复杂战场对抗环境下空中目标抗干扰识别算法

doi:10.12382/bgxb.2021.0576

摘要/Abstract

摘要： 针对复杂背景和红外诱饵对抗环境下红外成像攻坚破甲导弹空中目标识别的难题，提出融合强判别性特征的抗干扰识别算法，将区域生成、特征学习和分类识别融合至抗干扰算法中，形成从像素至区域，再到特征识别的逐级抽象的识别框架。首先通过模拟典型战场环境，生成大量不同对抗态势下的目标特性库，作为算法研究的基础；然后由像素相似性聚类形成候选区域，完成区域“粗粒度”定位；再将提取的各区域特征输入至特征选择模块，学习强判别性的特征；最后将选取的特征输入至改进的多分类支持向量机进行目标的分类识别，实现目标区的“细粒度”锁定。通过逐步细化的识别机制，识别复杂战场对抗环境下的空中目标。验证试验表明，算法在不同对抗态势下的弹道图像数据集中的平均识别正确率达到78.63%，可有效完成目标与干扰之间的区分，为工程应用中的算法研制提供支撑。

关键词: 攻坚破甲导弹, 红外目标, 抗干扰识别, 特征学习

Abstract: In the confrontatoin environment with complex background and infrared decoy flares, aerial target recognition by infrared imaging of fortification storming/HEAT missiles remains a challenge. For the problem of aerial target recognition, an anti-interference recognition algorithm with strong discriminative features is proposed, which integrates region generation, feature learning, classification and identification into the anti-interference algorithm to form an abstract recognition framework from the pixel level to region level and then to feature recognition step by step. Firstly, by simulating the typical battlefield environment, a large number of target feature libraries under different confrontation situations are generated, which serve as the basis of the algorithm research. Secondly, region proposals are formed by pixel similarity clustering, and “coarse granularity” location of regions is completed. Then the extracted region features are input into the feature selection module to learn the strong discriminative features. Finally, the selected features are input into the improved multi-classification support vector machines (SVM) for target classification and recognition, and the “finer granularity” locking of the target region is realized. Through the recognition mechanism of gradual refinement, aerial targets in the complex battlefield confrontation environment are recognized. The validation experiments show that the algorithm has an average recognition accuracy rate of 78.63% in the ballistic image datasets under different confrontation situations, which can effectively distinguish between targets and interference, and provide support for the development of algorithms in engineering applications.

Key words: fortificationstorming/HEAT(High-ExplosiveAnti-Tank)missile, infraredtarget, anti-interferenceidentification, featurelearning

中图分类号:

TP391.4

赵军民，魏嘉艺，吴思捷，李新国，吕梅柏. 复杂战场对抗环境下空中目标抗干扰识别算法[J]. 兵工学报, 2022, 43(10): 2576-2587.

ZHAO Junmin， WEI Jiayi， WU Sijie， LI Xinguo， L Meibo. Anti-Interference Recognition Algorithm for Aerial Targets in the Complex Confrontation Environment on the Battlefield[J]. Acta Armamentarii, 2022, 43(10): 2576-2587.

