LI Xinwei, YANG Tian. Double-Branch DenseNet-Transformer Hyperspectral Image Classification[J]. Infrared Technology , 2022, 44(11): 1210-1219.
Citation: LI Xinwei, YANG Tian. Double-Branch DenseNet-Transformer Hyperspectral Image Classification[J]. Infrared Technology , 2022, 44(11): 1210-1219.

Double-Branch DenseNet-Transformer Hyperspectral Image Classification

More Information
  • Received Date: July 31, 2022
  • Revised Date: September 12, 2022
  • To reduce the training samples of hyperspectral images and obtain better classification results, a double-branch deep network model based on DenseNet and a spatial-spectral transformer was proposed in this study. The model includes two branches for extracting the spatial and spectral features of the images in parallel. First, the spatial and spectral information of the sub-images was initially extracted using 3D convolution in each branch. Then, the deep features were extracted through a DenseNet comprising batch normalization, mish function, and 3D convolution. Next, the two branches utilized the spectral transformer module and spatial transformer module to further enhance the feature extraction ability of the network. Finally, the output characteristic maps of the two branches were fused and the final classification results were obtained. The model was tested on Indian pine, University of Pavia, Salinas Valley, and Kennedy Space Center datasets, and its performance was compared with six types of current methods. The results demonstrate that the overall classification accuracies of our model are 95.75%, 96.75%, 95.63%, and 98.01%, respectively when the proportion of the training set of Indian pines is 3% and the proportion of the training set of the rest is 0.5%. The overall performance was better than that of other methods.
  • [1]
    ZHONG Y, MA A, Ong Y soon, et al. Computational intelligence in optical remote sensing image processing[J]. Applied Soft Computing, 2018, 64: 75-93. DOI: 10.1016/j.asoc.2017.11.045
    [2]
    LI Z, HUANG L, HE J. A multiscale deep middle-level feature fusion network for hyperspectral classification[J]. Remote Sensing, 2019, 11(6): 695. DOI: 10.3390/rs11060695
    [3]
    Mahdianpari M, Salehi B, Rezaee M, et al. Very deep convolutional neural networks for complex land cover mapping using multispectral remote sensing imagery[J]. Remote Sensing, 2018, 10(7): 1119. DOI: 10.3390/rs10071119
    [4]
    Pipitone C, Maltese A, Dardanelli G, et al. Monitoring water surface and level of a reservoir using different remote sensing approaches and comparison with dam displacements evaluated via GNSS[J]. Remote Sensing, 2018, 10(1): 71. DOI: 10.3390/rs10010071
    [5]
    ZHAO C, WANG Y, QI B, et al. Global and local real-time anomaly detectors for hyperspectral remote sensing imagery[J]. Remote Sensing, 2015, 7(4): 3966-3985. DOI: 10.3390/rs70403966
    [6]
    Awad M, Jomaa I, Arab F. Improved capability in stone pine forest mapping and management in lebanon using hyperspectral CHRIS-Proba data relative to landsat ETM+[J]. Photogrammetric Engineering & Remote Sensing, 2014, 80(8): 725-731.
    [7]
    Ibrahim A, Franz B, Ahmad Z, et al. Atmospheric correction for hyperspectral ocean color retrieval with application to the Hyperspectral Imager for the Coastal Ocean (HICO)[J]. Remote Sensing of Environment, 2018, 204: 60-75. DOI: 10.1016/j.rse.2017.10.041
    [8]
    Marinelli D, Bovolo F, Bruzzone L. A Novel change detection method for multitemporal hyperspectral images based on binary hyperspectral change vectors[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(7): 4913-4928. DOI: 10.1109/TGRS.2019.2894339
    [9]
    LI J, Bioucas Dias J M, Plaza A. Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(11): 4085-4098.
    [10]
    LI J, Bioucas Dias J M, Plaza A. spectral–spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random fields[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(3): 809-823. DOI: 10.1109/TGRS.2011.2162649
    [11]
    FANG L, LI S, DUAN W, et al. Classification of hyperspectral images by exploiting spectral–spatial information of superpixel via Multiple Kernels[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(12): 6663–6674. DOI: 10.1109/TGRS.2015.2445767
    [12]
    Camps Valls G, Gomez Chova L, Munoz Mari J, et al. Composite Kernels for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2006, 3(1): 93–97. DOI: 10.1109/LGRS.2005.857031
    [13]
    HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 770-778.
    [14]
    Shelhamer E, LONG J, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651. DOI: 10.1109/TPAMI.2016.2572683
    [15]
    HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. DOI: 10.1109/TPAMI.2015.2389824
    [16]
    ZHAO W, DU S. Spectral–spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8): 4544-4554. DOI: 10.1109/TGRS.2016.2543748
    [17]
    LEE H, Kwon H. Going deeper with contextual CNN for hyperspectral image classification[J]. IEEE Transactions on Image Processing, 2017, 26(10): 4843-4855. DOI: 10.1109/TIP.2017.2725580
    [18]
    CHEN Y, JIANG H, LI C, et al. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(10): 6232–6251. DOI: 10.1109/TGRS.2016.2584107
    [19]
    HUANG G, LIU Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 4700-4708.
    [20]
    ZHONG Z, LI J, LUO Z, et al. Spectral–spatial residual network for hyperspectral image classification: A 3-D deep learning framework[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(2): 847–858. DOI: 10.1109/TGRS.2017.2755542
    [21]
    WANG W, DOU S, JIANG Z, et al. A fast dense spectral–spatial convolution network framework for hyperspectral images classification[J]. Remote Sensing, 2018, 10(7): 1068. DOI: 10.3390/rs10071068
    [22]
    Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [C]//Advances in Neural Information Processing Systems, 2017: 5998-6008.
    [23]
    LIU Z, LIN Y, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[J/OL]. Computer Vision and Pattern Recognition, 2021, https://arxiv.org/abs/2103.14030.
    [24]
    FANG B, LI Y, ZHANG H, et al. Hyperspectral images classification based on dense convolutional networks with spectral-wise attention mechanism[J]. Remote Sensing, 2019, 11(2): 159. DOI: 10.3390/rs11020159
    [25]
    MA W, YANG Q, WU Y, et al. Double-branch multi-attention mechanism network for hyperspectral image classification[J]. Remote Sensing, 2019, 11(11): 1307. DOI: 10.3390/rs11111307
    [26]
    LI R, ZHENG S, DUAN C, et al. Classification of hyperspectral image based on double-branch dual-attention mechanism network[J]. Remote Sensing, 2020, 12(3): 582. DOI: 10.3390/rs12030582
    [27]
    ZHONG Z, LI Y, MA L, et al. Spectral-spatial transformer network for hyperspectral image classification: a factorized architecture search framework[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, Doi: 10.1109/TGRS.2021.3115699.
    [28]
    MEI X, PAN E, MA Y, et al. Spectral-spatial attention networks for hyperspectral image classification[J]. Remote Sensing, 2019, 11(8): 963. DOI: 10.3390/rs11080963
    [29]
    SUN H, ZHENG X, LU X, et al. Spectral–spatial attention network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(5): 3232–3245. DOI: 10.1109/TGRS.2019.2951160
  • Related Articles

