가우스 교차 특징 융합 기반 고광대역 영상 분류 방법

  • role: First author第一作者
  • Affiliation:

    College of Computer Science and Engineering, North Minzu University, Yinchuan 750021, China

  • Email:2811862998@qq.com
  • Introduction:王文龙(1999-),男,宁夏银川人,硕士研究生,2022年于电子科技大学成都学院获得学士学位,主要从事高光谱图像分类研究。E-mail:2811862998@qq.com
WANG Wenlong1,  
  • role: Corresponding author通信作者
  • Affiliation:

    College of Computer Science and Engineering, North Minzu University, Yinchuan 750021, China

  • Email:wanghr@nun.edu.cn
  • Introduction:王海荣(1977-),女,宁夏石嘴山人,教授,博士,2017年于东北大学获得博士学位,主要从事大数据知识工程与智能信息处理研究,E-mail: wanghr@nun.edu.cn
WANG Hairong1*,  
  • Affiliation:

    College of Computer Science and Engineering, North Minzu University, Yinchuan 750021, China

YI Zhihang1,  
  • Affiliation:

    College of Computer Science and Engineering, North Minzu University, Yinchuan 750021, China

YANG Zhenye1,  
  • Affiliation:

    Ningxia Key Laboratory of Meteorological Disaster Prevention and Reduction (Ningxia Institute of Meteorological Sciences), Yinchuan 750002, China

YANG Jianling2

추상적인

기존 고광대역 영상(Hyperspectral Image, HSI) 분류 방법에서 지역 특징과 전역 특징 간의 불균형 문제를 해결하기 위해 본 논문에서는 가우스 교차 특징 융합 모델을 구축하였다. 서로 다른 특징 간의 상호 연결은 요소별 곱셈 연산을 통해 구현되었으며, 가우스 교차 주의 특징 융합 알고리즘을 설계하여 매핑 벡터 간의 유사도에 따라 두 가지 특징의 내재적 연관성을 분석하였다. 가우스 함수를 사용하여 융합 가중치를 양자화하였고, 주요 파라미터 최적화를 통해 지역 및 전역 특징에 대한 동적 가중치를 구현하여 융합 과정에서 두 특징의 균형을 보장하였다. 방법의 유효성을 검증하기 위해 농작물 장면인 Indian Pines, 도시 지형 장면인 Pavia University, 농업 식생 장면인 Salinas 및 이종 혼합 장면인 LongKou의 네 가지 대표 공개 데이터셋에서 실험을 수행하였으며, 실험 결과를 DCSST, SMESC, Vit-cov 등 11가지 주요 방법과 비교하였다. 전반적 정확도(Overall Accuracy, OA), 평균 정확도(Average Accuracy, AA), 카파 지수를 사용하여 평가한 결과 본 방법이 최상의 성능을 보였다. 이는 본 방법이 식물, 인공 지형 및 이종 혼합 장면 분류에서 우수한 분류 성능을 가지며, 일정 부분 방법의 일반화 능력이 우수함을 나타낸다.

