计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (12): 166-174.doi: 10.11896/jsjkx.221100203

• 计算机图形学&多媒体 • 上一篇    下一篇

基于特征融合与边界修正显著性目标检测

陈慧1,2, 彭力1   

  1. 1 江南大学物联网工程学院 江苏 无锡 214121
    2 无锡职业技术学院物联网技术学院 江苏 无锡 214121
  • 收稿日期:2022-11-24 修回日期:2023-03-07 出版日期:2023-12-15 发布日期:2023-12-07
  • 通讯作者: 彭力(244785662@qq.com)
  • 作者简介:(13489959@qq.com)

Feature Fusion and Boundary Correction Network for Salient Object Detection

CHEN Hui1,2, PENG Li1   

  1. 1 School of Internet of Things Engineering,Jiangnan University,Wuxi,Jiangsu 214121,China
    2 College of Internet of Things of Technology,Wuxi Institute of Technology,Wuxi,Jiangsu 214121,China
  • Received:2022-11-24 Revised:2023-03-07 Online:2023-12-15 Published:2023-12-07
  • About author:CHEN Hui,born in 1980,postgraduate,associate professor.Her main research interests include electronic information and visual Internet of Things.
    PENG Li,born in 1967,Ph.D,professor.His main research interests include networked collaborative control and vi-sual Internet of Things.

PDF (PC)

2151

摘要： 显著性目标检测旨在寻找图像中的视觉显著区域。现有的显著性目标检测方法已经展现出强大的优势,但依然在尺度感知和边界预测方面具有局限性。首先,各类场景中的显著目标存在诸多尺度,使算法难以适应不同尺度变化。其次,显著目标往往具有复杂的轮廓,这使边界像素点的检测变得更为困难。针对以上问题,文中提出了基于特征融合与边界修正的显著性目标检测网络,该网络基于特征金字塔,提取了不同层次显著特征。首先针对目标的尺度多样性设计了由多尺度特征解码模块组成的特征融合解码器,通过逐层融合相邻层特征,提高了网络对目标尺度的感知能力。同时设计了边界修正模块学习显著目标的轮廓特征,以生成边界清晰的高质量显著图。在5个常用显著性目标检测数据集上进行实验,结果表明所提算法在平均绝对误差、F指标和S指标3项定量指标上均能取得较优的结果。

关键词: 显著性目标检测, 深度学习, 卷积神经网络, 特征融合, 边界修正

Abstract: Saliency object detection aims to find visually significant areas in an image.Existing salient object detection methods have shown strong advantages,but they are still limited by scale perception and boundary prediction.First of all,there are many scales of salient objects in various scenes,which makes it difficult for the algorithm adapt to different scale changes.Secondly,salient objects often have complex contours,which makes detection of boundary pixels more difficult.To solve these problems,this paper proposes a feature fusion and boundary correction network for salient object detection.This network extracts salient features at different levels on the feature pyramid.Firstly,a feature fusion decoder composed of multi-scale feature decoding modules is designed for the scale diversity of the object.By fusing the features of adjacent layer by layer,the network's ability to perceive the scale is improved.At the same time,a boundary correction module is designed to learn the contour features of salient objects to generate high quality salient images with clear boundaries.Experimental results on five commonly used salient object detection datasets show that the proposed algorithm can achieve better results on the average absolute error,F index and S index.

Key words: Salient object detection, Deep learning, Convolutional neural network, Feature fusion, Boundary correction

中图分类号: 

