首页 > 论文 > 激光与光电子学进展 > 56卷 > 15期(pp:151502--1)

基于深度残差网络与边缘监督学习的显著性检测

Salient Object Detection Based on Deep Residual Networks and Edge Supervised Learning

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对复杂背景下,图像显著区域显著值低和目标边缘表现模糊的问题,提出了基于深度残差网络和多尺度边缘残差学习的显著性检测方法。一方面提出了边缘残差块,使用边缘残差块在深度残差网络的基础上构建边缘监督网络,用于显著图边缘监督学习;另一方面,通过构建基于背景、前景和边缘的三分类模型,训练网络学习边缘特征,使目标边缘更加准确,同时输出采用空洞卷积构建多尺度空洞卷积单元,多尺度地对全局信息进行特征整合提取。最后,将提出的算法在数据集SED2和ECSSD上进行模型简化测试,使用公认评价指标对所提算法和当前多种算法进行评价。实验结果表明,该方法的准确率和召回率更高,对显著目标保持了良好的完整性,且在边缘轮廓区域更好地区分了显著目标与背景。

Abstract

This paper proposes a saliency detection method based on deep residual networks and multiscale edge residual learning to address the problems of low salient values and blurred edges in images having complex backgrounds. Further, an edge residual block is proposed, and an edge residual network is constructed based on the deep residual network using the edge residual block for the salient graph edge supervised learning. In addition, the edge features are learned while training the network by constructing a three-category model based on the background, foreground, and edge, which can make the target edge more accurate. The output uses atrous convolutions to construct a multiscale atrous convolution unit for integrating and extracting the multiscale features based on the global information. Finally, the proposed algorithm is tested in an ablation study using two datasets (SED2 and ECSSD) and compared with various existing algorithms based on the common evaluation indicators. The experimental results demonstrate that the proposed method exhibits high accuracy and recall rate, maintains good integrity for the significant target, and distinguishes the significant target and background from the edge contour regions.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.151502

所属栏目:机器视觉

基金项目:国家自然科学基金(61873112)、国家重点研发项目子课题(2018YFD0400900)、教育部-中国移动科研基金项目(MCM20170204);

收稿日期:2018-12-29

修改稿日期:2019-03-07

网络出版日期:2019-08-01

作者单位    点击查看

时斐斐:江南大学物联网工程学院, 物联网应用技术教育部工程中心, 江苏 无锡 214122
张松龙:江南大学物联网工程学院, 物联网应用技术教育部工程中心, 江苏 无锡 214122
彭力:江南大学物联网工程学院, 物联网应用技术教育部工程中心, 江苏 无锡 214122

联系人作者:时斐斐(6171913022@stu.jiangnan.edu.cn); 彭力(884208590@qq.com);

备注:国家自然科学基金(61873112)、国家重点研发项目子课题(2018YFD0400900)、教育部-中国移动科研基金项目(MCM20170204);

【1】Koch C and Poggio T. Predicting the visual world: silence is golden. Nature Neuroscience. 2(1), 9-10(1999).

【2】Yang C, Zhang L H, Lu H C et al. Saliency detection via graph-based manifold ranking. [C]∥2013 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2013, Portland, OR, USA. New York: IEEE. 13824451, (2013).

【3】Qin Y, Lu H C, Xu Y Q et al. Saliency detection via cellular automata. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 110-119(2015).

【4】Hou X D and Zhang L Q. Saliency detection: a spectral residual approach. [C]∥2007 IEEE Conference on Computer Vision and Pattern Recognition, June 17-22, 2007, Minneapolis, MN, USA. New York: IEEE. 9738156, (2007).

【5】Guo C L, Ma Q and Zhang L M. Spatio-temporal saliency detection using phase spectrum of quaternion Fourier transform. [C]∥2008 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2008, Anchorage, AK, USA. New York: IEEE. 10140020, (2008).

【6】Guo C L and Zhang L M. A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. IEEE Transactions on Image Processing. 19(1), 185-198(2010).

【7】Liu T, Sun J, Zheng N N et al. Learning to detect a salient object. [C]∥2007 IEEE Conference on Computer Vision and Pattern Recognition, June 17-22, 2007, Minneapolis, MN, USA. New York: IEEE. 9737916, (2007).

【8】Liu T, Zheng N N, Ding W et al. Video attention: learning to detect a salient object sequence. [C]∥2008 19th International Conference on Pattern Recognition, December 8-11, 2008, Tampa, FL, USA. New York: IEEE. 10457751, (2008).

