[1]娄 康,朱志宇,葛慧林.基于目标运动特征的红外目标检测与跟踪方法[J].南京理工大学学报(自然科学版),2019,43(04):455-461.[doi:10.14177/j.cnki.32-1397n.2019.43.04.011]
　Lou Kang,Zhu Zhiyu,Ge Huilin.Infrared target detection and tracking method based ontarget motion feature[J].Journal of Nanjing University of Science and Technology,2019,43(04):455-461.[doi:10.14177/j.cnki.32-1397n.2019.43.04.011]
点击复制

基于目标运动特征的红外目标检测与跟踪方法()
分享到：

《南京理工大学学报》（自然科学版）[ISSN:1005-9830/CN:32-1397/N]

卷:
43卷
期数:
2019年04期
页码:
455-461
栏目:
出版日期:
2019-08-24

文章信息/Info

Title:
Infrared target detection and tracking method based ontarget motion feature
文章编号:
1005-9830(2019)04-0455-07
作者:
娄 康; 朱志宇; 葛慧林
江苏科技大学 电子信息学院,江苏 镇江 212003
Author(s):
Lou Kang; Zhu Zhiyu; Ge Huilin
School of Electronic Information,Jiangsu University of Science and Technology,Zhenjiang 212003,China
关键词:
运动特征;  卡尔曼滤波;  匈牙利算法;  目标跟踪;  红外目标
Keywords:
motion feature;  Kalman filter;  Hungarian algorithm;  target tracking;  infrared target
分类号:
TP391.4
DOI:
10.14177/j.cnki.32-1397n.2019.43.04.011
摘要:
为了提高红外目标检测与跟踪的速度和准确率,该文提出了一种基于红外弱小目标运动特征信息的检测与跟踪方法。方法主要分为目标运动特征检测和目标轨迹预测跟踪两个方面。目标检测方面,通过背景帧差分法将图像分割为前后景,形态学运算后在每一帧的前景中对红外弱小目标进行检测,并记录下候选目标。目标跟踪方面,通过卡尔曼滤波对红外目标轨迹进行预测,计算目标轨迹质心位置与目标实际位置欧式距离,通过匈牙利算法以欧式距离为权重对目标实际轨迹与预测轨迹进行分配,如果分配的结果超过一定阈值将会被重新分配。最终通过MATLAB,在公开的数据集上,仿真验证了该文算法在基本满足实时检测的要求下,仍然可以有效地提高红外弱小目标的检测与跟踪效果。
Abstract:
In order to improve the speed and accuracy of infrared target detection and tracking,this paper proposes a detection and tracking method based on infrared small target motion feature information. The method is mainly divided into two aspects:target motion feature detection and target trajectory prediction. In terms of target detection,the image is segmented into front and back scenes by the background frame difference method. The image is segmented into front and back scenes by the background frame difference method. After the morphological operation,the infrared weak targets are detected in the foreground of each frame,and the candidate targets are recorded. In terms of target tracking,the infrared target trajectory is predicted by Kalman filter,and the Euclidean distance between the target trajectory centroid position and the target actual position is calculated. The Hungarian algorithm uses the Euclidean distance as the weight to assign the actual trajectory and the predicted trajectory. If the result exceeds a certain threshold,it will be reassigned. Finally,through MATLAB,on the open dataset,the simulation verifies that the proposed algorithm can effectively improve the performance of detecting and tracking infrared weak targets while satisfying the requirements of real-time detection.

参考文献/References:

[1] Chen Luoyang,Liu Zheng. A robust and scalable method for infrared target identification[J]. Procedia Computer Science,2019,147:172-176.
[2]Cui Zheng,Yang Jingli,Jiang Shouda,et al. Robust spatio-temporal context for infrared target tracking[J]. Infrared Physics & Technology,2018,91:263-277.
[3]李成美,白宏阳,郭宏伟,等. 一种改进光流法的运动目标检测及跟踪算法[J]. 仪器仪表学报,2018,39(5):249-256.
Li Chengmei,Bai Hongyang,Guo Hongwei,et al. Moving object detection and tracking based on improved optical flow method[J]. Chinese Journal of Scientific Instrument,2018,39(5):249-256.
[4]Wei Yantao,You Xinge,Li Hong. Multiscale patch-based contrast measure for small infrared target detection[J]. Pattern Recognition,2016,58:216-226.
[5]Yang Chunwei,Yao Junping,Sun Dawei,et al. Kernel sparse coding method for automatic target recognition in infrared imagery using covariance descriptor[J]. Infrared Physics & Technology,2016,76:740-747.
[6]Zhang Baohua,Jiao Doudou,Pei Haiquan,et al. Infrared moving object detection based on local saliency and sparse representation[J]. Infrared Physics & Technology,2017,86:187-193.
[7]张燕,贾振宇,周顾人,等. 基于多方向混合模板的红外弱小目标检测算法[J]. 空天防御,2019,2(1):64-69.
Zhang Yan,Jia Zhenyu,Zhou Guren,et al. Infrared dim target detection based on multi-directional mixed template[J]. Air & Space Defense,2019,2(1):64-69.
[8]Liu Qiao,Lu Xiaohuan,He Zhenyu,et al. Deep convolutional neural networks for thermal infrared object tracking[J]. Knowledge-Based Systems,2017,134:189-198.
[9]Liu Lei,Huang Zhijian. Improved motion information-based infrared dim target tracking algorithms[J]. Infrared Physics & Technology,2014,67:341-349.
[10]Deng Lizhen,Zhang Jieke,Zhu Hu. Infrared moving point target detection using a spatial-temporal filter[J]. Infrared Physics & Technology,2018,95:122-127.
[11]许敬,王晓锋. 基于贝叶斯概率的运动目标识别方法[J]. 南京理工大学学报,2013,37(1):76-80.
Xu Jing,Wang Xiaofeng. Recognition method of moving target using Bayesian probability theory[J]. Journal of Nanjing University of Science and Technology,2013,37(1):76-80.
[12]杨阳,杨静宇. 基于显著性分割的红外行人检测[J]. 南京理工大学学报,2013,37(2):251-256.
Yang Yang,Yang Jingyu. Pedestrian detection of infrared images based on saliency segmentation[J]. Journal of Nanjing University of Science and Technology,2013,37(2):251-256.
[13]Qian Kun,Zhou Huixin,Qin Hanlin,et al. Guided filter and convolutional network based tracking for infrared dim moving target[J]. Infrared Physics & Technology,2017,85:431-442.
[14]Deng Lizhen,Zhu Hu,Tao Chao,et al. Infrared moving point target detection based on spatial-temporal local contrast filter[J]. Infrared Physics & Technology,2016,76:168-173.
[15]Wang Xin,Shen Siqiu,Ning Chen,et al. A sparse representation-based method for infrared dim target detection under sea-sky background[J]. Infrared Physics & Technology,2015,71:347-355.

