边缘信息引导的伪装目标检测
DOI:
作者:
作者单位:

1.安徽理工大学;2.河南中烟工业有限责任公司安阳卷烟厂

作者简介:

通讯作者:

中图分类号:

TP391.4

基金项目:

国家自然科学基金(62102003);国家重大专项(2020YFB1314103);安徽省自然科学基金(2108085QF258);安徽省博士后基金(2022B623);安徽省高等学校自然科学研究项目(KJ2020A0299)


Edge Information Guided Camouflaged Object Detection
Author:
Affiliation:

1.Anhui University of Science & Technology;2.Anyang Cigarette Factory China Tobacco Henan Industrial Co

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    伪装目标检测(camouflaged object detection, COD)旨在检测隐藏在复杂背景中的伪装目标。由于伪装目标的特点:前景与背景纹理相似、边缘对比度低,导致现有方法得到的预测图像边缘模糊、小目标区域缺失。因此,本文提出了边缘信息引导的伪装目标检测网络。首先,通过低层特征和高层特征对目标的边缘进行显式建模,充分提取目标的边缘特征指导后续特征表示。然后,通过双分支结构处理不同维度的伪装目标。其中,全局分支用以提取全局上下文信息强调大目标的全局贡献,局部分支用以挖掘丰富的局部低级线索增强小目标的特征表示。最后,采用自顶向下的方式实现相邻层特征的逐步融合,得到具有精细边缘和完整区域的预测图像。在三个伪装数据集上的实验结果表明本文方法优于其他15个模型,在NC4K数据集上平均绝对误差降至0.044。

    Abstract:

    Camouflaged object detection (COD) aims to detect camouflaged objects hidden in complex backgrounds. Due to the characteristics of camouflaged objects, such as similar foreground and background textures and low-contrast edges, existing methods often produce blurry edge predictions and miss small object regions. Therefore, this paper proposes an edge information guided COD network. First, the edge of the camouflaged object is explicitly modeled through low-level and high-level features, which fully extract the edge features of the objects to guide subsequent feature representations. Then, a dual-branch structure is used to process different dimensions of camouflaged objects. The global branch is used to extract global contextual information to emphasize the global contribution of large objects, while the local branch is used to mine rich local low-level clues to enhance the feature representation of small objects. Finally, a top-down manner is used to gradually aggregate adjacent layer features to obtain a prediction image with fine edges and complete regions. Experimental results on three camouflaged datasets show that our method outperforms 15 other models, with a mean absolute error of 0.044 on the NC4K dataset.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-04-09
  • 最后修改日期:2023-06-24
  • 录用日期:2023-07-06
  • 在线发布日期:
  • 出版日期: