改进的YOLOv3算法及其在军事目标检测中的应用

于博文;吕明

兵工学报 ›› 2022, Vol. 43 ›› Issue (2) : 345-354.

EN 投稿 期刊 文章 图表 检索
高级检索

  • 主管：中国科学技术协会

    主编：许毅达

    ISSN 1000-1093

    　

  • 主办：中国兵工学会

    出版：《兵工学报》 编辑部

    CN 11-2176/TJ

《兵工学报》是我国国防科技领域最具影响力的学术期刊之一，创刊于1979年，目前被国内所有重要数据库收录，其综合评价指标近年来一直名列兵工技术类科技期刊的首位；《兵工学报》目前还被国际上著名的检索机构美国......
兵工学报 ›› 2022, Vol. 43 ›› Issue (2) : 345-354. DOI: 10.3969/j.issn.1000-1093.2022.02.012
论文

改进的YOLOv3算法及其在军事目标检测中的应用

  • 于博文， 吕明
作者信息 +

Improved YOLOv3 Algorithm and Its Application in Military Target Detection

  • YU Bowen， L Ming
Author information +
文章历史 +

摘要

复杂环境下军事目标检测技术是提高战场态势生成、分析能力的基础和关键。针对军事目标检测任务在复杂环境下传统检测算法的检测性能较低问题，提出一种基于改进YOLOv3的军事目标检测算法，通过深度学习实现复杂环境下军事目标的自动检测。构建军事目标图像数据集，为各类目标检测算法提供测试环境；在网络结构上通过引入可形变卷积改进的ResNet50-D残差网络作为特征提取网络，提高网络对形变目标的检测精度和速度；在特征融合阶段引入双注意力机制和特征重构模块，增强目标特征的表征能力，抑制干扰，提升检测精度；利用DIOU损失函数和Focal损失函数重新设计目标检测器的损失函数，进一步提高其对军事目标的检测精度；在军事目标图像数据集中进行测试实验。实验结果表明，改进的YOLOv3算法相比于原YOLOv3算法，平均精度均值提高了2.98%，检测速度提高了8.6帧/s，具有较好的检测性能，可为战场态势生成、分析提供有效的辅助技术支持。

Abstract

Military target detection in a complex environment is the basis and key to improving battlefield situation generation and analysis capability. For the military target detection tasks, the detection performance of traditional detection algorithms in complex environment is low. A military target detection algorithm based on improved YOLOv3 algorithm is proposed to automatically detect the military targets in complex environment through deep learning. A military target image dataset is constructed to provide a testing environment for various target detection algorithms.The detection accuracy and speed of deformable target are improved by introducing the deformable convolutional improved ResNet50-D residual network as feature extraction network. In the stage of feature fusion, a dual-attention mechanism and feature reconstruction module are introduced to enhance the characterization ability of target features, suppress the interference, and improve the detection accuracy. The loss function of target detector is redesigned by using DIOU Loss functions and Focal Loss to funther improve the detection accuracy of military targets. The experimental results show that the improved YOLOv3 algorithm improves the average detection accuracy by 2.98% and the detection speed by 8.6 frames/s compared with the original YOLOv3 algorithm. The improved YOLOv3 algorithm has better detection performance and can provide effective auxiliary technical support for battlefield situation generation and analysis.

关键词

目标检测 / 可形变卷积 / YOLOv3算法 / 特征融合 / 注意力机制

Key words

targetdetection / deformableconvolution / YOLOv3algorithm / featurefusion / attentionmechanism

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
于博文， 吕明. 改进的YOLOv3算法及其在军事目标检测中的应用. 兵工学报. 2022, 43(2): 345-354 https://doi.org/10.3969/j.issn.1000-1093.2022.02.012
YU Bowen， L Ming. Improved YOLOv3 Algorithm and Its Application in Military Target Detection. Acta Armamentarii. 2022, 43(2): 345-354 https://doi.org/10.3969/j.issn.1000-1093.2022.02.012

