基于对比度优化流形排序的显著目标检测算法

doi:10.11772/j.issn.1001-9081.2017.03.684

计算机应用 ›› 2017, Vol. 37 ›› Issue (3): 684-690.DOI: 10.11772/j.issn.1001-9081.2017.03.684

• 第二十五届全国多媒体技术学术会议(NCMT2016) • 上一篇下一篇

基于对比度优化流形排序的显著目标检测算法

谢畅¹, 朱恒亮¹, 林晓^1,2, 马利庄¹

1. 上海交通大学计算机科学与工程系, 上海 200240;
2. 上海理工大学光电信息与计算机工程学院, 上海 200093

收稿日期:2016-09-23 修回日期:2016-10-08 出版日期:2017-03-10 发布日期:2017-03-22
通讯作者: 谢畅
作者简介:谢畅(1991-),男,四川雅安人,硕士研究生,主要研究方向:图像处理、模式识别、机器学习;朱恒亮(1981-),男,山东微山人,博士研究生,主要研究方向:图像处理、模式识别;林晓(1978-),女,河南洛阳人,副教授,博士,CCF会员,主要研究方向:图像处理、视频处理;马利庄(1963-),男,浙江宁波人,教授,博士,CCF会员,主要研究方向:计算机图形学、图像处理、计算机辅助设计、科学数据可视化、计算机动画。
基金资助:
国家自然科学基金重点项目（61133009）；国家自然科学基金资助项目（61472245，U1304616，61502220）。

Salient target detection algorithm based on contrast optimized manifold ranking

XIE Chang¹, ZHU Hengliang¹, LIN Xiao^1,2, MA Lizhuang¹

1. Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China;
2. School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2016-09-23 Revised:2016-10-08 Online:2017-03-10 Published:2017-03-22
Supported by:
This work is partially supported by the Key Project of National Natural Science Foundation of China (61133009), the National Natural Science Foundation of China (61472245, U1304616, 61502220).

摘要/Abstract

摘要： 现有的基于背景先验的显著性算法模型中存在先验区域选取不合理的问题，导致计算出的前景区域不准确，影响最终结果。针对该问题提出了基于对比度优化流形排序的显著目标检测算法。利用图像边界信息找出背景先验，设计出采用显著期望、局部对比度以及全局对比度三个指标来衡量先验质量的算法，并根据先验质量设计带权加法，代替简单乘法融合显著先验，从而使显著先验更加准确。从先验中提取显著区域时，更改了选取阈值的策略，更合理地选取出前景区域，再利用流形排序得到显著性图，从而使显著性检测结果更加准确。实验结果表明，与同类算法相比，所提算法突出显著区域，减少噪声，更符合人类视觉感知，并在处理时间上领先于深度学习方法。

关键词: 边界先验, 先验融合, 显著估计, 全局对比度, 局部对比度, 流形排序

Abstract: The existing boundary prior based saliency algorithm model has the problem of improper selection of reasonable saliency prior region, which leads to the inaccurate foreground region and influence the final result. Aiming at this problem, a salient target detection algorithm based on contrast optimized manifold ranking was proposed. The image boundary information was utilized to find the background prior. An algorithm for measuring the priori quality was designed by using three indexes, namely, saliency expection, local contrast and global contrast. A priori quality design with weighted addition replaced simple multiplication fusion to make the saliency prior more accurate. When the salient regions were extracted from the a priori, the strategy of selecting the threshold was changed, the foreground region was selected more rationally, and the saliency map was obtained by using the manifold ranking, so that the saliency detection result was more accurate. The experimental results show that the proposed algorithm outperforms the similar algorithms, reduces the noise, which is more suitable for human visual perception, and ahead of the depth learning method in processing time.

Key words: boundary prior, prior fusion, saliency estimation, global contrast, local contrast, manifold ranking

中图分类号:

TP391.41

谢畅, 朱恒亮, 林晓, 马利庄. 基于对比度优化流形排序的显著目标检测算法[J]. 计算机应用, 2017, 37(3): 684-690.

XIE Chang, ZHU Hengliang, LIN Xiao, MA Lizhuang. Salient target detection algorithm based on contrast optimized manifold ranking[J]. Journal of Computer Applications, 2017, 37(3): 684-690.

