基于多任务深度卷积神经网络的显著性对象检测算法

doi:10.11772/j.issn.1001-9081.2017061633

计算机应用 ›› 2018, Vol. 38 ›› Issue (1): 91-96.DOI: 10.11772/j.issn.1001-9081.2017061633

基于多任务深度卷积神经网络的显著性对象检测算法

杨帆, 李建平, 李鑫, 陈雷霆

电子科技大学计算机科学与工程学院, 成都 611731

收稿日期:2017-07-03 修回日期:2017-08-23 出版日期:2018-01-10 发布日期:2018-01-22
通讯作者: 杨帆
作者简介:杨帆(1987-),男,四川简阳人,博士研究生,主要研究方向:计算机视觉、深度学习、语义级稠密匹配;李建平(1964-),男,湖南祁阳人,教授,博士生导师,博士,主要研究方向:小波信号处理、模式识别、图像处理;李鑫(1986-),男,四川江油人,博士研究生,主要研究方向:计算机视觉、深度学习、人工智能;陈雷霆(1966-),男,重庆人,教授,博士生导师,博士,主要研究方向:图形处理、多媒体技术、图像处理。
基金资助:
国家自然科学基金资助项目（61370073）；国家863计划项目（2015AA016010）。

Salient object detection algorithm based on multi-task deep convolutional neural network

YANG Fan, LI Jianping, LI Xin, CHEN Leiting

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu Sichuan 611731, China

Received:2017-07-03 Revised:2017-08-23 Online:2018-01-10 Published:2018-01-22
Supported by:
This work is partially supported by the National Natural Science Foundation (6157021026), the National High Technology Research and Development Program (863 Program) of China (2015AA016010).

摘要/Abstract

摘要： 针对当前基于深度学习的显著性对象检测算法不能准确保存对象边缘的区域，从而导致检测出的显著性对象边缘区域模糊、准确率不高的问题，提出了一种基于多任务深度学习模型的显著性对象检测算法。首先，基于深度卷积神经网络（CNN），训练一个多任务模型分别学习显著性对象的区域和边缘的特征；然后，利用检测到的边缘生成大量候选区域，再结合显著性区域检测的结果对候选区域进行排序和计算权值；最后提取出完整的显著性图。在三个常用标准数据集上的实验结果表明，所提方法获得了更高的准确率，其中F-measure比基于深度学习的算法平均提高了1.9%，而平均绝对误差（MAE）平均降低了12.6%。

关键词: 显著性对象检测, 深度学习, 边缘检测, 多任务神经网络, 显著图, 卷积神经网络

Abstract: The current deep learning-based salient object detection algorithms fail to produce accurate object boundaries, which makes the regions along object contours blurred and inaccurate. To solve the problem, a salient object detection algorithm based on multi-task deep learning model was proposed. Firstly, based on deep Convolutional Neural Network (CNN), a multi-task model was used to separately learn region and boundary features of a salient object. Secondly, the detected object boundaries were utilized to produce a number of region candidates. After that the region candidates were re-ranked and their weights were computed by combining the results of salient region detection. Finally, the entire saliency map was extracted. The experimental results on three widely-used benchmarks show that the proposed method achieves better accuracy. According to F-measure, the proposed method averagely outperforms the deep learning-based algorithm by 1.9%, while lowers the Mean Absolutely Error (MAE) by 12.6%.

Key words: salient object detection, deep learning, boundary detection, multi-task deep neural network, saliency map, Convolutional Neural Network (CNN)

中图分类号:

杨帆, 李建平, 李鑫, 陈雷霆. 基于多任务深度卷积神经网络的显著性对象检测算法[J]. 计算机应用, 2018, 38(1): 91-96.

YANG Fan, LI Jianping, LI Xin, CHEN Leiting. Salient object detection algorithm based on multi-task deep convolutional neural network[J]. Journal of Computer Applications, 2018, 38(1): 91-96.

