采用空谱特征自适应融合网络的军事地质土体分类方法
Military Geological Soil Classification Method Based on Spatial-Frequency Feature Adaptive Fusion Network
针对非抵近地区土体要素提取中多源特征融合效率低和土体边界特征表征差等问题,提出采用空谱特征自适应融合网络的军事地质土体分类方法(SFAM-Net)。在编码器—解码器结构上,引入空间和光谱注意力机制,构建双分支特征提取模块来提取影像中土体的空间、光谱特征;通过卷积块注意力模块融合提取特征,并采用自适应融合机制优化特征权重分配。实验结果显示,SFAM-Net能对夹石土、硬土和普通土这3种典型土体类型及其边界信息进行有效区分,平均交并比(mIoU)、平均像素精度(mPA)分别为71.16%和84.60%,较基线模型最佳结果分别提升5.46个百分点和8.11个百分点,验证该方法能够提高军事地质土体分类精准度。
To address issues such as low efficiency in multi-source feature fusion and poor characterization of soil boundary features during soil element extraction in non-close-range areas, a military geological soil classification method based on spatial-frequency feature adaptive fusion network (SFAM-Net) is proposed. The spatial and spectral attention mechanisms are introduced in the encoder-decoder architecture, and a dual-branch feature extraction module is constructed to capture both spatial and spectral characteristics of soil in imagery. Features are extracted through the fusion of convolutional block attention modules, and an adaptive fusion mechanism is adopted to optimize the distribution of feature weights. Experimental results demonstrate that SFAM-Net can effectively distinguish three typical soil types, namely rocky soil, hard soil and ordinary soil, and their boundary information. The mean intersection over union (mIoU) and mean pixel accuracy (mPA) are 71.16% and 84.60% respectively, which are 5.46 percentage points and 8.11 percentage points higher than the best result of the baseline model. It is verified that the accuracy of military geological soil classification are improved by using the method.
军事地质土体 / 自适应融合 / 空谱特征 / 注意力机制 / 遥感影像
military geological soil / adaptive fusion / spatial-frequency feature / attention mechanism / remote sensing images
| [1] |
张栋,葛良胜,王卫兵, |
| [2] |
李显巨,吴春明,陈伟涛, |
| [3] |
詹纯,杨虎,梁军, |
| [4] |
孙红政,李宏伟,徐哲, |
| [5] |
|
| [6] |
刘晓煌,孙兴丽,刘玖芬, |
| [7] |
李爱迪.地形因素影响下重庆市主要土壤的质地类型空间分布预测研究[D].重庆:西南大学,2019:6-13. |
| [8] |
于德浩,龙凡,杨清雷, |
| [9] |
|
| [10] |
|
| [11] |
魏锦山,陈争光.基于深度学习与近红外光谱的土壤质地分类模型研究[J].现代农业研究,2023,29(1):8-13. |
| [12] |
冯文康,梁忠伟,刘晓初, |
| [13] |
|
| [14] |
|
| [15] |
WOO S, |
| [16] |
郭宏伟.顾及军事地质要素的越野路径规划研究[D].郑州:信息工程大学,2022:8-15. |
| [17] |
|
/
| 〈 |
|
〉 |