Remote Sensing Image Classification Based on Multi-scale Feature Extraction

doi:10.3969/j.issn.1006-2475.2025.03.013

Abstract

Abstract: In order to improve the accuracy of convolutional neural network in the classification task of remote sensing image， a method based on multi-scale feature extraction for classification is proposed. Aiming at the problems that the scale difference of target objects in remote sensing images is large and ordinary convolutional extraction tends to produce redundant features， a multi-scale hybrid convolution module with ordinary convolution and atrous convolution is proposed， which can effectively enhance the feature extraction ability of the model. In terms of feature fusion， a feature cross fusion module is proposed， which can effectively fuse the semantic information of each branch and make full use of the information between various scale features for deep fusion and interaction. Aiming at the problem of complex land cover information in remote sensing images， a parallel attention module is proposed to apply attention mechanisms to each branch， which makes it pay more attention to the key parts of the image and ignore the redundant information. Compared with the existing methods， the classification performance of the proposed method is significantly improved. On the data sets WHU-RS19、RSSCN7 and SIRI-WHU，the overall accuracy of the proposed method reaches 98.19%、94.18% and 96.37%， respectively.

Key words: remotes sensing image, attention mechanism, convolutional neural network, deep learning

CLC Number:

TP391

LUO Hao, LI Xianfeng. Remote Sensing Image Classification Based on Multi-scale Feature Extraction[J]. Computer and Modernization, 2025, 0(03): 86-92.

References

［1］张兵. 遥感大数据时代与智能信息提取［J］. 武汉大学学报（信息科学版）， 2018，43（12）：1861-1871.
［2］李大湘，南艺璇，刘颖. 面向遥感图像场景分类的双知识蒸馏模型［J］. 电子与信息学报， 2023，45（10）：3558-3567.
［3］宋中山，彭丹，郑禄，等. 基于改进密集连接网络的遥感图像场景分类［J］. 激光杂志， 2023，44（10）：71-78.
［4］杨星，宋玲玲，王时绘. 基于改进的ResNeXt网络结构的遥感图像分类［J］. 计算机科学， 2023，50（增刊1）：282-287.
［5］ MARTHA T R， KERLE N， VAN WESTEN C J， et al. Segment optimization and data-driven thresholding for knowledge-based landslide detection by object-based image analysis［J］. IEEE Transactions on Geoscience and Remote Sensing， 2011，49（12）：4928-4943.
［6］ ZHANG Y S， WU L， REN H， et al. Mapping water quality parameters in urban rivers from hyperspectral images using a new self-adapting selection of multiple artificial neural networks［J］. Remote Sensing， 2020，12：336.
［7］ VERAVERBEKE S， DENNISON P， GITAS I， et al. Hyperspectral remote sensing of fire： State-of-the-art and future perspectives［J］. Remote Sensing of Environment， 2018，216：105-121.
［8］岳泓光，韩龙玫，王正勇，等. 基于多通道自注意力网络的遥感图像场景分类［J］. 四川大学学报（自然科学版）， 2023，60（2）：97-105.
［9］余东行，张保明，赵传，等. 联合卷积神经网络与集成学习的遥感影像场景分类［J］. 遥感学报， 2020，24（6）：717-727.
［10］吕启，窦勇，牛新，等. 基于DBN模型的遥感图像分类［J］. 计算机研究与发展， 2014，51（9）：1911-1918.
［11］ NOGUEIRA K， PENATTI O A， SANTOS J A D. Towards better exploiting convolutional neural networks for remote sensing scene classification［J］. arXiv preprint arXiv：1602.01517， 2016.
［12］李彦甫，范习健，杨绪兵，等. 基于自注意力卷积网络的遥感图像分类［J］. 北京林业大学学报， 2021，43（10）：81-88.
［13］王协，章孝灿，苏程. 基于多尺度学习与深度卷积神经网络的遥感图像土地利用分类［J］. 浙江大学学报（理学版）， 2020，47（6）：715-723.
［14］何自芬，史本杰，张印辉，等. 多注意力融合的环高原湖泊遥感影像分割［J］. 电子学报， 2023，51（4）：885-895.
［15］ DAI D X， YANG W. Satellite image classification via two-layer sparse coding with biased image representation［J］. IEEE Geoscience and Remote Sensing Letters， 2010，8（1）：173-176.
［16］ ZOU Q， NI L H， ZHANG T， et al. Deep learning based feature selection for remote sensing scene classification［J］. IEEE Geoscience and Remote Sensing Letters， 2015，12（11）：2321-2325.
［17］ ZHU Q Q， ZHONG Y F， ZHAO B， et al. Bag-of-visual-words scene classifier with local and global features for high spatial resolution remote sensing imagery［J］. IEEE Geoscience and Remote Sensing Letters， 2016，13（6）：747-751.
［18］ HOWARD A G， ZHU M L， CHEN B， et al. MobileNets： Efficient convolutional neural networks for mobile vision applications［J］. arXiv preprint arXiv：1704.04861， 2017.
［19］ SANDLER M， HOWARD A， ZHU M L， et al. MobileNetv2： Inverted residuals and linear bottlenecks［C］// Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2018：4510-4520.
［20］ LIU Z Y， DONG A M， YU J G， et al. Scene classification for remote sensing images with self-attention augmented CNN［J］. IET Image Processing， 2022，16（11）：3085-3096.
［21］ BIAN X Y， CHEN C， TIAN L， et al. Fusing local and global features for high-resolution scene classification［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2017，10（6）：2889-2901.
［22］ XIA G S， HU J W， HU F， et al. AID： A benchmark data set for performance evaluation of aerial scene classification［J］. IEEE Transactions on Geoscience and Remote Sensing， 2017，55（7）：3965-3981.
［23］ SUN H， LI S Y， ZHENG X T， et al. Remote sensing scene classification by gated bidirectional network［J］. IEEE Transactions on Geoscience and Remote Sensing， 2019，58（1）：82-96.
［24］ ZHANG B， ZHANG Y J， WANG S G. A lightweight and discriminative model for remote sensing scene classification with multidilation pooling module［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2019，12（8）：2636-2653.
［25］ WU H， LIU B Z， SU W H， et al. Hierarchical coding vectors for scene level land-use classification［J］. Remote Sensing， 2016，8（5）： 436.
［26］ WU H， LIU B Z， SU W H， et al. Deep filter banks for land-use scene classification［J］. IEEE Geoscience and Remote Sensing Letters， 2016，13（12）：1895-1899.
［27］ LIU Y S， LIU Y B， DING L W. Scene classification based on two-stage deep feature fusion［J］. IEEE Geoscience and Remote Sensing Letters， 2017，15（2）：183-186.
［28］ GAO Y， SHI J， LI J， et al. Remote sensing scene classification with dual attention-aware network［C］// 2020 IEEE 5th International Conference on Image， Vision and Computing （ICIVC）. IEEE， 2020：171-175.
［29］ LIU X N， ZHOU Y， ZHAO J Q， et al. Siamese convolutional neural networks for remote sensing scene classification［J］. IEEE Geoscience and Remote Sensing Letters， 2019，16（8）：1200-1204.
［30］ LIU Y F， ZHONG Y F， QIN Q Q. Scene classification based on multiscale convolutional neural network［J］. IEEE Transactions on Geoscience and Remote Sensing， 2018，56（12）：7109-7121.
［31］ LI L L， LIANG P J， MA J J， et al. A multiscale self-adaptive attention network for remote sensing scene classification［J］. Remote Sensing， 2020，12（14）. DOI： 10.3390/rs12142209.
［32］ HAN X B， ZHONG Y F， CAO L Q， et al. Pre-trained AlexNet architecture with pyramid pooling and supervision for high spatial resolution remote sensing image scene classification［J］. Remote Sensing， 2017， 9（8）. DOI： 10.3390
/rs9080848.
［33］ THIRUMALADEVI S， VEERA SWAMY K， SAILAJA M. Improved transfer learning of CNN through fine-tuning and classifier ensemble for scene classification［J］. Soft Computing， 2022，26（12）：5617-5636.

