[1]田旭,彭飞,刘飞,等.基于金字塔特征与边缘优化的显著性对象检测[J].郑州大学学报(工学版),2022,43(02):35-43.[doi:10.13705/j.issn.1671-6833.2022.02.003]
　TIAN Xu,PENG Fei,LIU Fei,et al.Salient Object Detection Based on Pyramid Features and Edge Optimization[J].Journal of Zhengzhou University (Engineering Science),2022,43(02):35-43.[doi:10.13705/j.issn.1671-6833.2022.02.003]
点击复制

基于金字塔特征与边缘优化的显著性对象检测()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
43
期数:
2022年02期
页码:
35-43
栏目:
出版日期:
2022-02-27

文章信息/Info

Title:
Salient Object Detection Based on Pyramid Features and Edge Optimization
作者:
田旭1; 彭飞1; 刘飞1; 陈庆文2; 闫馨宇3; 4
国网青海省电力公司经济技术研究院;中国电建集团西北勘测设计研究院有限公司;天津大学智能与计算学部;天津大学天津机器学习重点实验室;

Author(s):
TIAN Xu1;  PENG Fei1;  LIU Fei1;  CHEN Qingwen2;  YAN Xinyu3; 4
1.State Grid Qinghai Electric Power Company Economic and Technical Research Institute, Xining 810000, China;
2.Northwest Engineering Corporation Limited, Xi′an 710065, China; 
3.College of Intelligence and Computing, Tianjin University, Tianjin 300350, China;
4.Tianjin Key Lab of Machine Learning, Tianjin University, Tianjin 300350, China
关键词:
Keywords:
salient object detection;  multi-scale feature extraction;  fully convolutional networks;  edge feature extraction;  deep learning
分类号:
TP391.4
DOI:
10.13705/j.issn.1671-6833.2022.02.003
文献标志码:
A
摘要:
针对图像显著性对象检测领域中多尺度特征提取不充分’对象边缘模糊等问题!提出了一个端到端的基于注意力嵌入的金字塔特征以及渐进边缘优化的显著性对象检测模型" 首先!设计了由多个扩张卷积构成的注意力嵌入的密集空洞金字塔模块%DPJDH:& !在不减小特征分辨率的前提下!得到丰富且有效的多级多尺度特征#其次!为了解决显著性对象边缘模糊的问题!提出了渐进边缘优化模块% 0PI:& !在特征恢复分辨率的过程中逐步补充空间细节信息!使模型检测出的显著对象能够拥有清晰的边缘轮廓" 在J[R0)RP’P+00J’J[R)I:2IK’Yd[)Q0’HD0+DZ)0 $ 个显著性领域公开的数据集上与其他"% 种已有的先进方法在’ 个常用指标下进行了比较!结果表明$所提方法能够得到更加准确’边缘更加清晰的显著性结果" 此外!自对比实验也充分证明了提出的注意力嵌入的密集空洞金字塔模块和渐进边缘优化模块的有效性"
Abstract:
To solve the problems of insufficient multiscale feature extraction and object edge blur in image-based salient object detection, an end-to-end salient object detection model was proposed based on attention embedding pyramid feature and stepped edge optimization. Firstly, the attention embedded dense atrous Pyramid Module (AEDAPM) composed of multiple dilated convolutions was designed to obtain rich and effective multi-level multi-scale features without reducing the feature resolution； Secondly, in order to solve the problem of blurring the edges of salient objects, a stepped edge optimization module (SEOM) is proposed, which gradually supplements spatial detail information during the process of feature restoration resolution, so that the salient objects detected by the model could have clear edge contours. The method in this paper was compared with 12 state-of-the-art saliency methods under 3 common indicators on 5 public datasets, such as DUTS-TE, ECSSD, DUT-OMRON, HKU-IS, and PASCAL-S. The experimental results show that the method proposed in this paper can obtain more accurate and clearer saliency results. In addition, the ablation study also fully proved the effectiveness of the AEDAPM and the SEOM proposed in this study.

参考文献/References:

［1］ 杨文柱，刘晴，王思乐，等．基于深度卷积神经网络 的羽 绒 图 像 识 别［J］． 郑 州 大 学 学 报 ( 工 学 版) ， 2018，39( 2) : 11－17． 

