首页 > 论文 > 激光与光电子学进展 > 55卷 > 12期(pp:121003--1)

结合深度学习的图像显著目标检测

Image Salient Object Detection Combined with Deep Learning

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

摘要

基于一种改进的跨层级特征融合的循环全卷积神经网络, 提出了一种结合深度学习的图像显著目标检测算法。通过改进的深度卷积网络模型对输入图像进行特征提取, 利用跨层级联合框架进行特征融合, 生成了高层语义特征的初步显著图; 将初步显著图与图像底层特征融合进行显著性传播以获取结构信息; 利用条件随机场对显著性传播结果进行优化, 得到了最终显著图。利用大型数据集将所提算法与其他多种算法进行了测试对比, 研究结果表明, 在对复杂场景图像的显著目标检测方面, 所提算法稳健性更好, 显著目标检测的完整性提升, 背景得到了更有效的抑制。

Abstract

An algorithm of image salient object detection combined with deep learning is proposed based on an improved recurrent deep convolutional neural network with the cross-level feature fusion. The feature extraction of input images is performed through this improved recurrent deep convolutional neural network model. The cross-level joint framework is used for the feature fusion and thus the initial salient maps with high-level semantics features are generated. The saliency propagation is applied to the fusion of initial salient maps and low-level image features, and thus the structural information is obtained. The saliency propagation results are further optimized with the conditional random field and the final salient maps are realized. With the massive datasets, the proposed algorithm is tested and compared with other algorithms. The research results show that the proposed method is more robust than the existing algorithms in the image salient object detection of the complex scenes. Moreover, the integrity of the significant target detection is improved and the background is suppressed effectively.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop55.121003

所属栏目:图像处理

基金项目:四川省科技支撑计划(2016GZ0194)

收稿日期:2018-05-14

修改稿日期:2018-06-05

网络出版日期:2018-06-08

作者单位    点击查看

赵恒:西南交通大学机械工程学院, 四川 成都 610031
安维胜:西南交通大学机械工程学院, 四川 成都 610031

联系人作者:赵恒(zhlance@foxmail.com); 安维胜(anweisheng@home.swjtu.edu.cn);

【1】Zheng L, Wang S J, Liu Z Q, et al. Fast image retrieval: Query pruning and early termination[J]. IEEE Transactions on Multimedia, 2015, 17(5): 648-659.

【2】Zhu J Y, Wu J J, Wei Y C. Unsupervised object class discovery via saliency-guided multiple class learning[J]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2012: 3218-3225.

【3】Liu F, Shen T S, Lou S L, et al. Deep network saliency detection based on global model and local optimization[J]. Acta Optica Sinica, 2017, 37(12): 1215005.
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[J]. 光学学报, 2017, 37(12): 1215005.

【4】Hadizadeh H, Bajic I V. Saliency-aware video compression[J]. IEEE Transactions on Image Processing, 2014, 23(1): 19-33.

【5】Chen Z H, Wang H Z, Zhang L M, et al. Visual saliency detection based on homology similarity and an experimental evaluation[J]. Journal of Visual Communication and Image Representation, 2016, 40: 251-264.

【6】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.

【7】Borji A, Cheng M M, Jiang H Z, et al. Salient object detection: A benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5706-5722.

【8】Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection[J]. Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, 2009: 1597-1604.

【9】Aytekin C, Kiranyaz S, Gabbouj M. Automatic object segmentation by quantum cuts[J]. Proceeding of IEEE International Conference on Pattern Recognition, 2014: 112-117.

【10】Cheng M M, Mitra N J, Huang X L, et al. Global contrast based salient region detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 569-582.

【11】Mou L, Zhang X W, Zhang Z, et al. Saliency detection optimization method in natural scene[J]. Laser & Optoelectronics Progress, 2016, 53(12): 121501.
牟丽, 张学武, 张卓, 等. 自然场景下的显著性检测优化方法[J]. 激光与光电子学进展, 2016, 53(12): 121501.

【12】Liu N, Han J W, Zhang D W, et al. Predicting eye fixations using convolutional neural networks[J]. Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, 2015: 362-370.

【13】Lin C, He B W, Dong S S. An indoor object fast detection method based on visual attention mechanism of fusion depth information in RGB image[J]. Chinese Journal of Lasers, 2014, 41(11): 1108005.
林昌, 何炳蔚, 董升升. 融合深度信息的室内RGB图像视觉显著物体快速检测方法[J]. 中国激光, 2014, 41(11): 1108005.

【14】Wang J D, Jiang H Z, Yuan Z J, et al. Salient object detection: A discriminative regional feature integration approach[J]. International Journal of Computer Vision, 2017, 123(2): 251-268.

【15】Li G B, Yu Y Z. Visual saliency based on multiscale deep features[J]. Proceeding of IEEE Computer Vision and Pattern Recognition, 2015: 5455-5463.

【16】Wang L Z, Wang L J, Lu H C, et al. Saliency detection with recurrent fully convolutional networks[C]. European Conference on Computer Vision, 2016: 825-841.

【17】Li X, Zhao L M, Wei L N, et al. Deep saliency: Multi-task deep neural network model for salient object detection[J]. IEEE Transactions on Image Processing, 2016, 25(8): 3919-3930.

【18】Lee G, Tai Y W, Kim J. Deep saliency with encoded low level distance map and high level features[J]. Proceeding of IEEE Computer Vision and Pattern Recognition, 2016: 660-668.

【19】Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[EB/OL]. (2015-04-10)[2018-03-02]. https://arxiv.org/abs/1409.1556.

【20】Li G B, Yu Y Z. Deep contrast learning for salient object detection[J]. Proceeding of IEEE Computer Vision and Pattern Recognition, 2016: 478-487.

【21】Krhenbühl P, Koltun V. Efficient inference in fully connected CRFs with Gaussian edge potentials[EB/OL]. (2012-10-20)[2018-03-02]. https://arxiv.org/abs/1210.5644.

【22】Zhang S L, Xie L B. Salient object detection based on all convolutional feature combination[J]. Laser & Optoelectronics Progress, 2018, 55(10):101502.
张松龙, 谢林柏. 基于全部卷积特征融合的显著性检测[J ].激光与光电子学进展, 2018, 55(10):101502.

【23】Achanta R, Shaji A, Smith K, et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.

【24】Jia Y Q, Shelhamer, Donahue J, et al. Caffe: Convolutional architecture for fast feature embedding[EB/OL]. (2014-06-20)[2018-03-02]. https://arxiv.org/abs/1408.5093.

引用该论文

Zhao Heng,An Weisheng. Image Salient Object Detection Combined with Deep Learning[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121003

赵恒,安维胜. 结合深度学习的图像显著目标检测[J]. 激光与光电子学进展, 2018, 55(12): 121003

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