本文已被:浏览 2437次 下载 882次
投稿时间:2020-09-07 修订日期:2020-12-16
投稿时间:2020-09-07 修订日期:2020-12-16
中文摘要: 显著性目标检测已经被广泛应用到图像检索、图像分割、行人重识别等领域。目前主流的显著性目标检测方法通常采用短连接加权的方式融合多级别特征信息,这种方式无法精准有效地控制信息流的传递。而且,现有的检测方法通常采用单一的特征检测,导致显著性目标区域与背景的边界不连续、易模糊。因此,本文提出一种多尺度特征提取和多级别特征融合的显著性目标检测方法。首先,利用不同扩张率的空洞卷积获取多尺度的上下文信息,弥补单一特征检测带来的不足。其次,提出一个多级别特征融合模块,该模块有效地利用浅层特征信息、深层特征信息和全局上下文特征信息之间的分布特性进行融合,不仅可以抑制噪声的传递,而且可以更有效地恢复显著性目标的空间细节结构信息。同时构建一个简洁的注意力模块,该模块有效保留特征图融合后的通道信息。本文对综合指标、平均绝对误差、结构化度量、精确率-召回率曲线和F-measure曲线进行了实验评估,在5个公开的数据集上进行的实验结果表明:相比于其他13种主流的检测方法,本文方法在不同的评估指标上均有明显的提升,在4个数据集上的综合指标和结构化度量指标均超过其他方法;并且,本文方法的可视化检测的显著图边缘轮廓连续性更好,空间结构细节信息更清晰。
Abstract:Salient object detection has been widely used in image retrieval, image segmentation, pedestrian recognition and other fields. Current mainstream detection methods fuse multi-level feature information through short connection to add feature maps, which cannot accurately and effectively control the transmission of information flow. In addition, existing salient detection methods usually use single feature detection, which results in discontinuous and fuzzy boundary between the saliency object region and the background. A new salient object detection method based on multi-scale feature extraction and multi-level feature fusion was proposed in this paper. Firstly, the multi-scale context information was obtained by using the dilated convolution of different expansion rates to make up for the deficiencies caused by single feature detection. Secondly, a multi-level feature fusion module was designed, which fuses low-level feature, high-level feature and global context feature information for different distribution characteristics of them. It can not only restrain the transmission of noise, but also restore the spatial detail structure information of the saliency object effectively. At the same time, a concise attention module was constructed, which can effectively retain the channel information after feature map fusion. The F-score, mean absolute error, structural measurement, precision-recall rate curve and F-measure curve have been evaluated experimentally. Experiments on five public datasets show that compared with other thirteen mainstream detection methods, the proposed method in this paper achieves significant improvements in different evaluation indicators, of which the F-score, and structural measurement on four datasets are better than other methods. Meanwhile, the saliency map predicted by the proposed method in this paper has better continuity of edge contours and clearer details of spatial structure details.
keywords: salient object detection multi-scale feature extraction multi-level feature fusion saliency map deep learning
文章编号:202000771 中图分类号:TP389.1 文献标志码:
基金项目:黑龙江省自然科学基金优秀青年项目(YQ2019F016);黑龙江省自然科学基金项目(ZD2019F003)
作者 | 单位 | |
黎玲利 | 黑龙江大学 计算机科学技术学院,黑龙江 哈尔滨 150080 | lilingli@hlju.edu.cn |
孟令兵 | 黑龙江大学 计算机科学技术学院,黑龙江 哈尔滨 150080 | |
李金宝 | 齐鲁工业大学(山东省科学院) 山东省人工智能研究院,山东 济南 250014 | lijinb@sdas.org |
作者简介:第一作者:黎玲利(1986-),女,副教授,博士.研究方向:大数据管理与分析.E-mail:lilingli@hlju.edu.cn;通信作者:李金宝,E-mail:lijinb@sdas.org
引用文本:
黎玲利,孟令兵,李金宝.多尺度特征提取和多级别特征融合的显著性目标检测方法[J].工程科学与技术,2021,53(1):170-177.
LI Lingli,MENG Lingbing,LI Jinbao.Salient Object Detection Based on Multi-scale Feature Extraction and Multi-level Feature Fusion[J].Advanced Engineering Sciences,2021,53(1):170-177.
引用文本:
黎玲利,孟令兵,李金宝.多尺度特征提取和多级别特征融合的显著性目标检测方法[J].工程科学与技术,2021,53(1):170-177.
LI Lingli,MENG Lingbing,LI Jinbao.Salient Object Detection Based on Multi-scale Feature Extraction and Multi-level Feature Fusion[J].Advanced Engineering Sciences,2021,53(1):170-177.