    [1]DENG Changzheng, LIU Mingze, FU Tian, GONG Mengqing, LUO Bingjie. Infrared Image Recognition of Substation Equipment Based on Improved YOLOv7-Tiny Algorithm[J]. Infrared Technology , 2025, 47(1): 44-51.
    [2]WANG Chongwen, PENG Tinghai, LUO Rui, LIU Jian, YANG Yuping, WANG Shijin, YAN Tingyu, GE Fan, LIU Yanfang, LIU Yunhong. Tropical Marine Environmental Adaptability of Germanium Coated Infrared Antireflection Film[J]. Infrared Technology , 2024, 46(8): 957-964.
    [3]ZHOU Huikui, ZHANG Li, HU Sujuan. Underwater Image Enhancement Based on Improved Histogram Matching and Adaptive Equalization[J]. Infrared Technology , 2024, 46(5): 532-538.
    [4]YANG Yuping, LIU Jian, ZHOU Xiaoyu, ZHAO Hongkun, LIU Yanfang, WANG Chongwen, ZHAO Yuanrong, GE Fan, XIAO Jianjun, LUO Rui, YANG Pinjie. Environmental Adaptability of Infrared Antireflection Films in Humid Hot Rain Forest[J]. Infrared Technology , 2021, 43(12): 1197-1201.
    [5]TANG Changming, ZHONG Jianfeng, ZHONG Shuncong, CHEN Man, FU Xibin, HUANG Xuebin. Ultrasound Infrared Thermography Defect Recognition Based on Improved Adaptive Genetic Algorithm with Two-Dimensional Maximum Entropy[J]. Infrared Technology , 2020, 42(8): 801-808.
    [6]WANG Chongwen, ZHAO Hongkun, LIU Jian, WANG Qiaofang, ZHU Guangyu, YANG Yuping, LUO Rui, ZHAO Yuanrong, LI Wei, LIU Yanfang, GE Fan. Dissecting the Adaptability of OLED Displays in Tropical Rainforest[J]. Infrared Technology , 2020, 42(6): 542-546.
    [7]JING Weiguo, SUN Mingzhao, LI Yongtao. Novel Experimental Method of Intense Light Adaptability of Night Vision Systems with Large Dynamic Range[J]. Infrared Technology , 2019, 41(7): 689-692.
    [8]LIU Hui, SHI Xiaolong. Improved GrabCut Segmentation Based on Salience and Superpixels[J]. Infrared Technology , 2018, 40(1): 55-61.
    [9]Improved Adaptive Segmentation Non-uniformity Correction Method for IRFPA[J]. Infrared Technology , 2017, 39(3): 209-213.
    [10]ZHANG Jin-cheng, LIAO Shou-yi, ZHANG Zuo-yu, SU De-lun, YAN Xun-liang. Real-time Improvement for Resistor Array Nonuniformity Correction[J]. Infrared Technology , 2015, 37(11): 921-925.
  • Cited by

