融合前景信息的背景模板优化显著性检测算法

doi:10.19678/j.issn.1000-3428.0049791

计算机工程 ›› 2019, Vol. 45 ›› Issue (1): 221-225,232. doi: 10.19678/j.issn.1000-3428.0049791

融合前景信息的背景模板优化显著性检测算法

陈威¹,李决龙²,邢建春¹,杨启亮^1,3,周启臻¹

1.陆军工程大学国防工程学院,南京 210007; 2.海军海防工程研究中心,北京 100841; 3.南京大学计算机软件新技术国家重点实验室,南京 210093

收稿日期:2017-12-21 出版日期:2019-01-15 发布日期:2019-01-15
作者简介:陈威(1994—),男,硕士研究生,主研方向为计算机视觉;李决龙、邢建春,教授;杨启亮,副教授;周启臻,硕士研究生。
基金资助:
江苏省自然科学基金(BK20151451)。

Background Template Optimization Saliency Detection Algorithm Fusing with Foreground Information

CHEN Wei ¹,LI Juelong ²,XING Jianchun ¹,YANG Qiliang^1,3,ZHOU Qizhen¹

1.College of Defense Engineering,Army Engineering University of PLA,Nanjing 210007,China; 2.Research Center of Coastal Defense Engineering,Beijing 100841,China; 3.State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210093,China

Received:2017-12-21 Online:2019-01-15 Published:2019-01-15

摘要/Abstract

摘要：

当显著目标位于图像边界时,已有显著性检测模型往往将显著性区域误检为背景模板,导致检测效果不佳。为此,提出一种背景模板优化的显著性检测算法。设计一种选择策略移除图像边界区域的显著超像素模块,建立改进的背景模板后计算基于背景的显著图,从该显著图中得到紧凑的前景区域,描述显著目标的外观和位置后计算基于前景的显著图。在此基础上,将2个显著图进行融合,通过一种能量函数对其进行改善,得到最终平滑和精确的显著图。实验结果表明,相对SEG、CA等算法,该算法能提高目标检测的精确率与召回率。

关键词: 显著性检测, 背景模板, 选择策略, 显著图, 前景信息

Abstract:

When salient objects exist at image boundaries,most saliency detection models misdetect salient regions as background templates,resulting in poor detection results.To solve this problem,a saliency detection algorithm based on background template optimization is proposed.A selection strategy is designed to remove the salient super-pixel module in the image boundary area,and an improved background template is established to calculate the salient image based on the background.A compact foreground region is obtained from the saliency map,and the saliency map based on foreground is calculated after describing the appearance and location of salient objects.On this basis,two saliency maps are fused and improved by an energy function,and eventually more smooth and accurate saliency maps are obtained.Experimental results show that the proposed algorithm can improve the accuracy and recall rate of target detection compared with SEG,CA and other algorithms.

Key words: saliency detection, background template, selection strategy, saliency map, foreground information

中图分类号:

TN911.73

陈威,李决龙,邢建春,杨启亮,周启臻. 融合前景信息的背景模板优化显著性检测算法[J]. 计算机工程, 2019, 45(1): 221-225,232.

CHEN Wei,LI Juelong,XING Jianchun,YANG Qiliang,ZHOU Qizhen. Background Template Optimization Saliency Detection Algorithm Fusing with Foreground Information[J]. Computer Engineering, 2019, 45(1): 221-225,232.

