Salient Object Detection Based on Stack Edge-Aware Module

被引：0
|
作者：
Yang J. [1 ]
Hu X. [1 ]
Xiang J. [1 ]
机构：
[1] School of Electronics and Communication Engineering, Guang zhou University, Guangzhou
来源：
Hu, Xiao (huxiao@gzhu.edu.cn) | 1600年 / Science Press卷 / 33期
基金：
中国国家自然科学基金;
关键词：
Edge-Aware Module; High-Level Semantic Information; Low-Level Texture Information; Salient Object Detection(SOD);
D O I：
10.16451/j.cnki.issn1003-6059.202010005
中图分类号：
学科分类号：
摘要：
To improve the poor performance of the existing salient object detection algorithms in edge perception, a salient object detection algorithm based on stack edge-aware module is proposed to utilize high-level semantic information and low-level texture information effectively. Multi-scale backbone network is utilized as the backbone network to extract the multi-scale and multi-target salient features. In stacked edge-aware module, the high-level information and low-level information of the image are combined in an asymmetric manner to enhance the area of the salient object. The network outputs salient object detection results. The experiments on five public datasets indicate that the proposed algorithm produces better detection results and better performance in objective evaluation indicators and subjective visual effects. © 2020, Science Press. All right reserved.
引用
收藏
页码：906 / 916
页数：10
相关论文
共 32 条
  • [1] LEE H, KIM D., Salient Region-Based Online Object Tracking, Proc of the IEEE Winter Conference on Applications of Computer Vision, pp. 1170-1177, (2018)
  • [2] AYE H M, ZAW S M M., Salient Object Based Action Recognition Using Histogram of Changing Edge Orientation(HCEO), Proc of the 15th IEEE International Conference on Software Engineering Research, Management and Applications, pp. 115-122, (2017)
  • [3] BAO L, LU J J, LI Y, Et al., Image Saliency Detection Based on Global and Local Information Fusion, Pattern Recognition and Artificial Intelligence, 28, 3, pp. 275-281, (2015)
  • [4] WANG Y Z, PENG G H, YAN W D., Salient Object Detection Based on Manifold Ranking and Co-connectivity, Pattern Recognition and Artificial Intelligence, 32, 1, pp. 82-93, (2019)
  • [5] SHELHAMER E, LONG J, DARRELL T., Fully Convolutional Networks for Semantic Segmentation, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440, (2015)
  • [6] WANG W G, LAI Q X, FU H Z, Et al., Salient Object Detection in the Deep Learning Era: An In-Depth Survey[J/OL]
  • [7] LI G B, YU Y Z., Visual Saliency Based on Multiscale Deep Features, Proc of the IEEE Conference on Computer Vision and Pa-ttern Recognition, pp. 5455-5463, (2015)
  • [8] ZHANG P P, WANG D, LU H C, Et al., Learning Uncertain Convolutional Features for Accurate Saliency Detection, Proc of the IEEE International Conference on Computer Vision, pp. 212-221, (2017)
  • [9] LUO Z M, MISHRA A, ACHKAR A, Et al., Non-local Deep Features for Salient Object Detection, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6593-6601, (2017)
  • [10] ZHANG P P, WANG D, LU H C, Et al., Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection, Proc of the IEEE International Conference on Computer Vision, pp. 202-211, (2017)
1234