参考文献

［1］周卫文，康美玲，周泽强.红外诱饵对成像制导导弹影响规律研究［J］.红外与激光工程，2019，48(12):118-124.
ZHOU W W，KANG M L，ZHOU Z Q.Research of infrared flares influence mechanism on the imaging guidance missile［J］.Infrared and Laser Engineering，2019，48(12):118-124.(in Chinese)
［2］马贤杰，李国平，王洪静，等.国外红外导引头及红外诱饵发展历程与展望［J］.航天电子对抗，2020，36(3):58-64.
MA X J，LI G P，WANG H J，et al.Development roadmap and direction of infrared seekers and infrared decoys［J］.Aerospace Electronic Countermeasure，2020，36(3):58-64. (in Chinese)
［3］杨栋，高德亮，曹耀心，等.红外导引头抗诱饵干扰研究［J］.飞控与探测，2020，3(3):79-85.
YANG D，GAO D L，CAO Y X，et al.Study on anti-jamming technology of IR seeker［J］.Flight Control and Detection，2020，3(3): 79-85. (in Chinese)
［4］赵军民，李鹏，邹汝平.智能攻坚破甲导弹技术发展分析［J］.弹箭与制导学报，2021，41(3):1-5.
ZHAO J M，LI P，ZOU R P.Technical development analysis on intelligent fortification storming /HEAT missiles［J］.Journal of Projectiles，Rockets，Missiles and Guidance，2021，41(3):1-5. (in Chinese)
［5］李召，徐文旭，吴晓鸥.美俄反坦克导弹发展现状及技术需求［J］.飞航导弹，2020(8):35-40，56.
LI Z，XU W X，WU X O.Development status and technical requirements of American and Russian anti tank missiles［J］.Aerodynamic Missile，2020(8):35-40，56. (in Chinese)
［6］ BERG A C，BERG T L，ALIK J.Shape matching and object recognition using low distortion correspondences［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，San Diego，CA，US：IEEE，2005，1:26-33.
［7］张冬青，张纯学，文苏丽.自动目标识别技术在导弹上的应用研究［J］.战术导弹技术，2010(5):1-6.
ZHANG D Q，ZHANG C X，WEN S L.Research on the application of automatic target recognition on missile［J］.Tactical Missile Technology，2010(5):1-6. (in Chinese)
［8］赵丹辉，王俊敏，张宏宇，等.精确制导武器导航与末制导技术发展综述［J］.飞航导弹，2021(2):64-70.
ZHAO D H，WANG J M，ZHANG H Y，et al.Overview of the development of precision guided weapon navigation and terminal guidance technology［J］.Aerodynamic Missile，2021(2):64-70. (in Chinese)
［9］张秀蓉.复合导引头目标跟踪技术及实现［D］.西安：西安电子科技大学，2020.
ZHANG X R.Target tracking technology and implementation of compound seeker［D］.Xi'an:Xidian University，2020. (in Chinese)
［10］张坤，胡斌星，许新鹏，等.基于对数极坐标变换的快速相关匹配算法［J］.飞行力学，2020，38(2):61-65.
ZHANG K，HU B X，XU X P，et al.A fast correlation matching algorithm based on log-polar transform［J］. Flight Dynamics，2020，38(2):61-65. (in Chinese)
［11］冉洪成.基于对数极坐标的图像匹配综述［J］.现代计算机，2020(4):65-69.
RAN H C.Review of image matching based on logarithmic polar coordinates［J］.Modern Computer，2020(4):65-69. (in Chinese)
［12］贾迪，朱宁丹，杨宁华，等.图像匹配方法研究综述［J］.中国图象图形学报，2019，24(5):677-699.
JIA D，ZHU N D，YANG N H，et al.Image matching methods［J］.Journal of Image and Graphics，2019，24(5):677-699. (in Chinese)
［13］谢春思，刘志赢，桑雨.基于特征匹配的舰载对陆导弹目标识别模型［J］.系统工程与电子技术，2021，43(8):2244-2253.
XIE C S，LIU Z Y，SANG Y.Target recognition model of ship-to-land missile based on feature matching［J］.Systems Engineering and Electronics，2021，43(8):2244-2253. (in Chinese)
［14］ REN S，HE K，GIRSHICK R，et al.Faster R-CNN: towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，39(6):1137-1149.
［15］ MOHD M R S，HERMAN S H，SHARIF Z.Application of K-Means clustering in hot spot detection for thermal infrared images［C］∥Proceedings of the IEEE Symposium on Computer Applications & Industrial Electronics.Langkawi，Malaysia:IEEE，2017:107-110.
［16］ GUPTA S. MUKHERJEE A.Infrared image segmentation using enhanced fuzzy C-means clustering for automatic detection systems［C］∥Proceedings of the IEEE International Conference on Fuzzy Systems.Taipei,China:IEEE，2011: 944-949.
