计算机应用 ›› 2021, Vol. 41 ›› Issue (10): 3010-3016.DOI: 10.11772/j.issn.1001-9081.2020121899

所属专题: 多媒体计算与计算机仿真

• 多媒体计算与计算机仿真 • 上一篇    下一篇

基于注意力机制网络的航运监控图像识别模型

张凯悦1,2, 张鸿1,2   

  1. 1. 武汉科技大学 计算机科学与技术学院, 武汉 430081;
    2. 智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学), 武汉 430081
  • 收稿日期:2020-12-04 修回日期:2021-04-14 出版日期:2021-10-10 发布日期:2021-07-14
  • 通讯作者: 张凯悦
  • 作者简介:张凯悦(1997-),男,湖北随州人,硕士研究生,主要研究方向:机器学习、图像识别、深度学习;张鸿(1979-),女,湖北襄阳人,教授,博士,CCF会员,主要研究方向:跨模态检索、机器学习、数据挖掘。
  • 基金资助:
    国家自然科学基金资助项目(61373109)。

Shipping monitoring image recognition model based on attention mechanism network

ZHANG Kaiyue1,2, ZHANG Hong1,2   

  1. 1. School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan Hubei 430081, China;
    2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System(Wuhan University of Science and Technology), Wuhan Hubei 430081, China
  • Received:2020-12-04 Revised:2021-04-14 Online:2021-10-10 Published:2021-07-14
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61373109).

摘要: 针对已有的航运监控图像识别模型C3D里中级表征学习能力有限,有效特征的提取容易受到噪声的干扰,且特征的提取忽视了整体特征与局部特征之间关系的问题,提出了一种新的基于注意力机制网络的航运监控图像识别模型。该模型基于卷积神经网络(CNN)框架,首先,通过特征提取器提取图像的浅层次特征;然后,基于CNN对不同区域激活特征的不同响应强度,生成注意力信息并实现对局部判别性特征的提取;最后,使用多分支的CNN结构融合局部判别性特征和图像全局纹理特征,从而利用局部判别性特征和图像全局纹理特征的交互关系提升CNN学习中级表征的能力。实验结果表明,所提出的模型在航运图像数据集上的识别准确率达到91.8%,相较于目前的C3D模型提高了7.2个百分点,相较于判别滤波器组卷积神经网络(DFL-CNN)模型提高了0.6个百分点。可见所提模型能够准确判断船舶的状态,可以有效应用于航运监控项目。

关键词: 智能监控, 深度学习, 卷积神经网络, 图像识别, 注意力机制

Abstract: In the existing shipping monitoring image recognition model named Convolutional 3D (C3D), the intermediate representation learning ability is limited, the extraction of effective features is easily disturbed by noise, and the relationship between global features and local features is ignored in feature extraction. In order to solve these problems, a new shipping monitoring image recognition model based on attention mechanism network was proposed. The model was based on the Convolutional Neural Network (CNN) framework. Firstly, the shallow features of the image were extracted by the feature extractor. Then, the attention information was generated and the local discriminant features were extracted based on the different response strengths of the CNN to the active features of different regions. Finally, the multi-branch CNN structure was used to fuse the local discriminant features and the global texture features of the image, thus the interaction between the local discriminant features and the global texture features of the image was utilized to improve the learning ability of CNN to the intermediate representations. Experimental results show that, the recognition accuracy of the proposed model is 91.8% on the shipping image dataset, which is improved by 7.2 percentage points and 0.6 percentage points compared with the current C3D model and Discriminant Filter within a Convolutional Neural Network (DFL-CNN) model respectively. It can be seen that the proposed model can accurately judge the state of the ship, and can be effectively applied to the shipping monitoring project.

Key words: intelligent monitoring, deep learning, Convolutional Neural Network (CNN), image recognition, attention mechanism

中图分类号: