A YOLO-EfficientNet Dual-stage Architecture for Highaccuracy Real-time Projectile-target Deviation Measurement

ZHAO Yuliang; YAN Shaojun; LI Miao; SUN Manhui; LÜ Xiaoyong

doi:10.12382/bgxb.2025.0856

您当前的位置：

首页 >

文章列表页 >

A YOLO-EfficientNet Dual-stage Architecture for Highaccuracy Real-time Projectile-target Deviation Measurement

更新时间：2026-07-06

- A YOLO-EfficientNet Dual-stage Architecture for Highaccuracy Real-time Projectile-target Deviation Measurement
- Acta Armamentarii Vol. 47, Issue 6, Pages: 250856(2026)
- 作者机构：
  
  东北大学秦皇岛分校智能感知与光电工程学院，河北秦皇岛 066004
  陆军工程大学石家庄校区，河北石家庄 050003
  军事科学院战争研究院，北京 100091
- 作者简介：
- 基金信息：
- DOI：10.12382/bgxb.2025.0856
  CLC： TJ765
- Received：17 September 2025，
  
  Online First：09 March 2026，
  
  Published：2026-06
- 稿件说明：
移动端阅览
ZHAO Yuliang, YAN Shaojun, LI Miao, et al. A YOLO-EfficientNet Dual-stage Architecture for Highaccuracy Real-time Projectile-target Deviation Measurement[J]. Acta Armamentarii, 2026, 47(6): 250856.
DOI：

ZHAO Yuliang, YAN Shaojun, LI Miao, et al. A YOLO-EfficientNet Dual-stage Architecture for Highaccuracy Real-time Projectile-target Deviation Measurement[J]. Acta Armamentarii, 2026, 47(6): 250856. DOI： 10.12382/bgxb.2025.0856.

摘要

高精度实时弹目偏差测量是提升现代火力打击系统命中精度与闭环校射能力的关键技术。然而，现有方法普遍存在实时性差、精度低和环境鲁棒性不足等问题。为此，提出一种基于YOLO-EfficientNet的双阶段深度学习模型，实现弹目目标的快速检测与偏差精准回归。在目标检测阶段采用轻量化改进的YOLOv11网络实现弹目区域的实时鲁棒检测；在偏差回归阶段通过嵌入坐标注意力机制的剪枝版EfficientNetV2网络，实现亚像素级偏差回归；设计标准化感兴趣区域生成机制，抑制背景干扰，增强模型在复杂环境下的稳定性。实验结果表明：所提出的双阶段模型在检测任务中，交并比阈值0.5至0.95范围内的平均精度均值达到82.6%，回归任务均方误差低至0.1683，并且整体网络帧率达107.9帧/s，有效满足了弹目偏差测量任务的实际需求，提供一个新的弹目偏差测量范式。

Abstract

High-precision real-time projectile-target deviation measurement is a key technology for enhancing the hit accuracy and closed-loop calibration capability of modern firepower strike systems. However

the existing methods generally suffer from poor real-time performance

low accuracy

and insufficient environmental robustness. To address these issues

this paper proposes a two-stage deep learning framework based on YOLO-EfficientNet for the fast detection of projectile and target and the accurate deviation regression. In the target detection stage

an improved lightweight YOLOv11 network is employed to achieve the real-time and robust detection of the projectile-target region. In the deviation regression stage

a pruned version of the EfficientNetV2 network embedded with a coordinate attention mechanism is used to accomplish sub-pixel-level deviation regression. A standardized region-of-interest generation mechanism is designed to suppress the background interference and enhance the stability of model in complex environments. Experimental results show that the proposed two-stage model achieves an mAP50-95 of 82.6% in the detection task

a mean square error of 0.1683 in the regression task

and an overall network frame rate of 107.9 fps

effectively meeting the practical requirements of projectile-target deviation measurement tasks and providing a new paradigm for projectile-target deviation measurement.

