基于改进YOLOv7的遥感图像目标检测方法

兰州理工大学学报 ›› 2026, Vol. 52 ›› Issue (1): 93-100.

• 自动化技术与计算机技术 • 上一篇下一篇

基于改进YOLOv7的遥感图像目标检测方法

陈辉^*1, 田博¹, 赵永红², 瞿海平², 梁建虎²

1.兰州理工大学自动化与电气工程学院, 甘肃兰州 730050;
2.甘肃长风电子科技有限公司, 甘肃兰州 730070

收稿日期:2023-07-30 出版日期:2026-02-28 发布日期:2026-03-05
通讯作者: 陈辉(1978-),男,山西闻喜人,博士,教授,博导.Email:huich78@hotmail.com
基金资助:
国家自然科学基金(62163023,62366031,62363023),甘肃省基础研究创新群体(25JRRA058),中央引导地方科技发展资金(25ZYJA040),甘肃省重点人才项目(2024RCXM86),甘肃省军民融合发展专项资金

Remote sensing image object detection method based on enhanced YOLOv7

CHEN Hui¹, TIAN Bo¹, ZHAO Yong-hong², QU Hai-ping², LIANG Jian-hu²

1. School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou 730050, China;
2. Gansu Province Changfeng Electronic Technology Co., LTD, Lanzhou 730070, China

Received:2023-07-30 Online:2026-02-28 Published:2026-03-05

摘要/Abstract

摘要： 为了解决遥感图像中小目标规模大、目标分布密集以及容易产生漏检和误检等问题,提出了一种基于改进YOLOv7模型的遥感图像目标检测方法.该方法首先在YOLOv7模型中引入DCNv2结构和残差结构,重新构建了新的骨干网络,以增强目标浅层特征信息的提取,并提高网络的准确性.其次,在颈部网络中采用新的特征融合模块,并通过SimAM注意力机制,自适应调节浅层特征的纹理信息和深层语义信息的融合权重,更有针对性地抑制提取浅层特征时带来的噪声.最后,采用归一化高斯瓦瑟斯坦距离损失作为模型的回归损失函数,取代传统的IOU,以提高多尺度目标的检测能力.该算法在DOTAv1.0数据集上小目标平均精度达到20.1%,在DIOR数据集上小目标平均精度达到29.0%.同时,与YOLOv7、YOLOv6等方法相比,该算法展现出了较强的竞争力.

关键词: 遥感图像, 目标检测, 可变形卷积网络, SimAM注意力机制, 高斯瓦瑟斯坦距离

Abstract: To address the challenges posed by large-scale small object detection, dense object distribution, and issues of missed detections and false positives in remote sensing images, this paper introduces a remote sensing image object detection approach grounded in an enhanced YOLOv7 model. Initially, the method integrates the DCNv2 structure and residual architecture into the YOLOv7 model, reconstructing a novel backbone network to enhance the extraction of shallow-level features information and improve network accuracy. Subsequently, a pioneering feature fusion module is incorporated into the neck network, combined with the SimAM mechanism, which adaptively adjusts the fusion weights of both shallow-level texture information and deep-level semantic information, thereby effectively curbing noise introduced during shallow feature extraction and augmenting the representation of essential features. Finally, the normalized Gaussian Wasserstein distance loss function is used as the regression loss function, replacing the traditional IOU to improve the detection capability for multi-scale targets. Empirical findings derived from the DOTAv1.0 dataset reveal an average precision of 20.1% for small objects, while the DIOR dataset yields an average precision of 29.0%. Furthermore, compared to recent advanced methods such as YOLOv7 and YOLOv6, the proposed algorithm demonstrates strong competitive performance.

Key words: remote sensing image, object detection, deformable convolutional networks, SimAM attention mechanism, Gaussian Wasserstein distance

中图分类号:

TP751

陈辉, 田博, 赵永红, 瞿海平, 梁建虎. 基于改进YOLOv7的遥感图像目标检测方法[J]. 兰州理工大学学报, 2026, 52(1): 93-100.

CHEN Hui, TIAN Bo, ZHAO Yong-hong, QU Hai-ping, LIANG Jian-hu. Remote sensing image object detection method based on enhanced YOLOv7[J]. Journal of Lanzhou University of Technology, 2026, 52(1): 93-100.