[1]	LI Haoran1, HE Wenxue1, XU Jiazhen1, YANG Banghua2. Classification Method of EEG Signals for Depression Based on Multi-Scale Dynamic Convolution and Attention Mechanism [J]. Computer and Modernization, 2025, 0(03): 60-65.
[2]	PU Yaya, WANG Yanbo, SU Yongdong, XU Zhongcheng. Multi-scale Feature Image Defogging Algorithm Based on Content-guided Attention Fusion [J]. Computer and Modernization, 2025, 0(03): 78-85.
[3]	ZHU Yongtian, TIAN Fei, DONG Baoliang. Ultrasonic Image Segmentation of Thyroid Nodules Based on HA-UNet++ [J]. Computer and Modernization, 2025, 0(03): 93-98.
[4]	XIE Haiqing, LING Jiaqi, YI Xinbo. Tongue Constitution Classification Method Based on Deep Learning [J]. Computer and Modernization, 2025, 0(03): 99-105.
[5]	LIU Yaokai, REN Dejun, LIU Chongyi, LU Yudong. AMDFF-Net： Adaptive Multi-dimensional Feature Fusion Network for Tiny Object Detection [J]. Computer and Modernization, 2025, 0(03): 106-112.
[6]	ZHANG Yue, GUO Zixin, HUANG Yibin, YAN Tao. Network Intrusion Detection Method Based on Convolutional Neural Networks with convLSTM [J]. Computer and Modernization, 2025, 0(03): 119-126.
[7]	GUO Hua. Resampling of Imbalanced Data for Optimizing Downstream Tasks [J]. Computer and Modernization, 2025, 0(02): 28-32.
[8]	LIU Chongyi, LI Hua, REN Dejun, LIU Yaokai, WANG Yulong. Anomaly Detection Algorithm Based on Bidirectional Multi-scale Knowledge Distillation [J]. Computer and Modernization, 2025, 0(02): 58-63.
[9]	FENG Xinjie, WANG Wei. Twin Feature Fusion Network for Scene Text Image Super Resolution [J]. Computer and Modernization, 2025, 0(02): 86-93.
[10]	ZHAO Yin, YIN Siqing, ZHANG Yonglai. Improved Traffic Sign Detection Algorithm of YOLOv7 [J]. Computer and Modernization, 2025, 0(02): 94-99.
[11]	XIAO Junbi, FU Tianqi. Real-Time Traffic Classification Method Based on High-dimensional Feature#br# Dimensionality Reduction and Clustering [J]. Computer and Modernization, 2025, 0(01): 80-85.
[12]	LI Xi, PAN Yu. Ground Penetrating Radar Pipeline Object Detection Method Based on Improved YOLOv8 [J]. Computer and Modernization, 2025, 0(01): 94-99.
[13]	LIU Fei, YANG Degang, ZHANG Xin, QIN Jing. Improved Underwater Target Detection Algorithm Based on YOLOv8 [J]. Computer and Modernization, 2025, 0(01): 113-119.
[14]	HE Sida, CHEN Pinghua. Intent-based Lightweight Self-Attention Network for Sequential Recommendation [J]. Computer and Modernization, 2024, 0(12): 1-9.
[15]	ZHAO Chenyang, XUE Tao, LIU Junhua. Fashion Clothing Pattern Generation Based on Improved Stable Diffusion [J]. Computer and Modernization, 2024, 0(12): 15-23.