关键词

Keywords

references

崔勇平，邢清华. 从俄乌战争看无人机对野战防空的挑战和启示[J].航天电子对抗，2022，38（4）:1-3.

CUI Y P，XING Q H. The challenge and enlightenment of UAV to field air defense from the Russia-Ukraine war [J]. Aerospace Electronic Countermeasures，2022，38（4）:1-3.（in Chinese）

陈浩，屈艺，吴盘龙，等. 弹目偏差仿真系统的设计与实现[J].兵器装备工程学报，2020，41（9）:154-159.

CHEN H，QU Y，WU P L，et al. Design and implementation of missile target deviation simulation system[J]. Journal of Ordnance Equipment Engineering，2020，41（9）:154-159.（in Chinese）

胡国欣，周唯，邵翔宇. 基于面阵式激光雷达的弹目交会参数解算仿真研究[J].舰船电子工程，2023，43（9）:88-94.

HU G X，ZHOU W，SHAO X Y. Simulation study of missile target rendezvous parameters based on array laser radar [J]. Naval Electronic Engineering，2023，43（9）:88-94.（in Chinese）

牛龙飞. 基于LFMCW雷达测距的空中目标轨迹测量方法[J].火力与指挥控制，2022，47（6）:171-175.

NIU L F. Measurement method of air target trajectory based on LFMCW radar ranging [J]. Fire Control & Command Control，2022，47（6）:171-175.（in Chinese）

邓桂福，刘海良，高节.基于LFMCW雷达的标量脱靶量测量系统[J].雷达科学与技术，2018，16（6）:671-675.

DENG G F，LIU H L，GAO J. Scalar miss distance measurement system based on LFMCW radar [J].Radar Science and Technology，2018，16（6）:671-675.（in Chinese）

毕月，冯玉光. 基于FMCW的导弹脱靶量测量系统设计与仿真[J].兵器装备工程学报，2021，42（4）:193-197.

BI Y，FENG Y G. Design and simulation of missile miss distance measurement system based on FMCW [J]. Journal of Ordnance Equipment Engineering，2021，42（4）:193-197.（in Chinese）

张飞猛，马春茂. 对空射击声学靶脱靶量测试系统的精度分析[J].兵工学报，2000，21（1）:23-26.

ZHANG F M，MA C M. Accuracy analysis of miss distance measurement system for acoustic target in air shooting [J]. Acta Armamentarii，2000，21（1）:23-26.（in Chinese）

王玉龙，刘艳红，陈均辉，等. 超音速弹丸斜入射脱靶量计算方法[J].电子测量技术，2020，43（4）:71-76.

WANG Y L，LIU Y H，CHEN J H，et al. Calculation method for miss distance of supersonic projectiles at oblique incidence [J]. Electronic Measurement Technology，2020，43（4）: 71-76.（in Chinese）

王激扬，白风宇，孙晓峰. 基于“脱靶管”原理的防空导弹脱靶量估算方法[J].现代防御技术，2023，51（2）:49-54.

WANG J Y，BAI F Y，SUN X F. Estimation method of miss distance of air defense missile based on “miss tube” principle [J]. Modern Defense Technology，2023，51（2）:49-54.（in Chinese）

韩先平. 靶场光学测量空间脱靶量高精度计算方法[J].电子测量技术，2019，42（17）:60-64.

HAN X P. High precision calculation method for space miss distance of optical measurement in shooting range [J]. Electronic Measurement Technology，2019，42（17）:60-64.（in Chinese）

崇元，艾葳，王玉坤. 空中脱靶量光学测量精度评估[J].战术导弹技术，2024（3）:41-46.

CHONG Y，AI W，WANG Y H. Evaluation of optical measurement accuracy of air miss distance [J]. Tactical Missile Technology，2024（3）:41-46.（in Chinese）

RABADAN J,GUERRA V,GUERRA C,et al. A novel ranging technique based on optical camera communications and time difference of arrival[J]. Applied Sciences,2019,9（11）:2382.

