结合背景先验和对象先验的显著性检测

doi:10.3969/j.issn.0255-8297.2016.04.010

应用科学学报 ›› 2016, Vol. 34 ›› Issue (4): 451-460.doi: 10.3969/j.issn.0255-8297.2016.04.010

结合背景先验和对象先验的显著性检测

岳珂娟¹, 郑明才¹, 肖建华¹, 伍炯星²

1. 湖南第一师范学院信息科学与工程学院, 长沙 410205;
2. 中南大学湘雅三医院, 长沙 410013

收稿日期:2015-07-14 修回日期:2015-11-05 出版日期:2016-07-30 发布日期:2016-07-30
作者简介:岳珂娟,讲师,研究方向:图像处理,E-mail:yuekejuan@163.com
基金资助:
湖南省教育厅资助科研项目基金(No.13C143)；湖南第一师范学院科研项目基金(No.XYS12N03)；湖南省自然科学基金(No.2015JJ2037)；湖南省教育厅一般项目基金(No.13C157)；湖南省教育厅科学研究项目基金(No.15C0282)资助

Saliency Detection via Combining BackgroundPriors and Object Priors

YUE Ke-juan¹, ZHENG Ming-cai¹, XIAO Jian-hua¹, WU Jiong-xing²

1. School of Information Science and Engineering, Hunan First Normal University, Changsha 410205, China;
2. The Third Xiangya Hospital, Central South University, Changsha 410013, China

Received:2015-07-14 Revised:2015-11-05 Online:2016-07-30 Published:2016-07-30

摘要/Abstract

摘要：

提出一个结合背景先验和对象先验的显著性检测方法.首先，基于背景先验计算两个互补的测地线显著图，即基于纹理特征的测地线显著图和基于颜色特征的测地显著图；然后，计算基于对象先验的显著图；最后，训练一个贝叶斯分类器，并将这3个显著图融合，得到最终的结果.在当前使用最广且最大的用于显著性检测方法评价的公开数据集ASD和MSRA5000上的实验结果表明，该方法优于目前已有的15种方法.

关键词: 对象性, 显著性检测, 背景先验, 测地线显著性, 特征整合

Abstract:

This paper proposes a saliency detection method in which both background prior-based characteristics and object prior-based characteristics are taken into consideration. First, two geodesic saliency maps are generated based on the average color contrast and the EMD distance between two regions represented by the bag of words （BoW）features. A region-level objectiveness map is then generated to measure probability of a region being salient. Finally, a Bayesian classifier is trained to integrate the three saliency maps. The experimental results on ASD and MSRA5000 show that the proposed method outperforms 15 alternative methods.

Key words: saliency detection, featureintegration, objectiveness, background prior, geodesic saliency

中图分类号:

TP399

岳珂娟, 郑明才, 肖建华, 伍炯星. 结合背景先验和对象先验的显著性检测[J]. 应用科学学报, 2016, 34(4): 451-460.

YUE Ke-juan, ZHENG Ming-cai, XIAO Jian-hua, WU Jiong-xing. Saliency Detection via Combining BackgroundPriors and Object Priors[J]. Journal of Applied Sciences, 2016, 34(4): 451-460.

