基于改进YOLOv3和核相关滤波算法的旋转弹目标探测算法

doi:10.12382/bgxb.2021.0283

摘要/Abstract

摘要： 旋转弹的电视摄像头拍摄画面会产生旋转及抖动模糊，在预先侦查目标数据较少且末制导段视野目标较小的情况下，目标难以精确探测，为此提出一种基于改进YOLOv3和核相关滤波（KCF）算法的目标检测与跟踪算法，通过深度学习实现目标的自动检测。制作模拟山地打击场景的数据集，基于少量数据样本的前提，模拟不同天气、光照、运动及旋转模糊等复杂环境，完成在网络学习中数据的增强和扩充；通过在YOLOv3网络基础上添加Inception多尺度分支结构，增加网络对于目标不同尺寸的适应性，减少网络层数，更能适应对小目标的检测；在实现目标定位方法上，将目标检测与跟踪算法相融合，提出一种目标丢失判别机制，并利用弹道的速度—时间信息更新目标跟踪框尺度。仿真实验结果表明，相比原始算法，改进算法能更有效实现复杂环境下的目标检测和跟踪。

关键词: 旋转弹, 目标检测与跟踪, 改进YOLOv3算法, 核相关滤波算法, 复杂环境, 小目标

Abstract: The image captured by the spinning projectile-borne TV camerawill rotate and jitter to become blurry. It is difficult to detect a target accurately when the target data is less in advance detection and the field of view in the terminal guidance phase is small. A target detection and tracking algorithm based on improved YOLOv3 and kernelized correlation filter (KCF) is proposed.On the premise of a small number of data samples，the complex environments such as different weather，illumination，motion，and rotation blur are simulated to complete the data enhancement and expansion in network learning; By adding the multi-scale branch structure of Induction based on YOLOv3 network，the adaptability of the network to different sizes of targets is increased and the number of network layers is reduced for small target detection. In the realization of target location method， the target detection is combined with tracking algorithm，a target loss discrimination mechanism based on Gaussian threshold is proposed ，and the target frame scale is updated by using the velocity-time information of trajectory. Simulated results show that the improved algorithm can achieve the target detection and tracking in the complex environment more effectively.

Key words: spinningprojectile, targetdetectionandtracking, improvedYOLOv3algorithm, kernelizedcorrelationfilteralgorithm, complexenvironment, smalltarget

中图分类号:

TJ765.4

王少博，张成，苏迪，冀瑞静. 基于改进YOLOv3和核相关滤波算法的旋转弹目标探测算法[J]. 兵工学报, 2022, 43(5): 1032-1045.

WANG Shaobo， ZHANG Cheng， SU Di， JI Ruijing. A Target Detecting Algorithm for Spinning Projectile Based on Improved YOLOv3 and KCF[J]. Acta Armamentarii, 2022, 43(5): 1032-1045.