毕月，冯玉光. 关于改进导弹脱靶量测量方法的研究[J].电光与控制，2021，28（8）:71-76.

BI Y，FENG Y G. Research on improving the measurement method of missile miss distance [J]. Electro Optics and Control，2021，28（8）:71-76.（in Chinese）

张琦，迟明祎，李佩军，等. 同测试平台脱靶量测试方法研究[J].火力与指挥控制，2023，48（2）:167-172.

ZHANG Q，CHI M Y，LI P J，et al. Research on miss distance test method of the same test platform [J]. Fire and Command and Control，2023，48（2）:167-172.（in Chinese）

BOCHKOVSKIY A,WANG C Y,LIAO H Y M. YOLOv4:optimal speed and accuracy of object detection: arXiv: 2004.10934 [R/OL]. Ithaca,NY,US:Cornell University,2020（2020-04-23）. https://arxiv. org/abs/2004.10934.

LI C Y,LI L L,JIANG H L,et al. YOLOv6:a single-stage object detection framework for industrial applications: arXiv: 2209.02976 [R/OL]. Ithaca, NY, US: Cornell University, 2022（2022-09-07）. https://arxiv. org/abs/2209.02976.

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 [C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023:7464-7475.

WANG C Y,YEH I H,LIAO H Y M. YOLOv9:learning what you want to learn using programmable gradient information: arXiv:2402.13616[R/OL]. Ithaca,NY,US:Cornell University,2024（2024-02-29）. https://arxiv. org/abs/2402.13616.

WANG A,CHEN H,LIU L H,et al. YOLOv10:real-time end-toend object detection:arXiv:2405.14458 [R/OL]. Ithaca,NY, US:Cornell University,2024（2024-10-30）. https://arxiv.org/abs/2405.14458.

TAN M X, LE Q V. Efficientnetv2: smaller models and faster training:arXiv: 2104.00298 [R/OL]. Ithaca, NY, US: Cornell University, 2021（2021-04-01）. https://arxiv. org/abs/2104.00298.

QIN D,LEICHNER C,DELAKIS M,et al. MobileNetV4-universal models for the mobile ecosystem:arXiv:2404.10518 [R/OL].Ithaca,NY,US:Cornell University,2024（2024-09-29）. https://arxiv. org/abs/2404.10518.

TAN M X,PANG R M,LE Q V. EfficientDet:scalable and efficient object detection [C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York,NY,US:IEEE,2020:10781-10790.

孟莉莎，杨贤昭，刘惠康. 基于CA-EfficientNetV2的蘑菇图像分类算法研究[J]. 激光与光电子学进展，2022，59（24）:56-63.

MENG L S，YANG X Z，LIU H K. Research on mushroom image classification algorithm based on CA-EfficientNetV2 [J]. Progress in Laser and Optoelectronics，2022，59（24）:56-63.（in Chinese）

HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville,TN,US:IEEE,2021:13708-13717.

LIN T Y,DOLLÁR P, GIRSHICK R B, et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. New York,NY,US:IEEE,2017:936-944.

Views

185

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research and Verification of Multi-objective Cooperative Control Technology for Multi-axis Distributed Drive Vehicle

Electro-mechanical-magnetic-control Coupling Dynamic Modeling of Electromechanical Transmission System

Heterogeneous Integration Theory and Design Method: Innovative Exploration for Design of Future Tank and Armored Vehicles

The Influence of Arc Additive and Subtractive Hybrid Manufacturing on the Forming Quality of 316L Stainless Steel

Computational Fusion Method for Real-time 3D Reconstruction of Weld Pool

Related Author

LI Miao

SUN Manhui

Related Institution

Shijiazhuang Campus, Army Engineering University

Postal code：100089
Tel：010-68963060/68962718 Fax：010-68963025 Email：bgxb@cos.org.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05059581号-4 京公网安备11010802024360号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：198925 Visits Today：644 Online Users：10

⁰