基于混合注意力和动态采样的遥感图像目标检测
作者:

Remote Sensing Image Target Detection Based on Hybrid Attention and Dynamic Sampling
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [25]
  • | | | |
  • 文章评论
    摘要:

    针对遥感图像目标检测中的复杂背景干扰, 目标密集堆积导致遥感图像目标检测模型效果差的问题, 通过对YOLOv5s目标检测模型进行改进. 首先使用混合注意力机制对CBAM (convolutional block attention module)加以改进并添加至骨干网络中, 使得模型所提取到的特征含有局部信息和全局信息, 以加强模型识别复杂背景下目标的能力; 其次使用超轻量级的动态上采样器DySample结构, 减少模型参数并提高检测效率, 最后使用EIoU损失函数提高对于待检测目标的定位水平. 在RSOD和DIOR数据集上进行了实验验证, 结果表明, 改进后的YOLOv5s在遥感图像目标检测中的准确度要比原始模型高7.8%, 同时能够满足遥感图像实时目标检测的需求; 此外与其他目标检测模型相比, 改进模型也能保有一定优势.

    Abstract:

    Ineffective object recognition models occur in remote sensing images through complex background interference and dense target integration. To this end, this study improves the YOLOv5s object output model. First, a mixed attention menu is utilized to improve the convolutional attention model (CBAM) and add it to backbone networks. Accordingly, the extracted features of the model contain local and global information to enhance the model’s ability to identify targets in complex backgrounds. Then the study uses the ultra-light sampler DySample to reduce model parameters and improve model performance. Finally, the study employs the EIoU loss function to improve the positioning level of the target to be detected. Experimental verification of RSOD and DIOR data sets shows that the improved YOLOv5s has a 7.8% higher accuracy than the original model in detecting targets in remote sensing images, meeting the real-time detection requirements of targets in remote sensing images. In addition, the improved model retains the advantages it has in comparison to other object recognition models.

    参考文献
    [1] Wang K, Wang Z, Li Z, et al. Oriented object detection in optical remote sensing images using deep learning: A survey. arXiv:2302.10473, 2024.
    [2] Sadgrove EJ, Falzon G, Miron D, et al. Real-time object detection in agricultural/remote environments using the multiple-expert colour feature extreme learning machine (MEC-ELM). Computers in Industry, 2018, 98: 183–191.
    [3] Kussul N, Lavreniuk M, Skakun S, et al. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters, 2017, 14(5): 778–782.
    [4] 薛俊达, 朱家佳, 张静, 等. 基于FFC-SSD模型的光学遥感图像目标检测. 光学学报, 2022, 42(12): 1210002.
    [5] Cheng G, Yuan X, Yao XW, et al. Towards large-scale small object detection: Survey and benchmarks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(11): 13467–13488.
    [6] 汪鹏, 郑文凤, 史进, 等. 基于MFANet和上下文特征融合的遥感影像目标检测. 应用科学学报, 2022, 40(1): 131–144.
    [7] 张绍文, 史卫亚, 张世强, 等. 基于加权感受野和跨层融合的遥感小目标检测. 电子测量技术, 2023, 46(18): 129–138.
    [8] 宋爽爽, 肖开斐, 刘昭华, 等. 一种基于YOLOv5的高分辨率遥感影像目标检测方法. 自然资源遥感, 2024, 36(2): 50–59.
    [9] 周沁坤, 周华平, 孙克雷, 等. ARST-YOLOv7: 用于航空遥感图像的小目标检测网络. 计算机工程与应用, 2024. http://kns.cnki.net/kcms/detail/11.2127.TP.20240905.1859.005.html, (2024-09-06)[2024-09-20].
    [10] 孙文赟, 车嘉航, 金忠. 基于全局上下文注意力特征融合金字塔网络的遥感目标检测. 计算机系统应用, 2024, 33(9): 114–122.
    [11] Zou ZX, Chen KY, Shi ZW, et al. Object detection in 20 years: A survey. Proceedings of the IEEE, 2023, 111(3): 257–276.
    [12] Woo S, Park J, Lee JY, et al. CBAM: Convolutional block attention module. Proceedings of the 15th European Conference on Computer Vision. Munich: Springer, 2018. 3–19.
    [13] Liu WZ, Lu H, Fu HT, et al. Learning to upsample by learning to sample. Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Paris: IEEE, 2023. 6004–6014.
    [14] Zhang YF, Ren WQ, Zhang Z, et al. Focal and efficient IoU loss for accurate bounding box regression. Neurocomputing, 2022, 506: 146–157.
    [15] Fu J, Liu J, Tian HJ, et al. Dual attention network for scene segmentation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 3141–3149.
    [16] Hu J, Shen L, Sun G. Squeeze-and-excitation networks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 7132–7141.
    [17] Hou QB, Zhou DQ, Feng JS. Coordinate attention for efficient mobile network design. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021. 13708–13717.
    [18] Wan DH, Lu RS, Shen SY, et al. Mixed local channel attention for object detection. Engineering Applications of Artificial Intelligence, 2023, 123: 106442.
    [19] Wang QL, Wu BG, Zhu PF, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 11531–11539.
    [20] Li K, Wan G, Cheng G, et al. Object detection in optical remote sensing images: A survey and a new benchmark. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159: 296–307.
    [21] Long Y, Gong YP, Xiao ZF, et al. Accurate object localization in remote sensing images based on convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(5): 2486–2498.
    [22] Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023. 7464–7475.
    [23] Zhao QJ, Sheng T, Wang YT, et al. M2Det: A single-shot object detector based on multi-level feature pyramid network. Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Honolulu: AAAI, 2019. 9259–9266.
    [24] Ge Z, Liu ST, Wang F, et al. YOLOX: Exceeding YOLO series in 2021. arXiv:2107.08430, 2021.
    [25] Tian Z, Shen CH, Chen H, et al. FCOS: Fully convolutional one-stage object detection. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019. 9626–9635.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

蔡清,王净雨,梁宏涛.基于混合注意力和动态采样的遥感图像目标检测.计算机系统应用,2025,34(3):171-179

复制
分享
文章指标
  • 点击次数:26
  • 下载次数: 474
  • HTML阅读次数: 7
  • 引用次数: 0
历史
  • 收稿日期:2024-09-04
  • 最后修改日期:2024-09-24
  • 在线发布日期: 2025-01-21
文章二维码
您是第10782479位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号