概率框架下多特征显著性检测算法

doi:10.3969/j.issn.0372-2112.2019.11.020

电子学报 ›› 2019, Vol. 47 ›› Issue (11): 2378-2385.DOI: 10.3969/j.issn.0372-2112.2019.11.020

概率框架下多特征显著性检测算法

杨小冈, 李维鹏, 马玛双

火箭军工程大学, 陕西西安 710025

收稿日期:2018-07-11 修回日期:2019-04-23 出版日期:2019-11-25
- 通讯作者:
- 李维鹏
- 作者简介:
- 杨小冈 男,1978年1月出生于陕西省西安市.现为火箭军工程大学教授、博士生导师.获得省部级科技进步奖励11项.在国内外发表学术论文90余篇,其中SCI、EI检索40余篇.E-mail:doctoryxg@163.com;马玛双 男,1995年01月出生于江西上饶.硕士生.主要研究方向为图像配准及视觉导航.E-mail:mamas008@163.com
- 基金资助:
- 国家自然科学基金 (No.61806209); 陕西省组合导航重点实验室基金 (No.SKLIIN-20180103)

Saliency Detection with Multi-features in Probability Framework

YANG Xiao-gang, LI Wei-peng, MA Ma-shuang

Rocket Force Engineering University, Xi'an, Shaanxi 710025, China

Received:2018-07-11 Revised:2019-04-23 Online:2019-11-25 Published:2019-11-25
- Corresponding author:
- LI Wei-peng
- Supported by:
- National Natural Science Foundation of China (No.61806209); Fund of Shaanxi Key Laboratory of Integrated and Intelligent Navigation, Xi'an (No.SKLIIN-20180103)

摘要/Abstract

摘要： 显著性检测是计算机视觉的一项基础问题，广泛地用于注视点预测、目标检测、场景分类等视觉任务当中.为提升多特征条件下图像的显著性检测精度，以显著图的联合概率分布为基础，结合先验知识，设计一种概率框架下的多特征显著性检测算法.首先分析了单一特征显著性检测的潜在缺陷，继而推导出多特征下显著图的联合概率分布；然后根据显著图的稀有性，稀疏性，紧凑性与中心先验推导出显著图的先验分布，并使用正态分布假设简化了显著图的条件分布；随后根据显著图的联合概率分布得到其极大后验估计，并基于多阈值假设构建了分布参数的有监督学习模型.数据集实验表明：相比于精度最高的单一特征显著性检测方法，多特征算法在有监督和启发式方法下的平均误差降低了6.98%和6.81%，平均F-measure提高了1.19%和1.16%；单幅图像的多特征融合耗时仅为11.8ms.算法精度较高，实时性好，且可根据不同任务选择所需的特征类别与先验信息，能够满足多特征显著性检测的性能要求.

关键词: 显著性检测, 联合概率分布, 多特征融合, 先验信息, 指数分布族, 极大后验估计

Abstract: Saliency detection is a fundamental issue in computer vision. It is widely applied in fixation prediction, object detection, scene classification, and other visual tasks. In order to improve the precision of visual saliency detection with multi-features, a multi-feature integration algorithm is proposed based on the joint probability distribution of saliency map and combined with priori knowledge. Firstly, the potential defects of single feature saliency detection are analyzed, and the joint probability distribution of saliency maps with multiple features is deduced. Secondly, the priori distribution of the saliency map is deduced based on the rarity,sparsity,compactness and center priori of the saliency map,and the condition distribution of the saliency map is simplified based on the assumption of normal distribution. Then the maximum a posteriori estimation is obtained from the joint probability distribution of the saliency map, and a supervised learning model of the distribution parameters is constructed based on the multi-threshold hypothesis. Experiments show that compared to the highest-precision saliency detection method on single feature, the mean average error of the multi-feature algorithm under the supervised and heuristic method is decreased by 6.98% and 6.81%, and the average F-measure is improved by 1.19% and 1.16%. And the multi-feature integration of single image takes only 11.8ms. The algorithm has high accuracy and real-time performance, and can be combined with the required features and different prior information according to the task. It meets the requirements of saliency detection with multi-features.

Key words: saliency detection, joint distribution, multi-feature integration, prior information, exponential distribution family, maximum a posteriori estimation

中图分类号:

TP391

杨小冈, 李维鹏, 马玛双. 概率框架下多特征显著性检测算法[J]. 电子学报, 2019, 47(11): 2378-2385.

YANG Xiao-gang, LI Wei-peng, MA Ma-shuang . Saliency Detection with Multi-features in Probability Framework[J]. Acta Electronica Sinica, 2019, 47(11): 2378-2385.