  • TP391.4
[1]REN Z,GAO S,CHIA LT,et al.Region-based saliency detection and its application in object recognition[J].IEEE Transactions on Circuits and Systems for Video Technology,2013,24(5):769-779.
[2]WEI Y,FENG J,LIANG X,et al.Object region mining with adversarial erasing:A simple classification to semantic segmentation approach[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1568-1576.
[3]LIANG P,PANG Y,LIAO C,et al.Adaptive objectness for object tracking[J].IEEE Signal Processing Letters,2016,23(7):949-53.
[4]MA Y F,ZHANG H J.Contrast-based image attention analysisby using fuzzy growing[C]//Proceedings of the Eleventh ACM International Conference on Multimedia.2003:374-381.
[5]JIANG H,WANG J,YUAN Z,et al.Automatic salient objectsegmentation based on context and shape prior[C]//Procee-dings of British Machine Vision Conference.2011.
[6]ZHU W,LIANG S,WEI Y,et al.Saliency optimization from robust background detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:2814-2821.
[7]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3431-3440.
[8]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2117-2125.
[9]PAN M Y,SONG H H,ZHANG K H,et al.Learning Global Guided Progressive Feature Aggregation Lightweight Network for Salient Object Detection[J].Computer Science,2021,48(6):103-109.
[10]WU J Y,YANG S,DU J,et al.Review of Bottom-up Salient Object Detection[J].Computer Science,2019,46(3):48-52.
[11]BADRINARAYANAN V,KENDALL A,CIPOLLA R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[12]LIU J J,HOU Q,LIU Z A,et al.Poolnet+:Exploring the potential of pooling for salient object detection[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence.2022.
[13]ZHOU H,XIE X,LAI J H,et al.Interactive two-stream decoder for accurate and fast saliency detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:9141-9150.
[14]WU Y H,LIU Y,ZHANG L,et al.EDN:Salient object detection via extremely-downsampled network[J].IEEE Transactions on Image Processing,2022,31:3125-3136.
[15]WU Z,LI S,CHEN C,et al.Salient Object Detection via Dynamic Scale Routing[J].IEEE Transactions on Image Proces-sing,2022,31:6649-6663.
[16]QIN X,ZHANG Z,HUANG C,et al.Basnet:Boundary-awaresalient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:7479-7489.
[17]WEI J,WANG S,HUANG Q.F3Net:Fusion,Feedback and Focus for Salient Object Detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:12321-12328.
[18]CHEN Z,ZHOU H,LAI J,et al.Contour-aware loss:Boundary-aware learning for salient object segmentation[J].IEEE Tran-sactions on Image Processing,2020,30:431-443.
[19]CANNY J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986(6):679-698.
[20]SHI J,YAN Q,XU L,et al.Hierarchical image saliency detection on extended CSSD[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,38(4):717-729.
[21]LI Y,HOU X,KOCH C,et al.The secrets of salient object segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:280-287.
[22]LI G,YU Y.Deep contrast learning for salient object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:478-487.
[23]WANG L,LU H,WANG Y,et al.Learning to detect salient objects with image-level supervision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:136-145.
[24]YANG C,ZHANG L,LU H,et al.Saliency detection via graph-based manifold ranking[C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2013:3166-3173.
[25]EVERINGHAM M,ESLAMI S,VAN GOOL L,et al.The pascal visual object classes challenge:A retrospective[J].International Journal of Computer Vision,2015,111(1):98-136.
[26]XIAO J,HAYS J,EHINGER K A,et al.Sun database:Large-scale scene recognition from abbey to zoo[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.IEEE,2010:3485-3492.
[27]DENG J,DONG W,SOCHER R,et al.Imagenet:A large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2009:248-255.
[28]PANG Y,ZHAO X,ZHANG L,et al.Multi-scale interactivenetwork for salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:9413-9422.
[29]FAN D P,CHENG M M,LIU Y,et al.Structure-measure:Anew way to evaluate foreground maps[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:4548-4557.
[30]WANG W,SHEN J,CHENG M M,et al.An iterative and co-operative top-down and bottom-up inference network for salient object detection[C]//Proceedings of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.2019:5968-5977.
[31]FENG M,LU H,DING E.Attentive feedback network forboundary-aware salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:1623-1632.
[32]LIU J J,HOU Q,CHENG M M,et al.A simple pooling-based design for real-time salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:3917-3926.
[33]WU Z,SU L,HUANG Q.Cascaded partial decoder for fast and accurate salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:3907-3916.
[34]CHEN Z,XU Q,CONG R,et al.Global context-aware progressive aggregation network for salient object detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:10599-10606.
[35]ZHAO X,PANG Y,ZHANG L,et al.Suppress and balance:A simple gated network for salient object detection[C]//Procee-dings of European Conference on Computer Vision.Springer,2020:35-51.
[36]PIAO Y,WANG J,ZHANG M,et al.MFNet:Multi-filter Directive Network for Weakly Supervised Salient Object Detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:4136-4145.
[37]FENG M,LU H,YU Y.Residual learning for salient object detection[J].IEEE Transactions on Image Processing,2020,29:4696-4708.
[38]CHEN X,ZHANG Q,ZHANG L.Edge-aware salient object detection network via context guidance[J].Image and Vision Computing,2021,110:104166.
[39]TONG N,LU H,ZHANG Y,et al.Salient object detection via global and local cues[J].Pattern Recognition,2015,48(10):3258-3267.
[40]MEI H,LIU Y,WEI Z,et al.Exploring dense context for salient object detection[C]//IEEE Transactions on Circuits and Systems for Video Technology.2021.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发