基于背景和前景交互传播的图像显著性检测

doi:10.6040/j.issn.1672-3961.0.2016.221

山东大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (2): 80-85.doi: 10.6040/j.issn.1672-3961.0.2016.221

基于背景和前景交互传播的图像显著性检测

翟继友^1,2,周静波¹,任永峰²,王志坚²

1. 南京工程学院计算机工程学院, 江苏南京 211167;2. 河海大学计算机与信息学院, 江苏南京 211100

收稿日期:2016-06-21 出版日期:2017-04-20 发布日期:2016-06-21
作者简介:翟继友(1978— ),男,江苏丰县人,助理研究员,博士研究生,主要研究方向为机器学习与图像分析.E-mail:jiyou1018@126.com
基金资助:
江苏省高校自然科学研究面上资助项目(14KJB520006),南京工程学院校级科研基金资助项目(CKJA201306)

A visual saliency detection based on background and foreground interaction

ZHAI Jiyou^1,2, ZHOU Jingbo¹, REN Yongfeng², WANG Zhijian²

1. School of Computer Engineering, Nanjing Institute of Technology, Nanjing 211167, Jiangsu, China;
2. College of Computer and Information, Hohai University, Nanjing 211100, Jiangsu, China

Received:2016-06-21 Online:2017-04-20 Published:2016-06-21

摘要/Abstract

摘要： 为了更精确地提取图像中的显著性区域,提出一种新的基于背景和前景交互传播的图像显著性检测计算模型。通过建立一个新的模型来寻找图像中的显著性元素,用一种交互式特征传播方法来扩散显著性特征。采用不同参数对图像进行分割,得到多个尺度下的超像素;在单一尺度下通过背景和前景交互传播获得超像素的显著值;对多个显著值进行加权平均融合,并采用平滑机制进行优化得到最终显著图。在公开图像数据库进行的试验结果表明,该模型提高了对图像显著目标大小的适应性,不仅较好地抑制了噪声,还使得显著目标更均匀地凸显出来,结果优于同类的算法。

关键词: 前景, 背景, 交互传播, 显著性检测

Abstract: In order to extract the salient region of image efficiently, a new algorithm model of image saliency detection based on background and foreground interaction was proposed. To find the significant elements in the image, a new model using an interactive feature propagation method to diffuse the significant features was built. The image was segmented into superpixels with different parameters. The salient value of each superpixel was obtained by background and foreground interaction according to a single scale. The final saliency map was obtained by the weighted average fusion of multiple salient values in different scale, and the optimization using the smoothing mechanism. Experimental results showed that the proposed method performed better than the other state-of-the-art methods, which improved the adaptability to the size of salient regions. In addition, our method was proved better not only in restraining the noise, but also in making the salient objects more uniform.

Key words: background, foreground, interactive propagation, saliency detection

中图分类号:

TP301.6

翟继友,周静波,任永峰,王志坚. 基于背景和前景交互传播的图像显著性检测[J]. 山东大学学报(工学版), 2017, 47(2): 80-85.

ZHAI Jiyou, ZHOU Jingbo, REN Yongfeng, WANG Zhijian. A visual saliency detection based on background and foreground interaction[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2017, 47(2): 80-85.