［2］ 张震，李浩方，李孟洲，等．改进 YOLOv3 算法与人体 信息数据融合的视频监控检测方法［J］．郑州大学 学报( 工学版) ，2021，42( 1) : 28－34． 
［3］ BOＲJI A，FＲINTＲOP S，SIHITE D N，et al．Adaptive object tracking by learning background context［C］/ / 2012 IEEE Computer Society Conference on Computer Vision and Pattern Ｒecognition Workshops． Piscataway: IEEE，2012: 23－30． 
［4］ 魏宏彬，张端金，杜广明，等．基于改进型 YOLO v3 的蔬 菜 识 别 算 法［J］． 郑 州 大 学 学 报 ( 工 学 版) ， 2020，41( 2) : 7－12，31． 
［5］ LONG J，SHELHAMEＲ E，DAＲＲELL T． Fully convolutional networks for semantic segmentation［C］/ /2015 IEEE Conference on Computer Vision and Pattern Ｒecognition ( CVPＲ ) ． Piscataway: IEEE，2015: 3431 －3440． 
［6］ YANG M K，YU K，ZHANG C，et al． DenseASPP for semantic segmentation in street scenes ［C］/ /2018 IEEE/CVF Conference on Computer Vision and Pattern Ｒecognition． Piscataway: IEEE，2018: 3684 －3692． 
［7］ ITTI L，KOCH C，NIEBUＲ E． A model of saliencybased visual attention for rapid scene analysis［J］． IEEE transactions on pattern analysis and machine intelligence，1998，20( 11) : 1254－1259． 
［8］ HOU X D，ZHANG L Q．Saliency detection: a spectral residual approach［C］/ /2007 IEEE Conference on Computer Vision and Pattern Ｒecognition．Piscataway: IEEE，2007: 1－8． 
［9］ ACHANTA Ｒ，HEMAMI S，ESTＲADA F，et al． Frequency-tuned salient region detection［C］/ /2009 IEEE Conference on Computer Vision and Pattern Ｒecognition．Piscataway: IEEE，2009: 1597－1604． 
［10］ XIE Y，LU H，YANG M H．Bayesian saliency via low and mid level cues［J］． IEEE transactions on image processing，2013，22( 5) : 1689－1698．
 ［11］ FAN D P，CHENG M M，LIU J J，et al． Salient objects in clutter: bringing salient object detection to the foreground ［C］/ / European Conference on Computer Vision． Springer: Cham，2018: 438－445． 
［12］ 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) ．Piscataway: IEEE，2015: 3183－3192． 
［13］ ZHANG P P，WANG D，LU H C，et al．Learning uncertain convolutional features for accurate saliency detection［C］/ /2017 IEEE International Conference on Computer Vision ( ICCV) ．Piscataway: IEEE，2017: 212 －221． 
［14］ LI X，ZHAO L M，WEI L N，et al．DeepSaliency: multitask deep neural network model for salient object detection［J］．IEEE transactions on image processing， 2016，25( 8) : 3919－3930． 
［15］ HU P，SHUAI B，LIU J，et al．Deep level sets for salient object detection［C］/ /2017 IEEE Conference on Computer Vision and Pattern Ｒecognition ( CVPＲ) ．Piscataway: IEEE，2017: 540－549． 
［16］ WANG W G，SHEN J B，DONG X P，et al． Salient object detection driven by fixation prediction［C］/ / 2018 IEEE/CVF Conference on Computer Vision and Pattern Ｒecognition．Piscataway: 2018: 1711－1720． 
［17］ WANG L J，LU H C，WANG Y F，et al． Learning to detect salient objects with image-level supervision ［C］/ /2017 IEEE Conference on Computer Vision and Pattern Ｒecognition ( CVPＲ) ．Piscataway: IEEE，2017: 3796－3805． 
［18］ LI G B，YU Y Z．Visual saliency based on multiscale deep features ［C］/ /2015 IEEE Conference on Computer Vision and Pattern Ｒecognition ( CVPＲ) ． Piscataway: IEEE，2015: 5455－5463． 
［19］ 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．Piscataway: IEEE，2013: 3166－3173． 
［20］ LI Y，HOU X D，KOCH C，et al．The secrets of salient object segmentation［C］/ /2014 IEEE Conference on Computer Vision and Pattern Ｒecognition．Piscataway: IEEE，2014: 280－287．
 ［21］ YAN Q，XU L，SHI J P，et al． Hierarchical saliency detection［C］/ /2013 IEEE Conference on Computer Vision and Pattern Ｒecognition． Piscataway: IEEE， 2013: 1155－1162． 
［22］ ZHANG P P，WANG D，LU H C，et al．Amulet: aggregating multi-level convolutional features for salient object detection［C］/ /2017 IEEE International Conference on Computer Vision ( ICCV) ．Piscataway: IEEE， 2017: 202－211．
 ［23］ LI G B，YU Y Z． Deep contrast learning for salient object detection［C］/ /2016 IEEE Conference on Computer Vision and Pattern Ｒecognition ( CVPＲ) ．Piscataway: IEEE，2016: 478－487． 
［24］ LEE G，TAI Y W，KIM J．Deep saliency with encoded low level distance map and high level features［C］/ / 2016 IEEE Conference on Computer Vision and Pattern Ｒecognition ( CVPＲ) ． Piscataway: IEEE，2016: 660 －668． 
［25］ WANG T T，ZHANG L H，LU H C，et al． Kernelized subspace ranking for saliency detection［M］．Computer Vision-ECCV 2016．Cham: Springer International Publishing，2016: 450－466． 
［26］ 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) ． Piscataway: IEEE，2015: 1265 －1274． 
［27］ ZHANG L，ZHANG J M，LIN Z，et al． CapSal: leveraging captioning to boost semantics for salient object detection［C］/ /2019 IEEE/CVF Conference on Computer Vision and Pattern Ｒecognition ( CVPＲ) ． Piscataway: IEEE，2019: 6017－6026． 
［28］ 刘尚旺，赵欣莹，杨磊．基于全局和局部信息融合的 显著性检测［J］． 河南师范大学学报 ( 自 然 科 学 版) ，2020，48( 3) : 26－33．

更新日期/Last Update: 2022-02-25