基于自适应频率感知网络的遥感图像分割方法

Remote sensing image segmentation method based on adaptive frequency-aware network

摘要

现有遥感图像分割方法在跨尺度特征融合时缺乏对低频结构与高频细节的协同处理，且无法对图像内容自适应响应，导致难以有效解决因自然变化、光照和阴影干扰引起的高分辨率遥感图像中类内差异大、类间差异小的问题。为此提出了一种自适应频率感知网络（AFANet）。首先，提出一种频率动态融合模块，通过自适应低通和高通滤波在保留低频结构的同时抑制高频噪音分量，并增强高频细节边界信息。其次，构建双域学习模块集成空间和频率信息，实现空间域局部细节与频域全局结构的联合建模。最后，引入一个细节增强模块，利用不同的差分卷积以增强模型的特征提取和泛化能力。在Vaihingen和Potsdam两个经典公开数据集上通过对比和消融实验的定量及可视化分析表明，AFANet在F1分数、总体精度和平均交并比等指标中优于7种先进的分割方法，验证了AFANet的优越性能。

Abstract

The existing remote sensing image segmentation methods lack the coordinated processing of low-frequency structures and high-frequency details during cross-scale feature fusion, and cannot adaptively respond to image content, making it difficult to effectively solve the problem of large intra-class variations and small inter-class variations in high-resolution remote sensing images caused by natural changes, illumination, and shadow interference. To address these problems, an adaptive frequency-aware network (AFANet) is proposed and implemented. First, a frequency dynamic fusion module is proposed, which suppresses high-frequency noise components while retaining low-frequency structures through adaptive low-pass and high-pass filter, and enhancing high-frequency detail boundary information. Secondly, a dual-domain learning block is constructed to integrate spatial and frequency information to achieve joint modeling of local details in the spatial domain and global structures in the frequency domain. Finally, a detail-enhanced module is introduced to enhance the feature extraction and generalization capabilities of the model using different differential convolutions. The quantitative analysis and visualization results of the comparative and ablation experiments on the two classic public datasets, Vaihingen and Potsdam, show that AFANet outperforms seven state-of-the-art segmentation methods in terms of F1 score, OA and mIoU, with the mIoU reaching 85.13% and 87.81% respectively, verifying the superior performance of AFANet.

关键词

遥感图像 / 语义分割 / 特征融合 / 自适应频率滤波 / 空间域—频域 Transformer

Key words

remote sensing images / semantic segmentation / feature fusion / adaptive frequency filter / spatial-frequency Transformer

参考文献

[1] VICTOR N, MADDIKUNTA P K R, MARY D R K, et al. Remote sensing for agriculture in the era of industry 5.0—A survey[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 5920-5945.

[2] KEMARAU R A, SUAB S A, EBOY O V, et al. Integrative approaches in remote sensing and GIS for assessing climate change impacts across Malaysian ecosystems and societies[J].Sustainability, 2025, 17(4): 1344.

[3] JIA P, CHEN C, ZHANG D, et al. Semantic segmentation of deep learning remote sensing images based on band combination principle: Application in urban planning and land use[J].Computer Communications, 2024, 217: 97-106.

[4] WENQI Y U, GONG C, MEIJUN W, et al. MAR20: A benchmark for military aircraft recognition in remote sensing images[J].National Remote Sensing Bulletin, 2024, 27(12): 2688-2696.

[5] WU Z, GAO Y, LI L, et al. Semantic segmentation of high—resolution remote sensing images using fully convolutional network with adaptive threshold[J].Connection Science, 2019, 31(2): 169-184.

[6] MARMANIS D, SCHINDLER K, WEGNER J D, et al. Classification with an edge: Improving semantic image segmentation with boundary detection[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 135: 158-172.

[7] 张晓磊, 潘卫军, 王思禹, 等. 一种基于双边模糊聚类的遥感图像分割算法[J].航空计算技术, 2020, 50(1): 33-37.

[8] ZHANG X L, PAN W J, WANG S Y, et al. A remote sensing image segmentation algorithm based on bilateral fuzzy clustering[J].Aeronautical Computing Technique, 2020, 50(1): 33-37.

[9] 马妍, 古丽米拉·克孜尔别克. 图像语义分割方法在高分辨率遥感影像解译中的研究综述[J].计算机科学与探索, 2023, 17(7): 1526-1548.

[10] MA Y, KEZIERBIEKE G. A review of image semantic segmentation methods in high—resolution remote sensing image interpretation[J].Journal of Computer Science and Exploration, 2023, 17(7): 1526-1548.