키워드

고광대역 영상 분류;주의 메커니즘;가우스 함수;특징 추출;특징 융합

References

  1. 1.
    ZHANG W D, LI Z X, LI G H, et al. GACNet: generate adversarial-driven cross-aware network for hyperspectral wheat variety identification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5503314. doi:
  2. 2.
    CHE M, WANG H R, XU X, et al. PSO-DF: a hyperspectral model for estimating nitrogen content in rice leaves[J]. Remote Sensing Technology and Application, 2024, 39(2): 280-289. (in Chinese)
  3. 3.
    WANG Z Y, ZUO R G. An evaluation of convolutional neural networks for lithological mapping based on hyperspectral images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 6414-6425. doi:
  4. 4.
    WANG M L, XU Y C, WANG Z S, et al. Deep margin cosine autoencoder-based medical hyperspectral image classification for tumor diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 2520512. doi:
  5. 5.
    JING H Z, TAO L J, ZHANG H K. Specral-spatial classification of hyperspectral imagery with hybrid architecture of 3D-CNN and Transformer[J]. Opt. Precision Eng., 2024, 32(23): 3504-3512. (in Chinese). doi:
  6. 6.
    LIU J, LI Y Q, LIU Y. Active learning-clustering-group convolutions network for hyperspectral images classification[J]. Opt. Precision Eng., 2024, 32(9): 1395-1407. (in Chinese). doi:
  7. 7.
    GAO H M, SHENG R H, CHEN Z H, et al. Multiscale random-shape convolution and adaptive graph convolution fusion network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5516017. doi:
  8. 8.
    LIU X, NG A H, GE L L, et al. Multibranch fusion: a multibranch attention framework by combining graph convolutional network and CNN for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5528817. doi:
  9. 9.
    LI J, YU L, DUAN Y L, et al. Advances in graph neural network-based hyperspectral remote sensing image classification[J]. National Remote Sensing Bulletin, 2025, 29(6): 1681-1704. (in Chinese)
  10. 10.
    YANG Y Q, TANG X, ZHANG X R, et al. Semi-supervised multiscale dynamic graph convolution network for hyperspectral image classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(5): 6806-6820. doi:
  11. 11.
    FENG H, WANG Y C, CHEN C, et al. Hyperspectral image classification framework based on multichannel graph convolutional networks and class-guided attention mechanism[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5515115. doi:
  12. 12.
    GONG X L, LI Y, JIA S H, et al. Tensor-based dictionary learning sparse representation classification for hyperspectral image[J]. Spectroscopy and Spectral Analysis, 2025, 45(3): 798-807. (in Chinese)
  13. 13.
    LIU J, LI Y, LIU Y. Hyperspectral images feature extraction and classification based on fractional differentiation[J]. Opt. Precision Eng., 2023, 31(21): 3221-3236. (in Chinese). doi:
  14. 14.
    WANG B L, WANG S S, ZHANG Z. Partial optimal transport-based domain adaptation for hyperspectral image classification[J]. Opt. Precision Eng., 2023, 31(17): 2555-2563. (in Chinese). doi:
  15. 15.
    CUI Y, LUO L, WANG L, et al. Hyperspectral image classification based on double-hop graph attention multiview fusion network[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 20080-20097. doi:
  16. 16.
    XU F L, MEI S H, ZHANG G, et al. Bridging CNN and transformer with cross-attention fusion network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5522214. doi:
  17. 17.
    LIU C, YANG L W, LI Z, et al. Multi-level relation learning for cross-domain few-shot hyperspectral image classification[J]. Applied Intelligence, 2024, 54(5): 4392-4410. doi:
  18. 18.
    YU C Y, ZHU Y C, SONG M P, et al. Unseen feature extraction: spatial mapping expansion with spectral compression network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5521915. doi:
  19. 19.
    WANG Y F, YU X D, WEN X Y, et al. Learning a 3-D-CNN and convolution transformers for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21: 5504505. doi:
  20. 20.
    TIAN R, LIU D Q, BAI Y, et al. Swin-MSP: a shifted windows masked spectral pretraining model for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 4509114. doi:
  21. 21.
    SUN L, ZHANG H, ZHENG Y H, et al. MASSFormer: memory-augmented spectral-spatial transformer for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5516415. doi:
  22. 22.
    YANG A T, LI M, DING Y, et al. GTFN: GCN and transformer fusion network with spatial-spectral features for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 6600115. doi:
  23. 23.
    LIU C, DONG A, DONG D M, et al. Contrastive graph convolution network with skip connections for few-shot hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21: 5502005. doi:
  24. 241.
    ZHOU H, LUO F L, ZHUANG H P, et al. Attention multihop graph and multiscale convolutional fusion network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5508614. doi:
  25. 25.
    WANG Q W, HUANG J B, WANG S Y, et al. Community structure guided network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 4404115. doi:
  26. 26.
    WANG G C, ZHANG X R, PENG Z L, et al. S2Mamba: a spatial-spectral state space model for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 5511413. doi:

더 읽기

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website