参考文献

[1] 朱煜,方观寿,郑兵兵,等.基于旋转框精细定位的遥感目标检测方法研究 [J].自动化学报,2023,49(2):415-424.
[2] 王燕,李国臣,孙晓丽.基于多分类器融合的高光谱图像分类研究 [J].兰州理工大学学报,2022,48(1):98-106.
[3] LOWE D G.Distinctive image features from scale-invariant keypoints [J].International Journal of Computer Vision,2004,60:91-110.
[4] ATTARMOGHADDAM N,LI K F.An area-efficient FPGA implementation of a real-time multi-class classifier for binary images [J].IEEE Transactions on Circuits and Systems II:Express Briefs,2022,69(4):2306-2310.
[5] 吴鹏,徐洪玲,李雯霖,等.基于区域检测的多尺度Harris角点检测算法 [J].哈尔滨工程大学学报,2016,37(7):969-973.
[6] 戴博,吴晓峰,王斌.基于哈尔特征及结构复杂度的视觉显著性模型 [J].复旦学报(自然科学版),2014,53(5):651-658.
[7] 刘凤,刘浩哲,张文天,等.一种鲁棒的基于对抗结构的生物特征ROI提取方法 [J].自动化学报,2023,49(6):1339-1353.
[8] LI Y,ZHANG S,WANG W Q.A lightweight faster R-CNN for ship detection in SAR images [J].IEEE Geoscience and Remote Sensing Letters,2020,19:1-5.
[9] WANG Y,BASHIR S M A,KHAN M,et al.Remote sensing image super-resolution and object detection:benchmark and state of the art [J].Expert Systems with Applications,2022,197:116793.
[10] TANG L,TANG W,QU X,et al.A scale-aware pyramid network for multi-scale object detection in SAR images [J].Remote Sensing,2022,14(4):973.
[11] YANG X,SUN H,SUN X,et al.Position detection and direction prediction for arbitrary-oriented ships via multitask rotation region convolutional neural network [J].IEEE Access,2018,6:50839-50849.
[12] VAN ETTEN A.You only look twice:rapid multi-scale object detection in satellite imagery [J/OL].[2023-06-15].https://arxiv.org/pdf/1805.09512.
[13] CHEN S,ZHAN R,ZHANG J.Geospatial object detection in remote sensing imagery based on multiscale single-shot detector with activated semantics [J].Remote Sensing,2018,10(6):169-174.
[14] WANG P,SUN X,DIAO W,et al.FMSSD:feature-merged single-shot detection for multiscale objects in large-scale remote sensing imagery [J].IEEE Transactions on Geoscience and Remote Sensing,2019,58(5):3377-3390.
[15] SU H,WEI S,YAN M,et al.Object detection and instance segmentation in remote sensing imagery based on precise mask R-CNN [C]//2019 IEEE International Geoscience and Remote Sensing Symposium.Yokohama,Japan:IEEE,2019:1454-1457.
[16] FU Y,WU F,ZHAO J.Context-aware and depthwise-based detection on orbit for remote sensing image [C]//2018 24th International Conference on Pattern Recognition (ICPR).Beijing:[s.n.],2018:1725-1730.
[17] ZHU X,HU H,LIN S,et al.Deformable convnets v2:more deformable,better results [C]//Proceedings of the IEEE/CVF Conference on ComputerVision and Pattern Recognition.Long Beach,CA,USA:IEEE,2019:9308-9316.
[18] WANG C,NING X,SUN L,et al.Learning discriminative features by covering local geometric space for point cloud analysis [J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-15.
[19] WANG D,LIU Z,GU X,et al.Automatic detection of pothole distress in asphalt pavement using improved convolutional neural networks [J].Remote Sensing,2022,14(16):3892.
[20] WANG J,XU C,YANG W,et al.A normalized Gaussian Wasserstein distance for tiny object detection [J/OL].[2023-06-15].https://arxiv.org/pdf/2110.13389.
[21] XIA G S,BAI X,DING J,et al.DOTA:a large-scale dataset for object detection in aerial images [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA:IEEE,2018:3974-3983.
[22] LI K,WAN G,CHENG G,et al.Object detection in optical remote sensing images:a survey and a new benchmark [J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,159:296-307.
[23] WU Z,PAN S,CHEN F,et al.A comprehensive survey on graph neural networks [J].IEEE Transactions on Neural Networks and Learning Systems,2020,32(1):4-24.
[24] LV Z,WANG F,CUI G,et al.Spatial-spectral attention network guided with change magnitude image for land cover change detection using remote sensing images [J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-12.
[25] REDMON J,FARHADI A.Yolov3:an incremental improvement [J/OL].[2023-05-04].https://arxiv.org/pdf.1804.02767.
[26] BOCHKOVSKIY A,WANG C Y,LIAO Y M.Yolov4:optimal speed and accuracy of object detection [J/OL].[2023-05-04].https://arxiv.org/pdf/2004.10934.
[27] Github.Glenn-jocher.yolov5 [EB/OL].(2022-11-22)[2023-05-04].https://github.com/ultralytics/yolov5.
[28] GE Z,LIU S,WANG F,et al.Yolox:exceeding yolo series in 2021 [J/OL].[2023-05-04].https://arxiv.org/pdf/2107.08430.
[29] LI C,LI L,JIANG H,et al.YOLOv6:a single-stage object detection framework for industrial applications [J/OL].[2023-05-04].https://arxiv.org/pdf/2209.02976.
[30] 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/OL].[2023-05-04].https://arxiv.org/pdf/2207.02696.

基于改进YOLOv7的遥感图像目标检测方法

Remote sensing image object detection method based on enhanced YOLOv7

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	王燕, 王振宇. 基于改进SE-Net和深度可分离残差的高光谱图像分类[J]. 兰州理工大学学报, 2024, 50(2): 87-95.
[2]	王惠琴, 吕佳芸, 张伟. 基于双边滤波-BM3D算法的GPR图像去噪[J]. 兰州理工大学学报, 2022, 48(1): 91-97.
[3]	王燕, 李国臣, 孙晓丽. 基于多分类器融合的高光谱图像分类研究[J]. 兰州理工大学学报, 2022, 48(1): 98-106.
[4]	徐铸业, 赵小强. 基于Agast-Adaboost的图像匹配算法[J]. 兰州理工大学学报, 2020, 46(4): 110-115.