参考文献

［1］张严.面向复杂环境的末制导目标识别与跟踪方法研究［D］.哈尔滨：哈尔滨工业大学，2012：8-20.
ZHANG Y.Terminal guidance of target recongnition and tracking for the complex environment［D］.Harbin：Harbin Institute of Technology，2012：8-20.(in Chinese)
［2］杨传栋，刘桢，马翰宇，等.一种基于改进Yolov3的弹载图像多目标检测方法［J］.弹箭与制导学报，2020，40(4):149-153.
YANG C D，LIU Z，MA H Y, et al. A multi-target detection method for missle-borne images based on improved YOLOv3［J］.Journal of Projectiles，Rockets，Missiles and Guidance，2020，40(4):149-153.(in Chinese)
［3］刘涛，杨子渊，蒋燕妮，等.极化SAR图像舰船目标检测研究综述［J］.雷达学报，2021，10(1):1-19.
LIU T，YANG Z Y，JIANG Y N，et al. Review of ship detection in polarimetric synthetic aperture imagery［J］. Journal of Radars，2021，10(1):1-19. (in Chinese)
［4］ WANG Q，SHEN F Y，CHENG L F，et al.Ship detection based on fused features and rebuilt YOLOv3 networks in optical remote-sensing images［J］.International Journal of Remote Sensing，2021，42(2):520-536.
［5］谭景信，洪岩，孟德地，等.基于卷积神经网络的作战目标识别方法的研究［J］.计算机仿真，2017，23(11):12-15，113.
TAN J X，HONG Y，MENG D D，et al. Research on target recongnition method based on convolutional neural network［J］.Computer Simulation，2017，23(11):12-15，113.(in Chinese)
［6］ GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation［C］∥Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus，OH，US:IEEE，2014:580-587.
［7］ GIRSHICK R.Fast R-CNN［C］∥Proceedings of IEEE International Conference on Computer Vision.Santiago，Chile:IEEE，2015:1440-1448.
［8］ REN S Q，HE K M，GIRSHICK R，et al.Faster R-CNN: towards realtime object detection with region proposal networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2016，39(6):1137-1149.
［9］ REDMON J，FARHADI A.YOLO9000:better，faster，stronger［C］∥
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu，HI，US:IEEE，2017:6517-6525.
［10］ REDMON J，FARHADI A.YOLOv3:an incremental im-provement: arXiv:1804.02767v1［R/OL］.Ithaca，NY，US:Cornell University.(2018-04-08)［2019-05-15］.https:∥arxiv.org/abs/1804.02767.
［11］ LIU W，ANGUELOV D，ERHAN D，et al.SSD: singleshot multibox detector［C］∥Proceedings of European Conference on Computer Vision.Cambridge，MA，US:MIT Press，2016:21-37.
［12］李响，苏娟，杨龙.基于改进YOLOv3的合成孔径雷达图像中建筑物检测算法［J］.兵工学报，2020，41(7):1347-1359.
LI X，SU J，YANG L.A SAR image building detection algorithm based on improved YOLOv3［J］.Acta Armamentarii，2020，41(7): 1347-1359.(in Chinese)
［13］余秀源.基于深度学习的复杂背景下目标检测与跟踪［D］.北京：中国科学院大学，2020：2-10.
YU X Y.Object detection and tracking in the complex background based on deep learning.［D］.Beijing: University of Chinese Academy of Sciences，2020：2-10.(in Chinese)
［14］ HENRIQUES J F，CASEIRO R，MARTINS P，et al. High-speed tracking with kernelized correlation filters［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2014，37(3):583-596.
［15］ BOLME D S，BEVERIDGE J R，DRAPER B A，et al.Visual object tracking using adaptive correlation filters［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Francisco，CA，US：IEEE，2010: 2544-2550.
［16］ HENRIQUES J F，CASEIRO R，MARRTINS P，et al.Exploiting
the circulant structure of tracking-by-detection with kernels［C］∥
Proceedings of the 12th European Conference on Computer Vision.Florence，Italy：Springer，2012: 702-715.
［17］ DANELLJAN M，HGER G，KHAN F S，et al.Convolutional features for correlation filter based visual tracking［C］∥Proceedings of IEEE International Conference on Computer Vision Workshop. Santiago，Chile：IEEE，2015:621-629.
［18］ BO L，YAN J J，WEI W，et al. High performance visual tracking with Siamese region proposal network［C］∥Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City，UT，US：IEEE，2018.
［19］ LI B，WU W，WANG Q，et al. SiamRPN++: evolution of Siamese visual tracking with very deep networks［C］∥Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach，CA，US:IEEE，2020.
［20］ DANELLJAN M，BHAT G，KHAN F S，et al.ATOM: accurate tracking by overlap maximization［C］∥Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach，CA，US:IEEE，2020.
［21］ KRIZHEVSKY A，SUTSKEVER I，HINTON G E.ImageNet classification with deep convolutional neural net-works［C］∥Proceedings of the 25th International Conference on Neural Information Processing Systems.Red Hook，NY，US:Curran Associates Inc.，2012:1097-1105.
［22］ HE K M，ZHANG X Y，REN S Q，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.
［23］王殿伟，何衍辉，李大湘，等.改进的YOLOv3红外视频图像行人检测算法［J］.西安邮电大学学报，2018，23(4):48-52，67.
WANG D W，HE Y H，LI D X，et al. An improved infrared video image pedestrian detection algorithm［J］.Journal of Xi'an University of Posts and Telecommunications，2018，23(4):48-52，67. (in Chinese)
［24］ ZHANG K P，ZHANG Z P，LI Z F，et al.Joint face detection and alignment using multitask cascaded convolutional networks［J］.IEEE Signal Processing Letters，2016，23(10):1499-1503.
［25］ 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.
［26］ HU H，GU J Y，ZHANG Z，et al.Relation networks for object detection［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City，UT，US:IEEE，2018:3588-3597.
［27］ LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft COCO: common objects in context［C］∥Proceedings of European Conference on Computer Vision.Zurich，Switzerlan:Springer，2014:740-755.
［28］ EVERINGHAM M，ALI ESLAMI S M，VAN GOOL L，et al.The pascal visual object classes challenge:a retrospective［J］.International Journal of Computer Vision，2015，111(1):98-136.
［29］ KISANTAL M，WOJNA Z，MURAWSKI J.Augmentation for small object detection［C］∥Proceedings of the IEEE Computer Vision and Pattern Recognition，Long Beach，CA，US:IEEE，2019: 16-20.
［30］ NEUBECK A，VAN GOOL L.Efficient non-maximum suppression［C］∥Proceedings of International Conference on Pattern Recognition.Hong Kong，China：IEEE，2006:850-855.
［31］ DALAL N，TRIGGS B.Histograms of oriented gradients for human detection［C］∥Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego，CA，US:IEEE，2005: 886-893.
［32］王向军，乐兵，邢峰，等.利用序列图像解算目标视线角速率的方法［J］.红外与激光工程，2017，46(8):240-246.
WANG X J，YUE B，XING F，et al.Method of measuring target LOS angular rate with sequence images［J］.Infrared and Laser Engineering，2017，46(8):240-246.(in Chinese)
［33］ ZHANG Z Y.A flexible new technique for camera calibration［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2000，22(11):1330-1334.

