基于改进SDU-YOLOv8的军事飞机目标检测算法

赵海丽; 包大泱; 张从豪; 刘鹏; 王彩霞; 景文博

doi:10.12382/bgxb.2025.0294

您当前的位置：

首页 >

文章列表页 >

基于改进SDU-YOLOv8的军事飞机目标检测算法

更新时间：2026-04-24

- 基于改进SDU-YOLOv8的军事飞机目标检测算法
- Military Aircraft Object Detection Algorithm Based on Improved SDU-YOLOv8
- 兵工学报 2026年47卷第1期页码：250294
- 作者机构：
  
  长春理工大学电子信息工程学院，吉林长春 130022
  长春理工大学光电工程学院，吉林长春 130022
- 作者简介：
  
  *通信作者邮箱：zhljlcc@126.com
- 基金信息：
  
  吉林省科技厅科技攻关项目(20210201092GX)
- DOI：10.12382/bgxb.2025.0294
  中图分类号： TP391.4
- 收稿：2025-04-17，
  
  网络首发：2026-02-11，
  
  纸质出版：2026-01-31
- 稿件说明：
移动端阅览
赵海丽, 包大泱, 张从豪, 等. 基于改进SDU-YOLOv8的军事飞机目标检测算法[J]. 兵工学报, 2026,47(1):250294.

ZHAO Haili, BAO Dayang, ZHANG Conghao, et al. Military Aircraft Object Detection Algorithm Based on Improved SDU-YOLOv8[J]. Acta Armamentarii, 2026, 47(1): 250294.
赵海丽, 包大泱, 张从豪, 等. 基于改进SDU-YOLOv8的军事飞机目标检测算法[J]. 兵工学报, 2026,47(1):250294. DOI： 10.12382/bgxb.2025.0294.

ZHAO Haili, BAO Dayang, ZHANG Conghao, et al. Military Aircraft Object Detection Algorithm Based on Improved SDU-YOLOv8[J]. Acta Armamentarii, 2026, 47(1): 250294. DOI： 10.12382/bgxb.2025.0294.

摘要

针对空天背景下军事飞机目标检测中存在的低对比度、小尺寸及形态多变导致的漏检率高、特征交互不足等问题，提出基于YOLOv8改进的SDU-YOLOv8网络。通过构建SSGBlock深度特征提取模块、动态可学习的Dy-RepGFPN特征融合网络以及参数共享的UCDN-Head检测头，实现特征提取、融合与检测头的协同优化。在自建军事飞机数据集上的实验结果表明，SDU-YOLOv8网络较基准YOLOv8的mAP@0. 5提升2. 5%，达到95. 7%，参数量减少6. 7%，计算量降低9. 9%，在小尺寸、低对比度及形变目标的检测鲁棒性显著增强；新方法在保持轻量化的同时实现了检测精度与效率的均衡优化，为空天侦察场景下的军事飞机检测提供了高效解决方案。

Abstract

Aiming at the problems of high leakage rate and insufficient feature interaction due to low contrast

small size and variable morphology in military aircraft target detection in the air-sky context

this paper proposes an improved SDU-YOLOv8 network based on YOLOv8. The synergistic optimization of feature extraction

fusion and detection head is achieved by constructing SSGBlock deep feature extraction module

dynamically learnable Dy-RepGFPN feature fusion network

and parameter-sharing UCDN-Head detection head. The improved SDU-YOLOv8 network is tested on a self-constructed military aircraft dataset. Compared with the benchmark YOLOv8

the improved SDU-YOLOv8 network improves mAP@ 0. 5 by 2. 5%

reduces the amount of parameters and the amount of computation by 6. 7% and 9. 9%

respectively

and significantly enhances the detection robustness of small-size

low-contrast and deformation targets. The experimental results show that the proposed method achieves a balanced optimization of detection accuracy and efficiency while maintaining lightweight

providing an efficient solution for military aircraft detection in air and space reconnaissance scenarios.

关键词

Keywords

references

张永梅，赖裕平，马健喆，等.基于视频的装甲车和飞机检测跟踪及轨迹预测算法[J].兵工学报，2021,42（3）:545-554.

ZHANG Y M, LAI Y P, MA J Z, et al. A video-based prediction algorithm for armored vehicle and aircraft detection/tracking and trajectory[J]. Acta Armamentarii,2021,42（3）:545-554.（in Chinese）

杨环宇，王军，吴祥，等.一种坐标通道注意力深度学习网络的军用飞机识别方法[J].兵工学报，2024,45（7）:2128-2143.

