.11896/jsjkx.210800011
[4] 罗靖杰, 王永利.
ADCSM:一种细粒度汽车行驶工况模型构建方法
ADCSM:A Fine-grained Driving Cycle Model Construction Method
计算机科学, 2021, 48(6A): 289-294. https://doi.org/10.11896/jsjkx.200600019
[5] 马创, 袁野, 尤海生.
基于灰色——马尔可夫模型的农产品产量预测方法
Agricultural Product Output Forecasting Method Based on Grey-Markov Model
计算机科学, 2020, 47(6A): 535-539. https://doi.org/10.11896/JsJkx.190700126
[6] 张经, 杨健, 苏鹏.
语音识别中单音节识别研究综述
Survey of Monosyllable Recognition in Speech Recognition
计算机科学, 2020, 47(11A): 172-174. https://doi.org/10.11896/jsjkx.200200006
[7] 张成伟, 罗凤娥, 代毅.
基于数据挖掘的指定航班计划延误预测方法
Prediction Method of Flight Delay in Designated Flight Plan Based on Data Mining
计算机科学, 2020, 47(11A): 464-470. https://doi.org/10.11896/jsjkx.200600001
[8] 岳鑫, 杜军威, 胡强, 王延平.
一种故障树结构匹配算法及其应用
Fault Tree Structure Matching Algorithm and Its Application
计算机科学, 2018, 45(9): 202-206. https://doi.org/10.11896/j.issn.1002-137X.2018.09.033
[9] 宫法明,朱朋海.
基于自适应隐马尔可夫模型的石油领域文档分词
Word Segmentation Based on Adaptive Hidden Markov Model in Oilfield
计算机科学, 2018, 45(6A): 97-100.
[10] 马晓迪, 吴茜茵, 金忠.
基于字典和加权低秩恢复的显著目标检测
Salient Object Detection Based on Dictionary and Weighted Low-rank Recovery
计算机科学, 2018, 45(6A): 146-150.
[11] 佟振明, 刘志鹏.
大型多人在线角色扮演游戏的下一地点预测
Next Place Prediction of Massively Multiplayer Online Role-playing Games
计算机科学, 2018, 45(11A): 453-457.
[12] 徐广根,杨璐,严建峰.
一种基于马尔可夫模型的稀疏轨迹终点预测算法
Sparse Trajectory Destination Prediction Algorithm Based on Markov Model
计算机科学, 2017, 44(8): 193-197. https://doi.org/10.11896/j.issn.1002-137X.2017.08.034
[13] 罗凤娥,张成伟,刘安.
基于数据挖掘的航班延误预警管理分析
Flight Delays Early Warning Management and Analysis Based on Data Mining
计算机科学, 2016, 43(Z6): 542-546. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.129
[14] 张向刚,唐海,付常君,石宇亮.
一种基于隐马尔科夫模型的步态识别算法
Gait Recognition Algorithm Based on Hidden Markov Model
计算机科学, 2016, 43(7): 285-289. https://doi.org/10.11896/j.issn.1002-137X.2016.07.052
[15] 王振朝,杨小龙.
异构网络中基于MPTCP的协作拥塞控制方案
Cooperative Congestion Control Scheme Based on MPTCP in Heterogeneous Network
计算机科学, 2016, 43(6): 97-101. https://doi.org/10.11896/j.issn.1002-137X.2016.06.020
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!