参考文献

[1] Kang S, Lee H, Kim J. Automatic image segmentation using saliency detection and superpixel graph cuts [J]. Advances in Intelligent Systems and Computing, 2013, 208(1): 1023-1034.
[2] Sun J, Ling H B. Scale and object aware image thumbnail [J]. International Journal of Computer Vision, 2013, 104(2): 135-153.
[3] Stas G, Lihi Z M, Ayellet T. Context-aware saliency detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(10): 1915-1926.
[4] Scharfenberger C, Wong A, Fergani K, Zelek J S, Clausi D A. Statistical textural distinctiveness for salient region detection in natural images [C]//IEEE Conference on computer vision and pattern recognition, Porland, OR, USA, 2013: 979-986.
[5] Wei Y C, Wen F, Zhu W J, Sun J. Geodesic saliency using background priors [C]//European Conference on Computer Vision, Florence, Italy, 2012: 29-42.
[6] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.
[7] Hou X D, Zhang L Q. Saliency detection: a spectral residual approach [C]//IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA, 2007: 1-8.
[8] Liu T, Yuan Z J, Sun J, Wang J D, Zheng N N, Tang X O, Shum H Y. Learning to detect a salient object [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 32(2): 353-367.
[9] Achanta R, Hemami S, Estrada F, Susstrunk S. Frequency-tuned salient region detection[C]//IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009: 1597-1604.
[10] Cheng M M, Mitra N J, Huang X L, Torr P H S, Hu S M. Global contrast based salient region detection [C]//IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2011: 409-416.
[11] Xie Y L, Lu H C, Yang M H. Bayesian saliency via low and mid level cues [J]. IEEE Transactions on Image Processing, 2013, 22(5): 1689-1698.
[12] Fu H Z, Cao X C, Tu Z W. Cluster-based co-saliency detection [J]. IEEE Transactions on Image Processing, 2013, 22(10): 3766-3778.
[13] Cheng M M, Warrell J, Lin W Y, Zheng S, Vibhav V, Nigel C. Efficient salient region detection with soft image abstraction [C]//IEEE International Conference on Computer Vision, Sydney, VIC, Australia, 2013: 1529-1536.
[14] Zhang J M, Sclaroff S. Saliency detection: a boolean map approach [C]//IEEE International Conference on Computer Vision, Sydney, NSW, Australia, 2013: 153-160.
[15] 郁志鸣, 王朔中, 张新鹏, 刘婷婷. 结合对比特性与局部清晰特性的图像显著区域检测[J]. 应用科学学报, 2010, 28(1): 24-31. Yu Z M, Wang S Z, Zhang X P, Liu T T. Image saliency detection based on contrast features and local sharpness [J]. Journal of Applied Sciences, 2010, 28(1): 24-31. (in Chinese)
[16] 刘晴, 邹北骥, 陈再良, 高旭, 傅红普. 一种基于颜色特征的感兴趣目标提取方法[J]. 计算机辅助设计与图形学学报, 2013, 25(6): 852-856. Liu Q, Zou B J, Chen Z L, Gao X, Fu H P. Color feature based interest objects detection [J]. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(6): 852-856. (in Chinese)
[17] 陈再良, 刘晴, 邹北骥. 结合视觉注意和纹理特征提取感兴趣区域算法[J]. 小型微型计算机系统, 2012, 33(5): 1135-1140. Chen Z L, Liu Q, Zou B J. Extraction algorithm of region of interest with attention and texture feature [J]. Journal of Chinese Computer Systems, 2012, 33(5): 1135-1140. (in Chinese)
[18] Jiang H Z, Wang J D, Yuan Z J, Wu Y, Zheng N N, Li S P. Salient object detection: a discriminative regional feature integration approach [C]//IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, 2013: 2083-2090.
[19] Radhakrishna A, Appu S, Kevin S, Aurelien L, Pascal F, Sabine S. Slic superpixels compared to state-of-the-art superpixel methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.
[20] Alexe B, Deselaers T, Ferrari V. What is an object? [C]//IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 2010: 73-80.
[21] Yang C, Zhang L H, Lu H C, Ruan X, Yang M H. Saliency detection via graph-based manifold ranking [C]//IEEE International Conference on Computer Vision, Portland, USA, 2013: 3166-3173.
[22] Zhai Y, Shah M. Visual attention detection in video sequences using spatiotemporal cues[C]//Proceedings of the 14th Annual ACM International Conference on Multimedia, Santa Barbara, CA, USA, 2006: 815-824.
[23] Harel J, Koch C, Perona P. Graph based visual saliency [C]//Advances in Neural Information Processing System, Vancouver Canada, 2007: 545-552.
[24] Jiang H Z, Wang J D, Yuan Z J, Liu T, Zheng N N, Li S P. Automatic salient object segmentation based on context and shape prior [C]//Proceedings of the British Machine Vision Conference, Dundee, UK, 2011: 1-12.
[25] Perazzi F, Krahenbuhl P, Pritch Y, Hornung A. Saliency filters: contrast based filtering for salient region detection [C]//IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2012: 733-740.

结合背景先验和对象先验的显著性检测

Saliency Detection via Combining BackgroundPriors and Object Priors

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价

[1]	方俊杰, 雷凯. 面向边缘人工智能计算的区块链技术综述[J]. 应用科学学报, 2020, 38(1): 1-21.
[2]	雷凯, 黄硕康, 方俊杰, 黄济乐, 谢英英, 彭波. 智能生态网络:知识驱动的未来价值互联网基础设施[J]. 应用科学学报, 2020, 38(1): 152-172.
[3]	王峰, 屈俊峰, 赵永标, 谷琼. 基于情境要素和用户偏好的旅行方式推荐[J]. 应用科学学报, 2019, 37(3): 407-418.
[4]	朱文强, 钟元生. 基于声誉计算的可信O2O服务提供商推荐方法[J]. 应用科学学报, 2017, 35(5): 585-601.
[5]	毕景芝1，刘湘南1，赵冬2. 基于粗糙集约简的水稻叶片叶绿素含量高光谱反演[J]. 应用科学学报, 2014, 32(4): 394-400.
[6]	郝琨1,2，金志刚1. 一种基于确定性网络编码的P2P文件分发机制[J]. 应用科学学报, 2014, 32(3): 246-250.
[7]	方欢1;2，陆阳1;3，葛方振1，黄镇谨1. 基于Petri 网的复杂空竭休假排队系统的性能评价[J]. 应用科学学报, 2012, 30(4): 379-386.
[8]	吕杰，刘湘南. 利用支持向量机构建水稻镉含量高光谱预测模型[J]. 应用科学学报, 2012, 30(1): 105-110.