[11] RONNEBERGER O, FISCHER P, BROX T. U—Net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer—Assisted Intervention. Cham: Springer International Publishing, 2015: 234-241.

[12] DIAKOGIANNIS F I, WALDNER F, CACCETTA P, et al. ResUNet—a: A deep learning framework for semantic segmentation of remotely sensed data[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 162: 94-114.

[13] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[EB/OL]. [2025—03—12].https://arxiv.org/pdf/2010.11929.

[14] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 10012-10022.

[15] ZHENG S X, LU J C, ZHAO H S, et al. Rethinking semantic segmentation from a sequence—to—sequence perspective with transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. [S.l.]: IEEE,2021: 6881.

[16] ZHANG R H, ZHANG Q, ZHANG G X. LSRFormer: Efficient transformer supply convolutional neural networks with global information for aerial image segmentation[J].IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 1-13.

[17] WANG L B, LI R, ZHANG C, et al. UNetFormer: A UNet—like transformer for efficient semantic segmentation of remote sensing urban scene imagery[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 190: 196-214.

[18] WU H L, HUANG P, ZHANG M, et al. CMTFNet: CNN and multiscale transformer fusion network for remote—sensing image semantic segmentation[J].IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-12.

[19] ZHANG J, SHAO M W, WAN Y C, et al. Boundary—aware spatial and frequency dual—domain transformer for remote sensing urban images segmentation[J].IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5637718.

[20] LIU H J, ZHOU X Y, WANG C L, et al. Fourier—deformable convolution network for road segmentation from remote sensing images[J].IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 4415117.

[21] DUAN S, ZHAO J, HUANG X, et al. Semantic segmentation of remote sensing data based on channel attention and feature information entropy[J].Sensors, 2024, 24(4): 1324.

[22] YANG Y S, YUAN G J, LI J J. SFFNet: A wavelet—based spatial and frequency domain fusion network for remote sensing segmentation[J].IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 3000617.

[23] DONG B, WANG P C, WANG F. Head—free lightweight semantic segmentation with linear transformer[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 37(1): 516-524.

[24] FAN J Y, LI J J, LIU Y P, et al. Frequency—aware robust multidimensional information fusion framework for remote sensing image segmentation[J].Engineering Applications of Artificial Intelligence, 2024, 129: 107638.

[25] WOO S, DEBNATH S, HU R H, et al. ConvNeXt V2: Co—designing and scaling ConvNets with masked autoencoders[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE,2023: 16133-16142.

[26] WANG J Q, CHEN K, XU R, et al. CARAFE: Content—aware reassembly of features[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 3007-3016.

[27] ABDEL M S, ZHANG Y L, WEI D L, et al. Dynamic high—pass filtering and multi—spectral attention for image super—resolution[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 4288-4297.

[28] CHEN L, FU Y, GU L, et al. Frequency—aware feature fusion for dense image prediction[J].IEEE Trans Pattern Anal Mach Intell, 2024, 46(12): 10763-10780.

[29] SU Z, LIU W Z, YU Z T, et al. Pixel difference networks for efficient edge detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 5117-5127.

[30] XU J F, BODDETI V N, SAVVIDES M. Local binary convolutional neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 19-28.

[31] CHEN Z, HE Z, LU Z M. DEA—net: Single image dehazing based on detail—enhanced convolution and content—guided attention[J].IEEE Trans Image Process, 2024, 33: 1002-1015.

[32] ZHAO H, SHI J, QI X, et al. Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 2881.

[33] ZHOU Y F, HUANG J X, WANG C L, et al. XNet: Wavelet—based low and high frequency fusion networks for fully— and semi—supervised semantic segmentation of biomedical images[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Vancouver: IEEE, 2023: 21085-21096.

[34] CHEN L, GU L , ZHENG D , et al. Frequency—adaptive dilated convolution for semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 3414-3425.

[35] WOO S, PARK J, LEE J Y, et al. Cbam: Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision. Munich: Springer, 2018: 3-19.

[36] WANG Q, WU B, ZHU P, et al. ECA—Net: Efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision And Pattern Recognition. Seattle: IEEE, 2020: 11534-11542.

[37] ZHANG Q L, YANG Y B. Sa—net: Shuffle attention for deep convolutional neural networks[C]//ICASSP 2021—2021 IEEE International Conference on Acoustics, Speech and Signal Processing. Melbourne: IEEE, 2021: 2235-2239.

基金资助

国家自然科学基金面上项目(62273155)

山东省自然科学基金(ZR2021MF017)

山东省自然科学基金(ZR2024QF022)

山东省重点研发计划(2023RKY01015)