计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (17): 37-45.DOI: 10.3778/j.issn.1002-8331.2104-0341

• 热点与综述 • 上一篇    下一篇

协同视觉显著性检测方法研究进展综述

陈志武,成曦,曾黎,钱晓亮   

  1. 郑州轻工业大学 电气信息工程学院,郑州 450002
  • 出版日期:2021-09-01 发布日期:2021-08-30

Research Progress Review of Co-saliency Detection

CHEN Zhiwu, CHENG Xi, ZENG Li, QIAN Xiaoliang   

  1. School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
  • Online:2021-09-01 Published:2021-08-30

摘要:

协同视觉显著性检测是基于人类视觉注意力机制,旨在捕获一组相关图像中的公共显著目标,在协同分割和目标检测等领域广泛应用。对现有的协同显著性检测方法进行归纳总结和实验评估。根据特征形式的差异将所有方法分为两大类:一类是采用浅层特征的传统方法,另一类是采用深层特征的基于深度学习方法。根据获取组间显著性和模型构建策略的不同,对这两大类方法进行相关介绍和理论分析。将流行方法在领域内两个公开数据集进行了主观和定量的实验评估。对现有方法进行定性总结,并分析了现阶段研究中存在的问题,同时对未来工作进行展望。

关键词: 协同视觉显著性, 公共显著目标, 深度学习, 浅层特征, 端到端模型

Abstract:

Co-saliency detection is based on the human visual attention mechanism to capture common and salient objects in a group of related images, co-saliency is widely used in co-segmentation, object detection and other fields. The existing methods of co-saliency detection are summarized and experimentally evaluated. Firstly, according to the difference of features, all methods are divided into two categories:one is the traditional methods with low-level features, the other is the deep learning methods with deep-level features. Secondly, on the basis of the different ways of obtaining inter-saliency and building models, the two kinds of methods are introduced and theoretically analyzed. Then the state-of-the-art methods are subjectively and quantitatively evaluated in the two public datasets. Finally, the existing methods are qualitatively summarized, the existing problems are analyzed in the present research, and the future work is prospected.

Key words: co-saliency, common salient object, deep learning, low-level feature, end-to-end model