Chen Bochao, Tong An, Wang Yapeng, Zhang Jie, Yang Xu, Im Sio-Kei
Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China.
Macao Polytechnic University, Macao 999078, China.
Sensors (Basel). 2024 Dec 25;25(1):54. doi: 10.3390/s25010054.
The accurate segmentation of land cover in high-resolution remote sensing imagery is crucial for applications such as urban planning, environmental monitoring, and disaster management. However, traditional convolutional neural networks (CNNs) struggle to balance fine-grained local detail with large-scale contextual information. To tackle these challenges, we combine large-kernel convolutions, attention mechanisms, and multi-scale feature fusion to form a novel LKAFFNet framework that introduces the following three key modules: LkResNet, which enhances feature extraction through parameterizable large-kernel convolutions; Large-Kernel Attention Aggregation (LKAA), integrating spatial and channel attention; and Channel Difference Features Shift Fusion (CDFSF), which enables efficient multi-scale feature fusion. Experimental comparisons demonstrate that LKAFFNet outperforms previous models on both the LandCover dataset and WHU Building dataset, particularly in cases with diverse scales. Specifically, it achieved a mIoU of 0.8155 on the LandCover dataset and 0.9326 on the WHU Building dataset. These findings suggest that LKAFFNet significantly improves land cover segmentation performance, offering a more effective tool for remote sensing applications.
在高分辨率遥感影像中准确分割土地覆盖对于城市规划、环境监测和灾害管理等应用至关重要。然而，传统卷积神经网络（CNN）难以平衡细粒度的局部细节与大规模上下文信息。为应对这些挑战，我们结合大内核卷积、注意力机制和多尺度特征融合，形成了一种新颖的LKAFFNet框架，该框架引入了以下三个关键模块：LkResNet，通过可参数化的大内核卷积增强特征提取；大内核注意力聚合（LKAA），整合空间和通道注意力；以及通道差异特征移位融合（CDFSF），实现高效的多尺度特征融合。实验比较表明，LKAFFNet在LandCover数据集和WHU建筑数据集上均优于先前模型，尤其是在尺度多样的情况下。具体而言，它在LandCover数据集上的mIoU为0.8155，在WHU建筑数据集上为0.9326。这些结果表明，LKAFFNet显著提高了土地覆盖分割性能，为遥感应用提供了一种更有效的工具。