参考文献

[1] ZHANG H, XU M, ZHUO L, et al. A novel optimization framework for salient object detection[J]. Visual Computer, 2016, 32(1):31-41.
[2] 李春雷, 张兆翔, 刘洲峰. 基于纹理差异视觉显著性的织物疵点检测算法[J].山东大学学报(工学版),2014,44(4):1-8. LI Chunlei, ZHANG Zhaoxiang, LIU Zhoufeng. A novel fabric defect detection algorithm based on textural differential visual saliency model[J]. Journal of Shandong University(Engineering Science), 2014, 44(4):1-8.
[3] 钱生,陈宗海,林名强,等.基于条件随机场和图像分割的显著性检测[J].自动化学报,2015,41(4):711-724. QIAN Sheng, CHEN Zonghai, LIN Mingqiang, et al. Saliency detection based on conditional random field and image segmentation[J]. Acta Automatica Sinica, 2015, 41(4):711-724.
[4] 任永峰,周静波.基于信息弥散机制的图像显著性区域提取算法[J]. 山东大学学报(工学版), 2015, 45(6):1-6. REN Yongfeng, ZHOU Jingbo. An image saliency object detection algorithm based on information diffusion[J]. Journal of Shandong University(Engineering Science), 2015, 45(6):1-6.
[5] JIANG H, WANG J, YUAN Z, et al. Salient object detection: a discriminative regional feature integration approach[C] //IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA: IEEE Press, 2014:2083-2090.
[6] ZHU W, LIANG S, WEI Y, et al. Saliency optimization from robust background detection[C] //IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA:IEEE Press, 2014:2814-2821.
[7] GOPALAKRISHNAN V, HU Y Q, RAJAN D. Random walks on graphs for salient object detection in images[J]. IEEE Transactions on Image Processing, 2010, 19(12):3232-3242.
[8] ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C] //IEEE Conference on Computer Vision and Pattern Recognition. Miami,Florida, USA: IEEE Press, 2009:1597-1604.
[9] Kim J S, Kim H, Sim J Y, et al. Video saliency detection based on random walk with restart[C] //IEEE International Conference on Image Processing, 2013:2465-2469.
[10] YANG C, ZHANG L, LU H, et al. Saliency detection via graph-based manifold ranking[C] //IEEE Conference on Computer Vision and Pattern Recognition.Portland, USA: IEEE Press, 2013:3166-3173.
[11] MOSCHENI F, BHATTACHARJEE S, KUNT M. Spatio-temporal segmentation based on region merging[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(9):897-915.
[12] ZHAI J, ZHOU J, REN Y, et al. Salient object detection via multiple random walks[J].KSII Transactions on Internet and Information Systems, 2016, 10(4):1712-1731.
[13] 徐少平,刘小平, 李春泉,等.基于稠密局部自相似特征流的图像配准算法[J].光电子·激光,2013,24(8):1619-1628. XU Shaoping, LIU Xiaoping, LI Chunquan, et al. An image registration algorithm based on dense local self-similarity feature flow[J].Journal of Optoelectronics.Laser, 2013, 24(8):1619-1628.
[14] HOU X, ZHANG L. Saliency detection: a spectral residual approach[C] //IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, Minnesota, USA: IEEE Press, 2007:1-8.
[15] XIA C, QI F, SHI G, et al. Nonlocal center—surround reconstruction-based bottom-up saliency estimation[J]. Pattern Recognition, 2015, 48(4):1337-1348.
[16] MARGOLIN R, TAL A, ZELNIK-MANOR L. What makes a patch distinction[C] //IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA:IEEE Press, 2013:1139-1146.
[17] CHANG K Y, LIU T L, CHEN H T, et al. Fusing generic objectness and visual saliency for salient object detection[C] //IEEE International Conference on Computer Vision. Barcelona, Spain:IEEE Press, 2011:914-921.
[18] YAN Q, XU L, SHI J, et al. Hierarchical saliency detection[C] //IEEE International Conference on Computer Vision. Portland, USA: IEEE Press, 2013:1155-1162.
[19] WANG L, XUE J, ZHENG N, et al. Automatic salient object extraction with contextual cue[C] //IEEE International Conference on Computer Vision. Barcelona, Spain: IEEE Press, 2011:105-112.
[20] ZHOU J, REN Y, YAN Y, et al. Salient object detection: manifold-based similarity adaptation approach[J]. Journal of Electronic Imaging, 2014, 23(6):704-714.
[21] JIANG H, WANG J, YUAN Z, et al. Salient object detection: a discriminative regional feature integration approach[C] //IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA:IEEE Press, 2013:2083-2090.
[22] ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C] //IEEE Conference on Computer Vision and Pattern Recognition. Miami,USA: IEEE Press, 2009:1597-1604.
[23] ZHOU D, BOUSQUET O, LAL T N, et al. Learning with local and global consistency[J]. Advances in Neural Information Processing Systems, 2004, 17(4):321-328.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于背景和前景交互传播的图像显著性检测

A visual saliency detection based on background and foreground interaction

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

多维度评价

本文评价

推荐阅读 0

[1]	惠开发,成科扬,詹永照. 基于改进ViBe算法的视频浓缩[J]. 山东大学学报(工学版), 2017, 47(3): 43-48.
[2]	任永峰,董学育. 基于自适应流形相似性的图像显著性区域提取算法[J]. 山东大学学报(工学版), 2017, 47(3): 56-62.
[3]	刘英霞,王希常,唐晓丽,常发亮. 基于小波域特征和贝叶斯估计的目标检测算法[J]. 山东大学学报(工学版), 2017, 47(2): 63-70.
[4]	任永峰, 周静波. 基于信息弥散机制的图像显著性区域提取算法[J]. 山东大学学报(工学版), 2015, 45(6): 1-6.
[5]	郭志波, 董健, 庞成. 多技术融合的Mean-Shift目标跟踪算法[J]. 山东大学学报(工学版), 2015, 45(2): 10-16.
[6]	邱晓欣1,2,张文强1,2*,秦晋贤1,2,杜正阳1,2,张德峰1,2. 恶劣环境下多目标实时跟踪算法研究[J]. 山东大学学报(工学版), 2014, 44(2): 21-27.
[7]	佀君淑,朱文兴*,沙永贺. 复杂背景下的交通信号灯综合识别方法[J]. 山东大学学报(工学版), 2014, 44(2): 64-68.
[8]	王秀芬,王汇源,王松. 基于背景差分法和显著性图的海底目标检测方法[J]. 山东大学学报(工学版), 2011, 41(1): 12-16.
[9]	崔英,陈文楷,雷飞 . 基于背景减法的游泳者检测[J]. 山东大学学报(工学版), 2008, 38(1): 39-42 .