参考文献

[1] 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.
[2] BORJI A, SIHITE D N, ITTI L. Probabilistic learning of task-specific visual attention[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2012:470-477.
[3] FRINTROP S, BACKER G, ROME E. Goal-directed search with a top-down modulated computational attention system[M]//Pattern Recognition, LNCS 3663. Berlin:Springer, 2005:117-124.
[4] GAO D, VASCONCELOS N. Discriminant saliency for visual recognition from cluttered scenes[J]. Advances in Neural Information Processing Systems, 2004, 17:481-488.
[5] TONG N, LU H, XIANG R, et al. Salient object detection via bootstrap learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:1884-1892.
[6] ACHANTA R, ESTRADA F, WILS P, et al. Salient region detection and segmentation[M]//Computer Vision Systems, LNCS 5008. Berlin:Springer, 2008:66-75.
[7] CHENG M M, ZHANG G X, MITRA N J, et al. Global contrast based salient region detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):569-582..
[8] ZHANG W, WANG Z, YAN C, et al. Saliency optimization from robust background detection[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:2814-2821.
[9] 蒋娇,陆平,朱恒亮,等.融合对比度与背景先验的显著目标检测算法[J].计算机辅助设计与图形学学报,2016,28(1):82-89.(JIANG J, LU P, ZHU H L, et al. Salient object detection using contrast and background priors[J]. Journal of Computer-Aided Design and Computer Graphics, 2016, 28(1):82-89.)
[10] 王晨,樊养余,李波,等.基于滤波合成的关键显著性目标检测方法[J].计算机应用,2014,34(12):3531-3535.(WANG C, FAN Y Y, LI B, et al. Key salient object detection based on filtering integration method[J]. Journal of Computer Applications, 2014, 34(12):3531-3535.)
[11] 葛涛,冯松鹤.基于层次和动态阈值的图像显著区域检测方法[J].计算机应用,2006,26(11):2721-2723.(GE T. FENG S H. A method for image salient regions detection based on layer and dynamic threshold[J]. Journal of Computer Applications, 2006, 26(11):2721-2723.)
[12] 赵三元,李凤霞,沈建冰,等.基于红黑小波的图像显著性检测[J].计算机辅助设计与图形学学报,2014,26(10):1789-1793.(ZHAO S Y, LI F X, SHEN J B, et al. Image saliency detection using red-black wavelet[J]. Journal of Computer-Aided Design and Computer Graphics, 2014, 26(10):1789-1793.)
[13] 柳欣,钟必能,张茂胜,等.基于张量低秩恢复和块稀疏表示的运动显著性目标提取[J].计算机辅助设计与图形学学报,2014,26(10):1753-1763.(LIU X, ZHONG B N, ZHANG M S, et al. Motion saliency extraction via tensor based low-rank recovery and block-sparse representation[J]. Journal of Computer-Aided Design and Computer Graphics, 2014, 26(10):1753-1763.)
[14] 胡正平,孟鹏权.全局孤立性和局部同质性图表示的随机游走显著目标检测算法[J].自动化学报,2011,37(10):1279-1284.(HU Z P, MENG P Q. Graph presentation random walk salient object detection algorithm based on global isolation and local homogeneity[J]. Acta Automatica Sinica, 2011, 37(10):1279-1284.)
[15] WANG L, LU H, RUAN X, et al. Deep networks for saliency detection via local estimation and global search[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:3183-3192.
[16] YANG J. Top-down visual saliency via joint CRF and dictionary learning[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2012:2296-2303.
[17] PERAZZI F, KRÄHENBÜHL P, PRITCH Y, et al. Saliency filters:contrast based filtering for salient region detection[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2012:733-740.
[18] FRINTROP S, WERNER T, GARCIA G M. Traditional saliency reloaded:a good old model in new shape[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:82-90.
[19] GONG C, TAO D, LIU W, et al. Saliency propagation from simple to difficult[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:2531-2539.
[20] GOPALAKRISHNAN V, HU Y, RAJAN D. Random walks on graphs to model saliency in images[C]//Proceeding of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2009:1698-1705.
[21] JIANG B, ZHANG L, LU H, et al. Saliency detection via absorbing Markov chain[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2013:1665-1672.
[22] REN Z, HU Y, CHIA L T, et al. Improved saliency detection based on superpixel clustering and saliency propagation[C]//Proceedings of the 18th ACM International Conference on Multimedia. New York:ACM, 2010:1099-1102.
[23] YANG C, ZHANG L, LU H, et al. Saliency detection via graph-based manifold ranking[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:3166-3173.
[24] ZHOU D, WESTON J, GRETTON A, et al. Ranking on data manifolds[J]. Advances in Neural Information Processing Systems, 2004, 16:169-176.
[25] LI C, YUAN Y, CAI W, et al. Robust saliency detection via regularized random walks ranking[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:2710-2717.
[26] QIN Y, LU H, XU Y, et al. Saliency detection via cellular automata[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:110-119.
[27] ACHANTA R, SHAJI A, SMITH K, et al. Slic superpixels[EB/OL].[2016-01-07]. https://infoscience.epfl.ch/record/149300/files/SLIC_Superpixels_TR_2.pdf?version=2.
[28] JIANG H, WANG J, YUAN Z, et al. Salient object detection:a discriminative regional feature integration approach[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:2083-2090.
[29] LI Y, HOU X, KOCH C, et al. The secrets of salient object segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:280-287.
[30] ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]//Proceeding of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2009:1597-1604.
[31] HAREL J, KOCH C, PERONA P. Graph-based visual saliency[C]//Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press, 2006:545-552.
[32] CHENG M M, WARRELL J, LIN W Y, et al. Efficient salient region detection with soft image abstraction[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2013:1529-1536.

基于对比度优化流形排序的显著目标检测算法

Salient target detection algorithm based on contrast optimized manifold ranking

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

[1]	朱征宇, 汪梅. 基于Manifold Ranking和结合前景背景特征的显著性检测[J]. 计算机应用, 2016, 36(9): 2560-2565.
[2]	刘兵, 张鸿. 基于卷积神经网络和流形排序的图像检索算法[J]. 计算机应用, 2016, 36(2): 531-534.
[3]	彭波王一鸣. 低照度图像增强算法的研究与实现[J]. 计算机应用, 2007, 27(8): 2001-2003.