YANG H Y, WANG J, WU X, et al. A method for military aircraft recognition using a coordinate attention-based deep learning network[J]. Acta Armamentarii, 2024, 45（7）: 2128-2143.（in Chinese）

PISNER D A, SCHNYER D M. Support vector machine [M]∥MECHELLI A, VIEIRA S, edit. Machine Learning. New York, NY, US:Academic Press,2020:101-121.

RIGATTI S J. Random forest[J]. Journal of Insurance Medicine, 2017,47（1）:31-39.

REN S Q, HE K M, GIRSHICK R, et al. Faster r-cnn:towards real-time object detection with region proposal: arXiv: 1506. 01497 [R]. Ithaca, NY, US:Cornell University,2015:1506. 01497.

REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real-time object detection[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, US:IEEE,2016:779-788.

REDMON J, FARHADI A. YOLO9000:better, faster, stronger[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, US:IEEE,2017:7263-7271.

REDMON J, FARHADI A. YOLO3: an incremental improvement [C]∥ Computer Vision and Pattern Recognition. Berlin, Heidelberg, Germany:Springer,2018,1804:1-6.

BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4:optimal speed and accuracy of object detection:arXiv:2004. 10934[R]. Ithaca, NY, US:Cornell University,2020:2004. 10934.

JOCHER G, STOKEN A, BOROVEC J, et al. Ultralytics/YOLOv5:v3.0[CP/OL]. Zenodo 2020[2024-02-10]. DOI:10. 5281/zenodo. 3983579.

赵海丽，许修常，潘宇航.基于改进YOLOv7-tiny的车辆目标检测算法[J].兵工学报，2025,46（4）:240393.

ZHAO H L, XU X C, PAN Y H. Vehicle target detection algorithm based on improved YOLOv7-tiny[J]. Acta Armamentarii,2025, 46（4）:240393.（in Chinese）

GLENN J, AYUSH C, JING Q, et al. Ultralytics/ YOLOv8:v8. 1. 0[CP/OL].（2023-02-10）[2024-02-10]. https:∥github. com/ultralytics/ultralytics/releases/tag/v8. 1. 0.

WANG Y F, WANG T, ZHOU X, et al. TransEffiDet: aircraft detection and classification in aerial images based on EfficientDet and transformer[J]. Computational Intelligence and Neuroscience, 2022,2022（1）:2262549.

CHEN X X, JIANG H, ZHENG H X, et al. Det-yolo:an innovative high-performance model for detecting military aircraft in remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2024:17753-17771.

YANG Z Q, GUAN Q, ZHAO K, et al. Multi-branch auxiliary fusion YOLO with re-parameterization heterogeneous convolutional for accurate object detection [C]∥Proceedings of Chinese Conference on Pattern Recognition and Computer Vision. Singapore:Springer,2024:492-505.

WANG J L, BAI Z, ZHANG X M, et al. A lightweight remote sensing aircraft object detection network based on improved YOLOv5n[J]. Remote Sensing,2024,16（5）:857.

HUANG M, MI W K, WANG Y M. EDGS-YOLOv8:an improved YOLOv8 lightweight UAV detection model [J]. Drones, 2024, 8（7）:337.

FENG Y F, HUANG J G, DU S Y, et al. Hyper-yolo:when visual object detection meets hypergraph computation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2024, 47（4）:2388-2401.

MX X, DAI X Y, BAI Y, et al. Rewrite the stars [C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, US: IEEE, 2024: 5694-5703.

JIANG Y Q, TAN Z Y, WANG J Y, et al. GiraffeDet:a heavyneck paradigm for object detection: arXiv: 2202. 04256 [R]. Ithaca, NY, US:Cornell University,2022:2202. 04256.

LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]∥Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, HI, US:IEEE,2017:2117-2125.

LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation [C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, US:IEEE,2018:8759-8768.

XU X Z, JIANG Y Q, CHEN W H, et al. DAMO-YOLO:a report on real-time object detection design: arXiv: 2211. 15444 [R]. Ithaca, NY, US:Cornell University,2022:2211. 15444.

LIU W Z, LH H, FU H T, et al. Learning to upsample by learning to sample [C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision. Paris, France:IEEE,2023:6027-6037.

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于频域TCAE-Informer的滚动轴承剩余使用寿命预测方法