基金

江苏省自然科学基金项目（BK20180467）

参考文献


［1］MILLERA. Situational awareness-from the battlefield to the corporation［J］. Computer Fraud & Security, 2006, 2006(9): 13-16.
［2］PENG H, ZHANG Y F, YANG S, et al. Battlefield image situational awareness application based on deep learning［J］. IEEE Intelligent Systems, 2020, 35(1): 36-43.
［3］HANRATTY T P, HAMMELL I R J, BODT B A, et al. Enhancing battlefield situational awareness through fuzzy based value of information［C］∥Proceedings of the 46th Hawaii International Conference on System Sciences. Wailea, HI, US: IEEE, 2013: 1402-1411.
［4］LIU S, LIU Z. Multi-channel CNN-based object detection for enhanced situation awareness ［C］∥Proceedings of the 9th NATO Military Sensing Symposium (2017-11-30)［2021-02-18］.https:∥arxiv.org/abs/1712.00075.
［5］戴文君, 常天庆, 褚凯轩, 等. 基于时空卷积特征记忆模型的坦克火控系统视频目标检测方法［J］. 兵工学报, 2020, 41(9): 1708-1718.
DAI W J, CHANG T Q, CHU K X, et al. Video object detection method for tank fire control system based on spatial-temporal convolution feature memory model ［J］. Acta Armamentarii,2020, 41(9): 1708-1718.(in Chinese)
［6］包壮壮,赵学军,王明芳,等.脱离预训练的多尺度目标检测网络模型［J］.计算机工程,2020,46(6):248-255.
BAO Z Z, ZHAO X J, WANG M F, et al. Multi-Scale target detection network model trained from scratch［J］. Computer Engineering,2020,46(6):248-255. (in Chinese)
［7］LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector［C］∥Proceedings of the European Conference on Computer Vision. Amsterdam, the Netherlands: Springer, 2016: 21-37.
［8］戴文君,常天庆,张雷,等.面向坦克火控系统的多尺度形变目标检测方法［J］.计算机辅助设计与图形学学报,2019,31(12): 2082-2090.
DAI W J, CHANG T Q, ZHANG L, et al. Multi-scale deformable target detection method for tank fire control system［J］. Journal of Computer-Aided Design & Computer Graphics,2019,31(12):2082-2090. (in Chinese)
［9］HE K M, ZHANG X, REN S, et al. Deep residual learning for image recognition［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, US: IEEE,2016:770-778.
［10］DAIJ F, LI Y, HE K M, et al. R-FCN: object detection via region-based fully convolutional networks［C］∥Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona, Spain: Curran Associates, 2016: 379-387.
［11］杜泽星,殷进勇,杨建.基于密集连接网络的遥感图像检测方法［J］.激光与光电子学进展,2019,56(22):210-216.
DU Z X, YIN J Y, YANG J. Remote sensing image detection based on dense connected networks［J］. Laster & Optoelectronics Progress,2019,56(22):210-216. (in Chinese)
［12］杨传栋,刘桢,石胜斌.基于CNN的弹载图像目标检测方法研究［J］.战术导弹技术,2019(4):85-92.
YANG C D, LIU Z, SHI S B. Research on object detection for missile-borne image based on CNN［J］. Tactical Missile Technology,2019(4):85-92. (in Chinese)
［13］王志,陈平,潘晋孝.基于深度学习的复杂背景下目标检测［J］.重庆理工大学学报(自然科学),2018,32(4):171-176.
WANG Z, CHEN P, PAN J X. Object detection based on deep learning in complex background［J］. Journal of Chongqing University of Technology (Natural Science), 2018, 32(4):171-176. (in Chinese)
［14］GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, US: IEEE,2014:580-587.
［15］GIRSHICK R. Fast R-CNN［C］∥Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile: IEEE,2015:1440-1448.
［16］REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards teal-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
［17］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.
［18］REDMON J, FARHADI A. YOLO9000: better, faster, stronger［C］∥Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, US: IEEE,2017.
［19］REDMON J, FARHADI A. YOLOv3: an incremental improvement［EB/OL］.(2018-04-08)［2021-02-18］.https:∥arxiv.org/abs/1804.02767.
［20］DAI J F, QI H Z, XIONG Y W, et al. Deformable convolutional networks［C］∥Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017:764-773.
［21］HE T, ZHANG Z, ZHANG H, et al. Bag of tricks for image classification with convolutional neural networks［C］∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, US: IEEE, 2019: 558-567.
［22］ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression ［C］∥Proceedings of the 34th AAAI Conference on Artificial Intelligence. New York, NY, US: AAAI, 2020: 12993-13000.
［23］LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327.
［24］EVERINGHAM M, GOOL L V, WILLIAMS C K I, et al. The pascal visual object classes (VOC) challenge［J］.International Journal of Computer Vision，2010，88:303-338.
［25］HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.
［26］鞠默然,罗江宁,王仲博,等. 融合注意力机制的多尺度目标检测算法［J］. 光学学报, 2020, 40(13): 126-134.
JU M R, LUO J N, WANG Z B, et al. Multi-scale target detection algorithm based on attention mechanism［J］. Acta Optica Sinica, 2020, 40(13): 126-134.(in Chinese)
［27］LIN T Y, DOLLR P, GIRSHICK R, et al. Feature pyramid networks for object detection［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, US: IEEE,2017: 2117-2125.


375

Accesses

0

Citation

Detail
段落导航
相关文章

/

〈 〉