基于改进YOLOv7的遥感图像小目标检测方法

doi:10.3778/j.issn.1002-8331.2310-0279

摘要/Abstract

摘要： 针对遥感图像中小目标数量众多且背景复杂所导致的识别精度低的问题，提出了一种改进的遥感图像小目标检测方法。该方法基于改进的YOLOv7网络模型，将双级路由注意力机制加入至下采样阶段以构建针对小目标的特征提取模块MP-ATT（max pooling-attention），使得模型更加关注小目标的特征，提高小目标检测精度。为了加强对小目标的细节感知能力，使用DCNv3（deformable convolution network v3）替换骨干网络中的二维卷积，以此构建新的层聚合模块ELAN-D。为网络设计新的小目标检测层以获取更精细的特征信息，从而提升模型的鲁棒性。同时使用MPDIoU（minimum point distance based IoU）替换原模型中的CIoU来优化损失函数，以适应遥感图像的尺度变化。实验表明，所提出的方法在DOTA-v1.0数据集上取得了良好效果，准确率、召回率和平均准确率（mean average precision，mAP）相比原模型分别提升了0.4、4.0、2.3个百分点，证明了该方法能够有效提升遥感图像中小目标的检测效果。

关键词: 深度学习, 目标检测, 遥感图像, 小目标, YOLOv7

Abstract: Aiming at the issue of low recognition accuracy for small targets in remote sensing images, which is caused by the presence of numerous small targets and complex backgrounds, an improved small target detection method for remote sensing images is introduced. Based on an enhanced YOLOv7 network model, this method incorporates a bi-level routing attention mechanism at the down-sampling stage to construct the feature extraction module for small targets MP-ATT (max pooling-attention). The model pays more attention to the characteristics of small targets and improves the accuracy of small target detection. To enhance the perception of small target details, two-dimensional convolutions in the backbone network are replaced with deformable convolution network v3 (DCNv3), and a new layer aggregation module ELAN-D is built. A novel small object detection layer is devised for the network to acquire more refined feature information, thereby enhancing the model’s robustness. Additionally, the loss function is optimized by replacing CIoU with MPDIoU (minimum point distance based IoU) in order to adapt to scale changes in remote sensing images and improve network robustness. Experimental results on the DOTA-v1.0 dataset demonstrate that the proposed method achieves significant improvement compared to the original model, the accuracy, recall and mAP(mean average precision) are improved by 0.4, 4.0 and 2.3 percentage points, which proves that the proposed method can effectively improve the detection effect of small targets in remote sensing images.

Key words: deep learning, target detection, remote sensing images, small target, YOLOv7

苗茹, 岳明, 周珂, 杨阳. 基于改进YOLOv7的遥感图像小目标检测方法[J]. 计算机工程与应用, 2024, 60(10): 246-255.

MIAO Ru, YUE Ming, ZHOU Ke, YANG Yang. Small Target Detection Method in Remote Sensing Images Based on Improved YOLOv7[J]. Computer Engineering and Applications, 2024, 60(10): 246-255.