[1]	陈成，赵良玉，谢浩怡，郝晓兵. 单通道控制旋转弹角运动的复分析方法[J]. 兵工学报, 2021, 42(2): 308-319.
[2]	丁天宝，何朝，王良明，林智伟. 高速旋转炮弹宽海拔弹道解算方法[J]. 兵工学报, 2021, 42(1): 209-213.
[3]	彭嘉诚，蒋建伟，廖伟. 高速旋转弹丸炸药装药在膛内运动中底层温度的数值模拟[J]. 兵工学报, 2020, 41(9): 1783-1791.
[4]	钟阳，王良明，吴映锋. 基于计算流体力学与刚体动力学耦合的高速旋转弹丸弹道计算方法[J]. 兵工学报, 2020, 41(6): 1085-1095.
[5]	岳雷. 一种基于双极性脉冲信号的沉底及掩埋小目标探测方法[J]. 兵工学报, 2019, 40(1): 143-152.
[6]	鞠潭，于纪言，王晓鸣，顾晓辉. 基于地磁辅助的弹载两轴陀螺传感器校正方法研究[J]. 兵工学报, 2018, 39(10): 1919-1926.
[7]	曾溢良，蓝金辉，邹金霖. 滑动置信度约束的红外弱小目标跟踪算法研究[J]. 兵工学报, 2017, 38(9): 1771-1778.
[8]	孟鹏，陈红彬，钱林方，李仁凤，乐贵高. 弹带对高速旋转弹丸气动特性影响的数值模拟[J]. 兵工学报, 2017, 38(12): 2363-2372.
[9]	王忠美，杨晓梅, 顾行发. 基于鲁棒主成分分析的红外图像小目标检测[J]. 兵工学报, 2016, 37(9): 1753-1760.
[10]	张龙，赵志勤，范斌宁，张岩. 基于弹载地磁测试的高速旋转稳定弹锥形运动分析[J]. 兵工学报, 2016, 37(12): 2235-2241.
[11]	吴一全，宋昱. 基于复无下采样轮廓波和Gaussian小波支持向量回归的红外目标图像背景抑制[J]. 兵工学报, 2015, 36(4): 687-695.
[12]	雷娟棉, 李田田, 黄灿. 高速旋转弹丸马格努斯效应数值研究[J]. 兵工学报, 2013, 34(6): 718-725.
[13]	吴一全，吴加明，占必超. 一种可有效分割小目标图像的阈值选取方法[J]. 兵工学报, 2011, 32(4): 469-475.
[14]	王恩德，朱枫，肖阳辉，佟新鑫，朱丹. 线性化信号与控制信号的相位差对周期平均力影响的分析[J]. 兵工学报, 2011, 32(1): 23-27.
[15]	李海涛，曹咏弘，祖静. 旋转弹姿态解算方法研究[J]. 兵工学报, 2010, 31(7): 987-990.