计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (5): 143-150.doi: 10.11896/jsjkx.230100132

• 计算机图形学&多媒体 • 上一篇    下一篇

基于多尺度视觉感知特征融合的显著目标检测方法

吴小琴1, 周文俊1,2, 左承林2, 王一帆1, 彭博1   

  1. 1 西南石油大学计算机科学学院 成都 610500
    2 中国空气动力研究与发展中心结冰与防除冰重点实验室 四川 绵阳 621000
  • 收稿日期:2023-01-30 修回日期:2023-06-29 出版日期:2024-05-15 发布日期:2024-05-08
  • 通讯作者: 周文俊(zhouwenjun@swpu.edu.cn)
  • 作者简介:(xiaoqinswpu@foxmail.com)
  • 基金资助:
    中国空气动力研究与发展中心结冰与防除冰重点实验室开放课题基金资助项目(IADL20210203);四川省自然科学基金(2023NSFSC0504,2023NSFSC1393)

Salient Object Detection Method Based on Multi-scale Visual Perception Feature Fusion

WU Xiaoqin1, ZHOU Wenjun1,2, ZUO Chenglin2, WANG Yifan1, PENG Bo1   

  1. 1 School of Computer Science,Southwest Petroleum University,Chendu 610500,China
    2 Key Laboratory of Icing and Anti/De-icing,China Aerodynamics Research and Development Center,Mianyang,Sichuan 621000,China
  • Received:2023-01-30 Revised:2023-06-29 Online:2024-05-15 Published:2024-05-08
  • About author:WU Xiaoqin,born in 1997,postgra-duate,is a member of CCF(No.N7647G).Her main research interests include compu-ter vision and salient object detection.
    ZHOU Wenjun,born in 1990,Ph.D,assistant professor,master supervisor,is a member of CCF(No.G0634M).His main research interests include compu-ter vision,image perception and understanding.
  • Supported by:
    Key Laboratory of Icing and Anti/De-icing of CARDC(IADL20210203) and Natural Science Foundation of Sichuan Province(2023NSFSC0504,2023NSFSC1393).

PDF (PC)

90

摘要： 显著性物体检测具有重要的理论研究意义和实际应用价值,已在许多计算机视觉应用中发挥了重要作用,如视觉追踪、图像分割、物体识别等。然而,自然环境下显著目标的类别未知、尺度多变依然是物体检测面临的一大挑战,影响着显著目标的检测效果。因此,提出了一种基于多尺度视觉感知特征融合的显著目标检测方法。首先,基于视觉感知显著目标的特性,设计并提取多个图像感知特征。其次,图像感知特征采用多尺度自适应方式,获取特征显著图。然后,将各个显著特征图融合,获得最终的显著目标。该方法基于不同图像感知特征的特点,自适应提取显著目标,能够适应多变的检测目标与复杂的检测环境。实验结果表明,在受自然环境中背景干扰的情况下,该方法能有效检测出未知类别和不同尺度的显著目标。

关键词: 视觉感知特征, 显著目标检测, 多特征融合, 图像分割, 多尺度采样

Abstract: Salient object detection has important theoretical research significance and practical application value,and has played an important role in many computer vision applications,such as visual tracking,image segmentation and object recognition.How-ever,the unknown categories and variable scales of salient objects in natural environments are still a major challenge for salient object detection,which affects the detection results.Therefore,this paper proposes a salient object detection method based on multi-scale visual perception feature fusion.First,based on the characteristics of visual perception,multiple perceptual features are designed and extracted.Second,each perceptual feature adopts a multi-scale adaptive method to obtain feature saliency maps.Finally,each salient feature map is fused to obtain the final salient object.According to the characteristics of different image perception features,the proposed method adaptively extracts feature salient objects,and can adapt to changing detection objects and complex detection environments.Experimental results show that this method can effectively detect salient objects of unknown categories and different scales under the background interference of natural environment.

Key words: Visual perceptual features, Salient object detection, Multi-feature fusion, Image segmentation, Multi-scale sampling

中图分类号: 

  • TP391
[1]BORJI A,CHENG M M,HOU Q,et al.Salient object detec-tion:A survey [J].Computational Visual Media,2019,5(2):117-150.
[2]ULLAH I,JIAN M,HUSSAIN S,et al.A brief survey of visual saliency detection [J].Multimedia Tools and Applications,2020,79(45):34605-34645.
[3]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.
[4]LOU J,WANG H,CHEN L,et al.Exploiting color name space for salient object detection [J].Multimedia Tools and Applications,2020,79(15):10873-10897.
[5]WANG L,LU H,RUAN X,et al.Deep networks for saliency detection via local estimation and global search [C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3183-3192.
[6]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.
[7]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.
[8]CHEN Z,XU Q,CONG R,et al.Global context-aware progres-sive aggregation network for salient object detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:10599-10606.
[9]YE X K,MA C Y,CHEN X W,et al.Global Attention-Based Multi-scale Salient Object Detection Network [J].Computer Applications and Software,2022,39(2):167-173.
[10]朱凯俊.基于改进的 FCM 算法对图像分割的研究和应用[J].重庆工商大学学报(自然科学版),2022,39(5):24-33.
[11]HE Y,XIANG S,ZHOU W,et al.A novel contrast operator for robust object searching [C]//2021 17th International Confe-rence on Computational Intelligence and Security(CIS).IEEE,2021:309-313.
[12]MITTAL A,MOORTHY A K,BOVIK A C.No-referenceimage quality assessment in the spatial domain [J].IEEE Tran-sactions on Image Processing,2012,21(12):4695-4708.
[13]ZHU C,LI G,WANG W,et al.An innovative salient object detection using center-dark channel prior[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops.2017:1509-1515.
[14]HE K,SUN J,TANG X.Single image haze removal using dark channel prior [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,33(12):2341-2353.
[15]ACHANTA R,SHAJI A,SMITH K,et al.SLIC superpixelscompared to state-of-the-art superpixel methods [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[16]CHENG M M,MITRA N J,HUANG X,et al.Global contrast based salient region detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,37(3):569-582.
[17]BORJI A,CHENG M M,JIANG H,et al.Salient object detection:A benchmark [J].IEEE Transactions on Image Proces-sing,2015,24(12):5706-5722.
[18]YAN Q,XU L,SHI J,et al.Hierarchical saliency detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2013:1155-1162.
[19]ACHANTA R,SÜSSTRUNK S.Saliency detection using maximum symmetric surround [C]//2010 IEEE International Conference on Image Processing.IEEE,2010:2653-2656.
[20]ERDEM E,ERDEM A.Visual saliency estimation by nonlinear-ly integrating features using region covariances [J].Journal of Vision,2013,13(4):1-20.
[21]YANG C,ZHANG L,LU H.Graph-regularized saliency detection with convex-hull-based center prior [J].IEEE Signal Processing Letters,2013,20(7):637-640.
[22]MARGOLIN R,TAL A,ZELNIK-MANOR L.What makes a patch distinct? [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2013:1139-1146.
[23]FANG S,LI J,TIAN Y,et al.Learning discriminative subspaces on random contrasts for image saliency analysis [J].IEEE Transactions on Neural Networks and Learning Systems,2016,28(5):1095-1108.
[24]LIU G H,YANG J Y.Exploiting color volume and color diffe-rence for salient region detection [J].IEEE Transactions on Image Processing,2018,28(1):6-16.
[25]LI W,YANG X,LI C,et al.Fast visual saliency based on multi-scale difference of Gaussians fusion in frequency domain [J].IET Image Processing,2020,14(16):4039-4048.
[26]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.
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