参考文献

[1] 聂光涛, 黄华.光学遥感图像目标检测算法综述[J].自动化学报, 2021, 47(8): 1749-1768.
NIE G T, HUANG H. A survey of object detection in optical remote sensing images[J]. Acta Automatica Sinica, 2021, 47(8): 1749-1768.
[2] 廖育荣, 王海宁, 林存宝, 等.基于深度学习的光学遥感图像目标检测研究进展[J].通信学报, 2022, 43(5): 190-203.
LIAO Y R, WANG H N, LIN C B, et al. Research progress of deep learning-based object detection of optical remote sensing images[J]. Journal on Communications, 2022, 43(5): 190-203.
[3] 张路青, 郭莹.基于卷积神经网络的遥感图像目标检测识别[J].舰船电子工程, 2023, 43(5): 49-53.
ZHANG L Q, GUO Y. Remote sensing image object detection and recognition based on convolutional neural network[J]. Ship Electronic Engineering, 2023, 43(5): 49-53.
[4] 赵加坤, 孙俊, 韩睿, 等.基于改进的Faster RCNN遥感图像目标检测[J].计算机应用与软件, 2022, 39(5): 192-196.
ZHAO J K, SUN J, HAN R, et al. Object detection based on improved Faster RCNN for remote sensing image[J]. Computer Applications and Software, 2022, 39(5): 192-196.
[5] 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[J].光学学报, 2022, 42(12): 138-148.
XUE J D, ZHU J J, ZHANG J, et al. Object detection in optical remote sensing images based on FFC-SSD model[J]. Acta Optica Sinica, 2022, 42(12): 138-148.
[6] 许新云. 光学遥感图像小目标检测方法研究[D]. 太原: 太原科技大学, 2023.
XU X Y. Research on small target detection methods in optical remote sensing images[D]. Taiyuan: Taiyuan University of Science and Technology, 2023.
[7] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the 15th European Conference on Computer Vision, 2018: 3-19.
[8] 余俊宇, 刘孙俊, 许桃.融合注意力机制的YOLOv7遥感小目标检测算法研究[J].计算机工程与应用, 2023, 59(20): 167-175.
YU J Y, LIU S J, XU T. Research on YOLOv7 remote sensing small target detection algorithm integrating attention mechanism[J]. Computer Engineering and Applications, 2023, 59(20): 167-175.
[9] PAN X, GE C, LU R, et al. On the integration of self-attention and convolution[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 815-825.
[10] 吴建成, 郭荣佐, 成嘉伟, 等. 注意力特征融合的快速遥感图像目标检测算法[J]. 计算机工程与应用, 2024, 60(1): 207-216.
WU J C, GUO R Z, CHENG J W, et al. A fast remote sensing image object detection algorithm based on attention feature fusion[J]. Computer Engineering and Applications, 2024, 60(1): 207-216.
[11] 梁礼明, 李仁杰, 董信, 等.基于上下文信息的遥感图像目标检测[J].电光与控制, 2023, 30(10): 89-94.
LIANG L M, LI R J, DONG X, et al. Target detection in remote sensing images based on context information[J]. Electronics Optics & Control, 2023, 30(10): 89-94.
[12] 肖振久, 林渤翰, 曲海成. 改进YOLOv7的SAR舰船检测算法[J]. 计算机工程与应用, 2023, 59(15): 243-252.
XIAO Z J, LIN B H, QU H C, Improved SAR ship detection algorithm for YOLOv7[J]. Computer Engineering and Applications, 2023, 59(15): 243-252.
[13] 李安达, 吴瑞明, 李旭东. 改进YOLOv7的小目标检测算法研究[J]. 计算机工程与应用, 2024, 60(1): 122-134.
LI A D, WU R M, LI X D. Research on improving YOLOv7’s small target detection algorithm[J]. Computer Engineering and Applications, 2024, 60(1): 122-134.
[14] 崔勇强, 黄谦, 高雪, 等.城市低空小型无人机目标实时高精度检测算法[J/OL].计算机工程与应用 [2023-11-22]. http://kns.cnki.net/kcms/detail/11.2127.TP.20230814.1642.
012.html.
CUI Y Q, HUANG Q, GAO X, et al. Real-time high-precision detection algorithm for small UAV targets in urban low-altitude areas[J/OL]. Computer Engineering and Applications [2023-11-22]. http://kns.cnki.net/kcms/detail/11.2127.TP.20230814.1642.012.html.
[15] QI Z T, REN Y, LONG J, et al. Application of YOLOv7 in remote sensing image target detection[C]//Proceedings of the 42nd Chinese Control Conference, Tianjin, Jul 24-26, 2023: 7603-7608.
[16] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J]. arXiv:2207.02696, 2022.
[17] DAI J F, QI H Z, XIONG Y W, et al. Deformable convolutional networks[J]. arXiv:1703.06211, 2017.
[18] WANG W H, DAI J F, CHEN Z, et al. InternImage: exploring large-scale vision foundation models with deformable convolutions[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, 2023: 14408-14419.
[19] VASWANI A, SHAZZER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st Conference on Neural Information Processing Systems, Long Beach, 2017: 5998-6008.
[20] ZHU L, WANG X J, KE Z H, et al. BiFormer: vision transformer with bi-level routing attention[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, 2023: 10323-10333.
[21] ZHENG Z H, WANG P, REN D W, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J]. IEEE Transactions on Cybernetics, 2021, 52(8): 8574-8586.
[22] ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[J]. arXiv:1911.08287, 2019.
[23] MA S L, XU Y. MPDIoU: a loss for effcient and accurate bounding box regression[J]. arXiv:2307.07662, 2023.
[24] XIA G S, BAI X, DING J, et al. DOTA: a large-scale dataset for object detection in aerial images[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018: 3974-3983.
[25] 张洋, 夏英.多尺度特征融合的遥感图像目标检测方法[J/OL]. 计算机科学[2023-10-05]. http://kns.cnki.net/kcms/detail/50.1075.tp.20230925.1342.094.html.
ZHANG Y, XIA Y. Object detection method with multi-scale feature fusion for remote sensing images[J/OL]. Computer Science [2023-10-05]. http://kns.cnki.net/kcms/detail/50.1075.tp.20230925.1342.094.html.
[26] HU J M, ZHI X Y, SHI T J, et al. PAG-YOLO: a portable attention-guided YOLO network for small ship detection[J]. Remote Sensing, 2021, 13(16): 3059.
[27] ZHANG J Q, LEI J, XIE W Y, et al. SuperYOLO: super resolution assisted object detection in multimodal remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-15.