http://www.ecice06.com/CN/Y2019/V45/I1/221

参考文献

［1］周帅骏,任福继,堵俊,等.融合背景先验与中心先验的显著性目标检测［J］.中国图象图形学报,2017,22(5):584-595.
［2］YANG J,YANG M H.Top-down visual saliency via joint CRF and dictionary learning［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:2296-2303.
［3］CHENGM 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.
［4］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.
［5］LIU T,YUAN Z,SUN J,et al.Learning to detect a salient object［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,33(2):353-367.
［6］ACHANTA R,HEMAMI S,ESTRADA F,et al.Frequency-tuned salient region detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2009:1597-1604.
［7］GOFERMAN S,ZELNIKMANOR L,TAL A.Context-aware saliency detection［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(10):191-195.
［8］WEI Y,WEN F,ZHU W,et al.Geodesic saliency using background priors［C］//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2012:29-42.
［9］YANG C,ZHANG L,LU H,et al.Saliency detection via graph-based manifold ranking［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3166-3173.
［10］JIANG B,ZHANG L,LU H,et al.Saliency detection via absorbing Markov chain［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:1665-1672.
［11］WANG J,LU H,LI X,et al.Saliency detection via background and foreground seed selection［J］.Neurocomputing,2015,152(C):359-368.
［12］JIANG H,WANG J,YUAN Z,et al.Salient object detection:a discriminative regional feature integration approach［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:2083-2090.
［13］ZHU W,LIANG S,WEI Y,et al.Saliency optimization from robust background detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:2814-2821.
［14］LEVINSHTEIN A,SMINCHISESCU C,DICKINSON S.Optimal contour closure by superpixel grouping［C］//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2010:480-493.
［15］JIANG H,WU Y,YUAN Z.Probabilistic salient object contour detection based on superpixels［C］//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2013:3069-3072.
(下转第232页)
(上接第225页)
［16］ALPERT S,GALUN M,BRANDT A,et al.Image segmentation by probabilistic bottom-up aggregation and cue integration［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):315-327.
［17］YAN Q,XU L,SHI J,et al.Hierarchical saliency detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:1155-1162.
［18］RAHTU E,KANNALA J,SALO M,et al.Segmenting salient objects from images and videos［C］//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2010:366-379.
［19］YANG C,ZHANG L,LU H.Graph-regularized saliency detection with convex-hull-based center prior［J］.IEEE Signal Processing Letters,2013,20(7):637-640.

[1]	宋梦柯, 郑元超, 陈程立诏. 基于深度质量感知和分层特征引导的RGB-D显著性检测[J]. 计算机工程, 2023, 49(5): 255-261,268.
[2]	孙欣悦, 李庆忠. 基于小波变换的水下显著性目标快速检测算法[J]. 计算机工程, 2023, 49(4): 249-255.
[3]	宋佳, 陈程立诏. 基于多流网络一致性的视频显著性检测[J]. 计算机工程, 2022, 48(2): 215-223.
[4]	董亚超, 刘宏哲, 徐成. 基于显著性多尺度特征协作融合的行人重识别方法[J]. 计算机工程, 2021, 47(6): 234-244,252.
[5]	郭伟, 洪倩. 基于边界和中心关系的显著性检测方法[J]. 计算机工程, 2020, 46(6): 241-247.
[6]	张驰, 谭南林, 李国正, 苏树强. 基于多级特征的红外图像行人检测算法[J]. 计算机工程, 2020, 46(4): 260-265.
[7]	蔡凯, 李新福, 田学东. 基于视觉注意力分析的3D内容生成方法[J]. 计算机工程, 2020, 46(4): 266-272.
[8]	董本志,陈迪,景维鹏. 基于对称性区域过滤的显著性区域检测方法[J]. 计算机工程, 2019, 45(5): 216-221.
[9]	姚钊健,谭台哲. 结合凸包先验与流形排序的显著性检测算法[J]. 计算机工程, 2018, 44(9): 203-211,217.
[10]	高东东,张新生. 基于空间卷积神经网络模型的图像显著性检测[J]. 计算机工程, 2018, 44(5): 240-245.
[11]	刘小丹,岳爽. 基于视觉注意的遥感图像森林植被纹理分割[J]. 计算机工程, 2018, 44(4): 274-280.
[12]	孔英会,尹紫薇,车辚辚. 基于稀疏学习与显著性的人脸识别方法研究[J]. 计算机工程, 2018, 44(2): 271-276.
[13]	段锁林,严翔,朱方,史兵. 基于改进混合高斯模型与六帧差分的目标检测算法[J]. 计算机工程, 2017, 43(7): 234-238.
[14]	邓凝旖,沈志强,郭跃飞. 基于类别先验与深度神经网络特征的显著性检测[J]. 计算机工程, 2017, 43(6): 225-229.
[15]	余超超,侯进,侯长征. 基于显著图与傅里叶描述子的交通标志检测[J]. 计算机工程, 2017, 43(5): 28-34.

选择文件类型/文献管理软件名称

选择包含的内容

融合前景信息的背景模板优化显著性检测算法

Background Template Optimization Saliency Detection Algorithm Fusing with Foreground Information

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 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

融合前景信息的背景模板优化显著性检测算法

Background Template Optimization Saliency Detection Algorithm Fusing with Foreground Information

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 15

编辑推荐

Metrics

本文评价