参考文献

[1] BORHI A,CHENG M M,et al.Salientobject detection:a survey[J].Eprint Arxiv,2014,16(7):3118-3137.
[2] BORHI A,SIHITE D N,ITTI L.Salientobject detection:a benchmark[A].Computer Vision-ECCV 2012[C].Berlin Heidelberg:Springer,2012.414-429.
[3] GUO C,MA Q,ZHANG L.Spatio-temporalsaliency detection using phase spectrum of quaternion fourier transform[A].Computer Vision and Pattern Recognition[C].Anchorage,Alaska,USA:IEEE Computer Society,2008.1-8.
[4] HOU X,ZHANG L.Saliency Detection:Aspectral residual approach[A].Computer Vision and Pattern Recognition[C].Minneapolis,Minnesota,USA:IEEE Computer Society,2007.1-8.
[5] 郑云飞,张雄伟,等.基于全卷积网络的语义显著性区域检测方法研究[J].电子学报,2017,45(11):2593-2601. ZHEN Y F,ZHANG X W,et al.Thesemantic salient region detection algorithm based on the fully convolutional networks[J].Acta Electronica Sinica,2017,45(11):2593-2601.(in Chinese)
[6] ACHANTA R,ESTRADA F,WILS P,et al.Salientregion detection and segmentation[A].International Conference on Computer Vision Systems[C].Berlin,Heidelberg:Springer,2008.66-75.
[7] Harel J,Koch C,Perona P.Graph-based visual saliency[A].International Conference on Neural Information Processing Systems[C].Cambridge,Massachusetts,USA:MIT Press,2006.545-552.
[8] 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.
[9] MA Y F,ZHANG H J.Contrast-based image attention analysis by using fuzzy growing[A].Eleventh ACM International Conference on Multimedia[C].Berkeley,California,USA:ACM,2003.374-381.
[10] ACHANDA R,HEMAMI S,Estrada F,et al.Frequency-tuned salient region detection[A].Computer Vision and Pattern Recognition[C].Miami,Florida,USA:IEEE Computer Society,2009.1597-1604.
[11] YAN Q,XU L,SHI J,et al.Hierarchical saliency detection[A].Computer Vision and Pattern Recognition[C].Portland,Oregon:IEEE Computer Society,2009.1155-1162.
[12] SHI J,YAN Q,XU L,et al.Hierarchical saliency detection on extended CSSD[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,38(4):717.
[13] CHENG M M,MITRA N J,HUANG X,et al.Global contrast based salient region detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(3):569-582.
[14] JIANG H,YUAN Z,CHENG M M,et al.Salient object detection:a discriminative regional feature integration approach[J].International Journal of Computer Vision,2017,123(2):251-268.

概率框架下多特征显著性检测算法

Saliency Detection with Multi-features in Probability Framework

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

[1]	陈星宇, 叶锋, 黄添强, 翁彬, 陈家祯, 林文忠. 融合小型深度生成模型的显著性检测[J]. 电子学报, 2021, 49(4): 768-774.
[2]	黎毅达, 高发荣, 姚婷, 蔡利杰. 基于Fisher判别和GKF-RELM算法的多特征步态模式识别[J]. 电子学报, 2021, 49(10): 1993-2001.
[3]	樊亚红, 刘宾, 陈平, 潘晋孝, 李毅红. 基于轮廓先验约束的复杂异形工件CT成像方法研究[J]. 电子学报, 2020, 48(10): 1976-1982.
[4]	丁颖, 刘延伟, 刘金霞, 刘科栋, 王利明, 徐震. 虚拟现实全景图像显著性检测研究进展综述[J]. 电子学报, 2019, 47(7): 1575-1583.
[5]	李庆武, 马云鹏, 周亚琴, 邢俊. 基于无监督栈式降噪自编码网络的显著性检测算法[J]. 电子学报, 2019, 47(4): 871-879.
[6]	刘颖, 胡丹, 范九伦, 王富平, 李大湘. 基于融合特征的现勘图像检索结果优化算法[J]. 电子学报, 2019, 47(2): 296-301.
[7]	侯小刚, 赵海英, 马严. 基于超像素多特征融合的快速图像分割算法[J]. 电子学报, 2019, 47(10): 2126-2133.
[8]	张峰, 钟宝江. 基于兴趣目标的图像检索[J]. 电子学报, 2018, 46(8): 1915-1923.
[9]	李梦, 刘星, 任泽民. 联合Sobolev梯度的相场变分模型应用于图像显著性检测[J]. 电子学报, 2018, 46(7): 1683-1690.
[10]	范舜奕, 管桦, 侯志强, 余旺盛, 戴铂. 基于多表观特征子模型更新的鲁棒视觉跟踪[J]. 电子学报, 2018, 46(2): 440-446.
[11]	杨兴明, 王雨廷, 谢昭, 吴克伟. 基于“轮廓-区域”多层互补特性的显著性检测[J]. 电子学报, 2018, 46(11): 2688-2695.
[12]	刘礼才, 李锐光, 殷丽华, 郭云川, 项菲. 面向移动智能设备的多特征融合隐式鉴别机制研究[J]. 电子学报, 2016, 44(11): 2713-2719.
[13]	钱晓亮, 郭雷, 韩军伟, 程塨, 姚西文. 一种基于加权稀疏编码的频域视觉显著性检测算法[J]. 电子学报, 2013, 41(6): 1159-1165.
[14]	樊鹤红;刘盼;赵兴群;孙小菡. 小样本条件下行波管可靠性评估方法的研究[J]. 电子学报, 2010, 38(6): 1394-1398.