［17］ LEI T，JIA X H，ZHANG Y N，et al. Significantly fast and robust fuzzy c-means clustering algorithm based on morphological reconstruction and membership filtering［J］.IEEE Transactions on Fuzzy Systems，2018，26(5):3027-3041.
［18］ WANG L P，ZHAN R H，HUANG Y，et al. Joint tracking and classification of extended targets with complex shapes ［J］.Frontiers of Information Technology & Electronic Engineering，2021，22(6):839-862.
［19］ DALAL N，TRIGGS B.Histograms of oriented gradients for human detection［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.San Diego，CA，US: IEEE，2005，1: 886-893.
［20］ 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.
［21］ PEKER M，ALTUN H，KARAKAYA F.Hardware emulation of HOG and AMDF based scale and rotation invariant robust shape detection［C］//Proceedings of the IEEE International Conference on Engineering and Technology.Cairo，Egypt: IEEE，2012，1:1-5.
［22］ ROFFO G，MELZI S，CASTELLANI U，et al.Infinite latent feature selection:a probabilistic latent graph-based ranking approach［C］//Proceedings of the IEEE International Conference on Computer Vision.Venice，Italy:IEEE，2017，1:1398-1406.
［23］ ROFFO G，MELZI S，CASTELLANI U，et al.Infinite feature selection: a graph-based feature filtering approach［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，1(1):1-15.
［24］ GU Q Q,LI Z H,HAN J W.Generalized fisher score for feature selection［C］//Proceedings of CoRR.abs/1202.3725.US:UaiPress,2012.
［25］王周春.基于机器学习的目标探测与识别技术研究［D］.上海:中国科学院大学(中国科学院上海技术物理研究所),2020.
WANG Z C.Research on target detection and recognition technology based on machine learning［D］.Shanghai:University of Chinese Academy of Sciences(Shanghai Institute of Technical Physics of the Chinese Academy of Sciences)，2020. (in Chinese)
［26］戴小路,汪廷华,胡振威.模糊多核支持向量机研究进展［J］.计算机应用研究，2021，38（10）：2896-2903.
DAI X L,WANG T H,HU Z W.Research progress of fuzzy multiple kernel support vector machine［J］.Application Research of Computers,2021,38(10):2896-2903.(in Chinese)
［27］周玉,任钦差,牛会宾.训练样本数据选择方法研究综述［J］.计算机科学,2020,47(增刊2):402-408.
ZHOU Y,REN Q C,NIU H B.Research on training data sample selection methods［J］.Computer Science,2020,47(S2):402-408. (in Chinese)
［28］吴青，付彦琳.支持向量机特征选择方法综述［J］.西安邮电大学学报，2020，25(5):16-21.
WU Q，FU Y L.Review on support vector machines based on feature selection［J］.Journal of Xi'an University of Posts and Telecommunications，2020，25(5):16-21. (in Chinese)
［29］王霞，董永权，于巧，等.结构化支持向量机研究综述［J］.计算机工程与应用，2020，56(17):24-32.
WANG X，DONG Y Q，YU Q，et al.Review of structural support vector machines［J］.Computer Engineering and Applications，2020，56(17):24-32. (in Chinese)
［30］ ZENG H，CHEUNG Y M.Feature selection and kernel learning for local learning-based clustering［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2011,33(8):1532-1547.
［31］李良福，陈卫东，高强，等.基于深度学习的光电系统智能目标识别［J］.兵工学报，2022，43（增刊1）：162-168.
LI L F， CHEN W D， GAO Q， et al. Deep learning-based intelligent target recognition technology for electro-optical system［J］. Acta Armamentarii, 2022,43(S1): 162-168. (in Chinese)

[1]	乔杨, 徐熙平, 辜义文, 潘越, 张潇予. 消热差的红外目标模拟器投影光学系统设计[J]. 兵工学报, 2013, 34(4): 431-436.
[2]	李科杰、易军凯. 红外目标识别中的分形理论[J]. 兵工学报, 1999, 20(1): 36-38.