    Periodical cited type(18)

    1. 田超华,赵欢,黄鸿基,孙伟可,王学峰. 基于深度学习的配电网开关柜电晕放电检测设计. 电子设计工程. 2025(01): 51-54+60 .
    2. 韩勇勇. 基于小波变换的PSO优化紫外双通道图像融合研究. 中国照明电器. 2025(02): 95-102 .
    3. 刘俊,王鲸,周炎生. 综合消磁工作线圈电缆接头击穿故障分析及应对策略. 广东造船. 2025(01): 59-62 .
    4. 朱杰,冯新颖,许网俊,范佳佳,杨赟. 基于YOLOV3神经网络的轨道车辆局部放电缺陷检测方法. 电工技术. 2025(03): 194-196 .
    5. 江澎,康正军,陈涛,冯一飞,吴琼. 融合人工智能与无线通信的热成像局放检测技术研究. 长江信息通信. 2024(01): 152-154 .
    6. 赵昊然,陆智勇,江明,刘立石. 小波包能量谱和神经网络的开关柜局部放电自动检测方法. 自动化与仪表. 2024(02): 92-96 .
    7. 汪可夫,胡志祥. 预制舱式变电站负荷支路漏电监测方法设计. 自动化仪表. 2024(07): 55-59+69 .
    8. 江熠,金坤鹏,钱锡颖,任一舟. 基于局部放电测试技术的避雷器状态诊断方法研究. 计算机测量与控制. 2024(07): 36-43 .
    9. 章铖. 基于红外热成像的变电站支柱绝缘子缺陷自动检测方法. 自动化技术与应用. 2024(08): 16-19+45 .
    10. 邵钦禹. 电力电缆的带电诊断与故障处理技术分析. 集成电路应用. 2024(09): 368-369 .
    11. 刘秀婷,李烨,高峰,马味敏. 高压电缆局部放电检测及识别系统研究. 电子测量技术. 2024(17): 97-107 .
    12. 胡梦捷. 基于非接触式测温技术的光伏直流侧拉弧线缆发热监测. 电线电缆. 2024(06): 31-34 .
    13. 韩勇勇,宋鹏,刘成涛. 基于ZYNQ 7020的双通道紫外放电检测系统设计. 国外电子测量技术. 2024(12): 115-120 .
    14. 苗堃,陈垒,李沛东,赵亚军,李健,郑城市,张胜利. 基于涡流技术的高压电缆铅封缺陷识别仿真研究. 环境技术. 2023(02): 139-145 .
    15. 龙丽名. 低压电线电缆检测手段及质量控制研究. 科技资讯. 2023(11): 42-45 .
    16. 何维晟,吴照国,徐扬,杜茂春,王谦,李勇,石钧仁. 高压电缆终端局部放电超声信号传输特性仿真分析. 高压电器. 2023(11): 48-55+64 .
    17. 刘杰,夏彦卫,贾伯岩,吴国强,殷庆栋. 基于高精度温度传感器的多股碳纤维导线潜伏性缺陷检测方法. 电子测量与仪器学报. 2023(11): 65-71 .
    18. 焦宇阳,段海南,张宏军,郑福建,朱进,刘新. 一种基于相关性分析和模糊规则的高压电缆状态评价方法. 电力大数据. 2022(10): 53-61 .

    Other cited types(11)

Catalog

    Article views PDF downloads Cited by(29)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return