计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (7): 192-203.DOI: 10.3778/j.issn.1002-8331.2211-0139

• 图形图像处理 • 上一篇    下一篇

双分支多维注意特征融合的高光谱图像分类

马亚美,王双亭,都伟冰   

  1. 河南理工大学 测绘与国土信息工程学院,河南 焦作 454003
  • 出版日期:2024-04-01 发布日期:2024-04-01

Hyperspectral Image Classification Based on Double Branch Multidimensional Attention Feature Fusion

MA Yamei, WANG Shuangting, DU Weibing   

  1. School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, Henan 454003, China
  • Online:2024-04-01 Published:2024-04-01

摘要: 为改善高光谱图像小样本类别的分类性能,提高模型特征表达的稳健性,提出了双分支多维注意力特征融合的神经网络分类模型(DBMD)。DBMD采用两个分支分别进行光谱特征提取和混合特征提取。光谱分支通过密集连接的扩张卷积逐级提取特征,然后融合低、中、高级语义信息作为特征输出。混合分支采用3D-2D网络架构,并通过改进的Inception块提取空间尺度特征。此外,注意力机制分别应用于光谱、空间和空谱特征,进行特征细化,增强重要区域的特征响应。最后,将不同维度的细化特征联合输入至分类器进行分类。在Indian Pines和Salinas Valley数据集上利用5%和1%的样本进行实验,分别取得了98.40%和99.78%的总体精度,与其他六种网络架构相比,该模型在准确性和稳定性上都具有更优的表现。

关键词: 混合特征提取, 注意力机制, 多维特征融合, 图像分类

Abstract: To improve the classification performance of small sample classes of hyperspectral images and to enhance the robustness of the model feature representation, a neural network classification model with two-branch multidimensional attentional feature fusion (DBMD) is proposed. DBMD uses two branches for spectral feature extraction and hybrid feature extraction respectively. The spectral branch extracts features step-by-step through densely connected dilated convolution, and then fuses low, medium and high level semantic information as the feature output. The hybrid branch uses a 3D-2D network architecture and extracts spatial scale features through improved Inception blocks. In addition, the attention mechanism is applied to spectral, spatial and spatial-spectral feature extraction respectively for feature refinement and to enhance the feature response in important regions. Finally, the refined features of different dimensions are jointly input to the classifier for classification. Experiments using 5% and 1% samples on the Indian Pines and Salinas Valley datasets achieve an overall accuracy of 98.40% and 99.78% respectively, and the proposed model performs better in terms of accuracy and stability compared to the other six network architectures.

Key words: hybrid feature extraction, attention mechanism, multidimensional feature fusion, image classification