相似文献/References:

[1]索晓峰,刘锐,王长城,等.一种雷达网络偏差估计补偿方法[J].南京理工大学学报(自然科学版),2012,36(02):256.
　SUO Xiao-feng,LIU Rui,WANG Chang-cheng,et al.Bias Estimation and Compensation Algorithm for Radar Network[J].Journal of Nanjing University of Science and Technology,2012,36(04):256.
[2]孙罡,王昌明,张爱军.GPS静态单点定位的滤波算法比较[J].南京理工大学学报(自然科学版),2011,(01):80.
　SUN Gang,WANG Chang-ming,ZHANG Ai-jun.Comparison of Filtering Algorithms for GPS Static Point Positioning[J].Journal of Nanjing University of Science and Technology,2011,(04):80.
[3]丁传炳,王良明,常思江,等.卡尔曼滤波在GPS制导火箭弹中的应用[J].南京理工大学学报(自然科学版),2010,(02):157.
　DING Chuan-bing,WANG Liang-ming,CHANG Si-jiang,et al.Application of Kalman Filtering in GPS-guided Rocket Projectiles[J].Journal of Nanjing University of Science and Technology,2010,(04):157.
[4]刘剑锋,等.一种卫星通信多普勒频偏快速捕获和跟踪算法[J].南京理工大学学报(自然科学版),2009,(03):357.
　LIU Jian-feng,DONG Jin-chun,SHEN Lian-feng,et al.Rapid Doppler Frequency Offset Acquisition and Tracking Algorithm of Satellite Communication[J].Journal of Nanjing University of Science and Technology,2009,(04):357.
[5]白宏阳,陈 帅,薛晓中,等.飞机SINS/多普勒/气压高度表组合导航性能分析[J].南京理工大学学报(自然科学版),2009,(05):581.
　BAI Hong-yang,CHEN Shuai,XUE Xiao-zhong,et al.Analysis of SINS/Doppler/Baro-altimeter Integrated Navigation Performance in Airplanes[J].Journal of Nanjing University of Science and Technology,2009,(04):581.
[6]丁明理,王祁,洪亮.GPS与无陀螺微惯性测量单元组合导航系统设计[J].南京理工大学学报(自然科学版),2005,(01):98.
　DING Ming-li,WANG Qi,HONG Liang.Design of Integrated Navigation System of GPS and Non-gyro Micro Inertial Measurement Unit[J].Journal of Nanjing University of Science and Technology,2005,(04):98.
[7]盛安冬,黄飞,刘健,等.一种基于多角度的运动目标参数估计新方法[J].南京理工大学学报(自然科学版),2002,(04):353.
　ShengAndong HuangFei LiuJian GuoZhi.A New Parameter Estimation Method for Flying Object Based on Multi-angle[J].Journal of Nanjing University of Science and Technology,2002,(04):353.
[8]杨春玲,孙泓波,倪晋麟,等.多传感器远距离目标跟踪精度分析[J].南京理工大学学报(自然科学版),1999,(03):53.
　YangChunling SunHongbo NiJinlin LiuGuosui.Research of Multisensor for long Range Target Tracking Accuracy[J].Journal of Nanjing University of Science and Technology,1999,(04):53.
[9]张元,陈庆生,吴喜录.被动声探测引信系统的后置处理[J].南京理工大学学报(自然科学版),1996,(01):30.
　Zhang Yuan,Chen Qingsheng,Wu Xilu.The Post Processing of Passive Sound Detecting Fuse Systems[J].Journal of Nanjing University of Science and Technology,1996,(04):30.
[10]王建新,张先萌,沈世泉,等.提高飞行弹丸跟踪滤波器滤波精度的一种方法[J].南京理工大学学报(自然科学版),1993,(06):40.

备注/Memo

备注/Memo:
收稿日期:2019-04-26 修回日期:2019-05-30
基金项目:国家自然科学基金(61671222)
作者简介:娄康(1995-),男,硕士,主要研究方向:红外目标检测和跟踪,E-mail:172030045@stu.just.edu.cn; 通讯作者:朱志宇(1971-),男,博士,教授,主要研究方向:红外目标检测和跟踪、电力系统自动化等,E-mail:zzydzz@163.com。
引文格式:娄康,朱志宇,葛慧林. 基于目标运动特征的红外目标检测与跟踪方法[J]. 南京理工大学学报,2019,43(4):455-461.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2019-09-30