【9】Tong N, Lu H C, Ruan X et al. Salient object detection via bootstrap learning. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 1884-1892(2015).

【10】Xu L, Cui G M, Zheng C P et al. Fusion method of visible and infrared images based on multi-scale decomposition and saliency region extraction. Laser & Optoelectronics Progress. 54(11), (2017).
许磊, 崔光茫, 郑晨浦 等. 基于多尺度分解和显著性区域提取的可见光红外图像融合方法. 激光与光电子学进展. 54(11), (2017).

【11】Zhu W J, Liang S, Wei Y C et al. Saliency optimization from robust background detection. [C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: IEEE. 2814-2821(2014).

【12】Zhao R, Ouyang W L, Li H S et al. Saliency detection by multi-context deep learning. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 1265-1274(2015).

【13】Zhang X N, Wang T T, Qi J Q et al. Progressive attention guided recurrent network for salient object detection. [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 714-722(2018).

【14】Li G B and Yu Y Z. Deep contrast learning for salient object detection. [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 478-487(2016).

【15】Bi L H and Liu Y C. Plant leaf image recognition based on improved neural network algorithm. Laser & Optoelectronics Progress. 54(12), (2017).
毕立恒, 刘云潺. 基于改进神经网络算法的植物叶片图像识别研究. 激光与光电子学进展. 54(12), (2017).

【16】He K M, Zhang X Y, Ren S Q et al. Deep residual learning for image recognition. [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 770-778(2016).

【17】Dai J F, Li Y, He K M et al. R-FCN: object detection via region-based fully convolutional networks. [C]∥Proceedings of the 30th International Conference on Neural Information Processing Systems, December 5-10, 2016, Barcelona, Spain. USA: Curran Associates Inc. 379-387(2016).

【18】Lin G S, Milan A, Shen C H et al. RefineNet: multi-path refinement networks for high-resolution semantic segmentation. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 5168-5177(2017).

【19】Feichtenhofer C, Pinz A and Wildes R P. Spatiotemporal multiplier networks for video action recognition. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 7445-7454(2017).

【20】Mahendran A and Vedaldi A. Understanding deep image representations by inverting them. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 5188-5196(2015).

【21】Li G B and Yu Y Z. Visual saliency based on multiscale deep features. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 5455-5463(2015).

【22】Chen L C, Papandreou G, Kokkinos I et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence. 40(4), 834-848(2018).

【23】Jia Y Q, Shelhamer E, Donahue J et al. Caffe:convolutional architecture for fast feature embedding. [C]∥Proceedings of the 22nd ACM international conference on Multimedia, November 3-7, 2014, Orlando, Florida, USA. New York: ACM. 675-678(2014).

【24】Liu F, Shen T S, Lou S L et al. Deep network saliency detection based on global model and local optimization. Acta Optica Sinica. 37(12), (2017).
刘峰, 沈同圣, 娄树理 等. 全局模型和局部优化的深度网络显著性检测. 光学学报. 37(12), (2017).

【25】Wang L Z, Wang L J, Lu H C et al. Saliency detection with recurrent fully convolutional networks. ∥Leibe B, Matas J, Sebe N, et al. Computer Vision-ECCV 2016. Cham: Springer. 825-841(2016).

【26】Wang L J, Lu H C, Ruan X et al. Deep networks for saliency detection via local estimation and global search. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 3183-3192(2015).

【27】Zhao H and An W S. Image salient object detection combined with deep learning. Laser & Optoelectronics Progress. 55(12), (2018).
赵恒, 安维胜. 结合深度学习的图像显著目标检测. 激光与光电子学进展. 55(12), (2018).

【28】Liu N and Han J W. DHSNet: deep hierarchical saliency network for salient object detection. [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 678-686(2016).

【29】Li G B and Yu Y Z. Deep contrast learning for salient object detection. [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 478-487(2016).

引用该论文

Shi Feifei,Zhang Songlong,Peng Li. Salient Object Detection Based on Deep Residual Networks and Edge Supervised Learning[J]. Laser & Optoelectronics Progress, 2019, 56(15): 151502

时斐斐,张松龙,彭力. 基于深度残差网络与边缘监督学习的显著性检测[J]. 激光与光电子学进展, 2019, 56(15): 151502

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF