基于稀疏和低秩表示的显著性目标检测

摘要/Abstract

摘要：

文中研究了无监督自下而上的显著性目标检测方法。基于显著性目标在自然图像中稀疏分布的这一先验性假设,提出了一种用低秩和稀疏表示进行显著性目标检测的方法。根据图像背景的先验分布,首先选取一个有效的背景字典来低秩表示图像的背景部分,进而更好地分离出显著性前景。由于人类视觉中心偏好可知,图像的边缘部分不易引起关注,故选取这些边缘部分作为背景先验来选取背景字典。与其他基于稀疏和低秩分解的显著性目标检测相比,文中选取的背景字典更简单有效,且能得到更好的显著性图。实验结果显示,该方法比主流的显著性检测方法得到的显著性图更令人满意。

关键词: 稀疏表示, 超像素分割, 显著性目标检测

Abstract:

This paper studies the unsupervised saliency detection method.Based on the assumption that salient objects are sparsely scattered over the image,we propose the sparse and low rank based saliency detection method.According to the priori distribution of image background,we select an effective background dictionary to represent the image background and thus separate the salient foreground.Compared with other saliency detection method the background dictionary in our method is simple and effective,and can help locate the salient objects accurately.Experimental results show that compared with other method a difference does exist in favor of ours.

Key words: sparse representation;sup-pixel segmentation;saliency detection

中图分类号:

TP391.41

刘甜甜. 基于稀疏和低秩表示的显著性目标检测[J]. , 2015, 28(2): 112-.

LIU Tiantian. Sparse and Low Rank Based Saliency Detection[J]. , 2015, 28(2): 112-.

参考文献

［1］Wolfe J.Guided search 2.0.A revised model of visual search［J］.Psychonomic Bulletin & Review,1994,1(2):202-238.

［2］Steven Yantis.Sensation and perception［M］.New York:Worth Publishers,2013.

［3］Santella A,Agrawala M,Decarlo D,et al.Gaze-based interaction for semi-automatic photo cropping［C］.In Proceeding SIGCHI Conference Human Factors Computer,2006:771-780.

［4］Bradley A,Stentiford F.Visual attention for region of interest coding［J］.J.Vis.Commun.Image Represent.,2003,14(3):232-250.

［5］Wang L,Xue J,Zheng N,et al.Automatic salient object extraction with contextual cue［C］.In ICCV,2011.

［6］Navalpakkam V,Itti L.An integrated model of top-down and bottom-up attention for optimizing detection speed［C］.In CVPR,2006.

［7］Lang Congyan,Liu Guangcan,Yu Jian,et al.Saliency detection by multitask sparsity pursuit［J］.IEEE Transactions on Image Processing,2012,21(3):1327-1338.

［8］Shen Xiaohui,Wu Ying.A unified approach to salient object detection via low rank matrix recovery［C］.2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2012:853,860.

［9］Wei Y,Wen F,Zhu W,et al.Geodesic saliency using background priors［C］.In ECCV,2012:29-42.

［10］Itti L,Koch C,Niebur E.A model of saliency-based visual attention for rapid scene analysis［J］.IEEE Transactions on PAMI,1998,20(11):1254-1259.

［11］Goferman S,Zelnik Manor L,Tal A.Context-aware saliency detection［J］.IEEE Transactions on Pattern Anal Mach Intell.,2012,34(10):1915-26.

［12］Bruce N,Tsotsos J.Saliency based on information maximization［M］.NZ USA:NIPS,2006.

［13］Hou X,Zhang L.Saliency detection:A spectral residual approach［C］.In IEEE Conference of Computer Vision and Pattern Recognition,2007.

［14］Guo C,Ma Q,Zhang L.Spatio-temporal saliency detection using phase specrum of quaternion fourier transform［C］.In IEEE Conference of Computer Vision and Pattern Recognition,2008.

［15］Hou Xiaodi,Harel J,Koch C.Image signature:highlighting sparse salient regions［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(1):194-201.

［16］Schlkopf B,Platt J.,Hofmann T.Advances in neural information processing systems［C］.Proceedings of the 2006 Conference,2006:545-552.

［17］Gopalakrishnan V,Yiqun Hu,Rajan D.Random walks on graphs for salient object detection in images［J］.IEEE Transactions on Image Processing,2010,19(12):3232-3242.

［18］Yang Chuan,Hang Lihe,Lu Huchuan,et al.Saliency detection viagraph-based manifold ranking［C］.2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2013:3166-3173.

［19］Wei Y,Wen F,Zhu W,et al.Geodesic saliency using background priors［C］.In ECCV,2012.

［20］Liu G,Lin Z,Yan S,et al.Robust recovery of subspace structures by low-rank representation［J］.IEEE Transactions on Pattern Anal.Mach.Intell.,2010(8):993-1001.

［21］Liu T,Sun J,Zheng N,et al.Learning to detect a salient object［C］.In Proceeding of IEEE Conference Computation Vision Pattern Recognition,2007:1-8.

［22］Radhakrishna Achanta,Sabine Susstrunk.Saliency detection using maximum symmetric surround［C］.Hong Kong:International Conference on Image Processing (ICIP),2010.

[1]	陆玮,刘翔,薛冕. 基于超像素分割的孪生网络双目立体匹配方法研究[J]. 电子科技, 2021, 34(9): 73-78.
[2]	顾正之,王素玉. 基于端元字典稀疏解混的高光谱图像亚像元定位[J]. 电子科技, 2019, 32(4): 33-39.
[3]	骆冲,邬春学. 一种改进的字典学习方法在医疗疾病分析中的应用[J]. 电子科技, 2019, 32(2): 47-50.
[4]	陈益, 李文钧. 基于正交匹配追踪算法的语音信号重构研究[J]. , 2018, 31(3): 44-.
[5]	郑昊辰, 姜维. 基于压缩感知的阅卷系统手写汉字识别算法[J]. , 2018, 31(3): 75-.
[6]	沈丽,韩彦芳. 基于稀疏表示的超分辨率图像重建[J]. , 2015, 28(9): 144-.
[7]	田香玲,席志红. 压缩感知观测矩阵的优化算法[J]. , 2015, 28(8): 102-.
[8]	曹蒙蒙,李新叶,范月坤. 基于判别低秩矩阵恢复和稀疏表示的车标识别[J]. , 2015, 28(4): 57-.