参考文献

[1] BORJI A, FRINTROP S, SIHITE D et al. Adaptive object tracking by learning background context[C]//CVPR 2012:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2012:23-30.
[2] ZHU J, WU J, XU Y, et al. Unsupervised object class discovery via saliency-guided multiple class learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(4):826-875.
[3] RUTISHAUSER U, WALTHER D, KOCH C, et al. Is bottom-up attention useful for object recognition?[C]//CVPR 2004:Proceedings of the 2004 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2004:37-44.
[4] YANG F, LI X, CHENG H, et al. Object-aware dense semantic correspondence[C]//CVPR 2017:Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2017:2777-2785.
[5] HE J, FENG J, LIU X, et al. Mobile product search with bag of Hash bits and boundary re-ranking[C]//CVPR 2012:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2012:3005-3012.
[6] ZHAO R, OUYANG W, LI H, et al. Saliency detection by multi-context deep learning[C]//CVPR 2015:Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:1265-1274.
[7] LI G B, YU Y Z. Visual saliency based on multi-scale deep features[C]//CVPR 2015:Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:5455-5463.
[8] LEE G, TAI Y W, KIM J. Deep saliency with encoded low level distance map and high level features[C]//CVPR 2016:Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:660-668.
[9] CHENG M, NILOY 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.
[10] YANG C, ZHANG L, LU H, et al. Saliency detection via graph-based manifold ranking[C]//CVPR 2013:Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:3166-3173.
[11] ZHANG J, SCLAROFF S. Exploiting surroundedness for saliency detection:a Boolean map approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(5):889-902.
[12] ZHU W, LIANG S, WEI Y, et al. Saliency optimization from robust background detection[C]//CVPR 2014:Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:2814-2821.
[13] JIANG H, WANG J, YUAN Z, et al. Salient object detection:a discriminative regional feature integration approach[C]//CVPR 2013:Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:2083-2090.
[14] LI X, YANG F, CHEN L, et al. Saliency transfer:an example-based method for salient object detection[C]//IJCAI 2016:Proceedings of the 2016 International Joint Conference on Artificial Intelligence. Menlo Park:AAAI Press, 2016:3411-3417.
[15] LI X, ZHAO L, WEI L, et al. DeepSaliency:multi-task deep neural network model for salient object detection[J]. IEEE Transactions on Image Processing, 2016, 25(8):3919-3930.
[16] 李岳云,许悦雷,马时平,等.深度卷积神经网络的显著性检测[J].中国图象图形学报,2016,21(1):53-59.(LI Y Y, XU Y L, MA S P, et al. Saliency detection based on deep convolutional neural network[J]. Journal of Image and Graphics, 2016, 21(1):53-59.)
[17] XIE S, TU Z. Holistically-nested edge detection[C]//CVPR 2016:Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:1395-1403.
[18] YANG J, PRICE B, COHEN S, et al. Object contour detection with a fully convolutional encoder-decoder network[C]//CVPR 2016:Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:193-202.
[19] ARBELAEZ P, PONTTUSET J, BSRRO J, et al. Multiscale combinatorial grouping[C]//ICCV 2014:Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:328-335.
[20] XIE Y, LU H, YANG M. Bayesian saliency via low and mid level cues[J]. IEEE Transactions on Image Processing, 2013, 22(5):1689-1698.
[21] 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.
[22] ZHANG J, SCLAROFF S, LIN Z, et al. Minimum barrier salient object detection at 80 FPS[C]//ICCV 2015:Proceedings of the 2015 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2015:1404-1412.
[23] KIM J, HAN D, TAI Y W, et al. Salient region detection via high-dimensional color transform[C]//CVPR 2014:Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:883-890.
[24] LI G, YU Y. Visual saliency based on multiscale deep features[C]//CVPR 2015:Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:5455-5463.

基于多任务深度卷积神经网络的显著性对象检测算法

Salient object detection algorithm based on multi-task deep convolutional neural network

PDF

可视化

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

[1]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[2]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[3]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[4]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[5]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[6]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[7]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[8]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[9]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[10]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[11]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[12]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[13]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[14]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[15]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.