基于多域网络的红外目标跟踪算法

doi:10.12305/j.issn.1001-506X.2021.05.03

系统工程与电子技术 ›› 2021, Vol. 43 ›› Issue (5): 1176-1183.doi: 10.12305/j.issn.1001-506X.2021.05.03

基于多域网络的红外目标跟踪算法

孙明杰^1,*(), 周林¹(), 顾金玲²(), 李培庚³()

1. 空军工程大学防空反导学院, 陕西西安 710051
2. 中国人民解放军32272部队, 甘肃兰州 730010
3. 中国人民解放军95169部队, 广西南宁 530031

收稿日期:2020-08-06 出版日期:2021-05-01 发布日期:2021-04-27
通讯作者: 孙明杰 E-mail:sunmj1982@163.com;houlin_36@163.com;3449888544qq.com;738284769@qq.com
作者简介:孙明杰(1982—), 男, 博士研究生, 主要研究方向为红外目标跟踪、人工智能和装备基础理论。E-mail: sunmj1982@163.com|周林(1965—), 男, 教授, 博士研究生导师，博士, 主要研究方向为装备基础理论研究、装备保障需求论证。E-mail: houlin_36@163.com|顾金玲(1989—), 女, 硕士研究生, 主要研究方向为装备基础理论研究。E-mail: 3449888544qq.com|李培庚(1993—), 男, 硕士研究生, 主要研究方向为装备指挥管理研究。E-mail: 738284769@qq.com
基金资助:
陕西省自然科学基础研究计划(2019JQ-708)

Infrared target tracking algorithm based on multi-domain network

Mingjie SUN^1,*(), Lin ZHOU¹(), Jinling GU²(), Peigeng LI³()

1. Air and Missile Defense College, Air Force Engineering University, Xi'an 710051, China
2. Unit 32272 of the PLA, Lanzhou 730010, China
3. Unit 95169 of the PLA, Nanning 530031, China

Received:2020-08-06 Online:2021-05-01 Published:2021-04-27
Contact: Mingjie SUN E-mail:sunmj1982@163.com;houlin_36@163.com;3449888544qq.com;738284769@qq.com

摘要/Abstract

摘要：

随着红外探测器性能的不断提升, 红外目标跟踪在智能安防等领域的应用越来越广泛。然而红外图像分辨率较低, 依赖其进行目标跟踪仍然是一个制约相关应用发展的难题。针对红外图像分辨率低的特点, 以多域网络为模型算法框架, 结合目标运动过程中的尺寸变化特点, 提出了一种基于多域网络的红外目标跟踪算法。为了评估算法性能, 分别在VOT-TIR2016数据库和AMCOM红外数据上进行了实验。实验结果表明, 目标尺度预测机制能够显著提高算法的跟踪精度。

关键词: 多域网络, 目标跟踪, 红外成像, 深度学习

Abstract:

With the continuous improvement of infrared detector performance, infrared target tracking is more and more widely used in intelligent security and other fields. However, it is still a difficult problem to rely on infrared image for target tracking due to the low resolution of infrared image. In view of the low resolution of infrared image, combining with the characteristics of size change in the process of target movement, a multi-domain network based infrared target tracking algorithm is proposed, which is based on the multi-domain network. To assess the algorithm performance, experiments are conducted on the VOT-TIR2016 database and AMCOM infrared data, respectively. Experimental results show that the target scale prediction mechanism can significantly improve the tracking accuracy of the algorithm.

Key words: multi-domain network, target tracking, infrared imaging, deep learning

中图分类号:

TP391

孙明杰, 周林, 顾金玲, 李培庚. 基于多域网络的红外目标跟踪算法[J]. 系统工程与电子技术, 2021, 43(5): 1176-1183.

Mingjie SUN, Lin ZHOU, Jinling GU, Peigeng LI. Infrared target tracking algorithm based on multi-domain network[J]. Systems Engineering and Electronics, 2021, 43(5): 1176-1183.

图/表 9

图1

图2

图3

图4

图5

图6

表1

图7

图8

参考文献 30

1	卢湖川, 李佩霞, 王栋. 目标跟踪算法综述[J]. 模式识别与人工智能, 2018, 31 (1): 61- 76.
	LU H C , LI P X , WANG D . Visual object tracking: a survey[J]. Pattern Recognition and Artificial Intelligence, 2018, 31 (1): 61- 76.
2	胡阳光, 肖明清, 张凯, 等. 传统特征和深度特征融合的红外空中目标跟踪[J]. 系统工程与电子技术, 2019, 41 (12): 2675- 2683.
	HU Y G , XIAO M Q , ZHANG K , et al. Infrared aerial target tracking based on fusion of traditional feature and deep feature[J]. Systems Engineering and Electronics, 2019, 41 (12): 2675- 2683.
3	LI B, WU W, WANG Q, et al. SiamRPN++: evolution of Siamese visual tracking with very deep networks[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, 4277-4286.
4	LEITLOFF J , ROSENBAUM D , KURZ F , et al. An operational system for estimating road traffic information from aerial images[J]. Remote Sensing, 2014, 6, 11315- 11341. doi: 10.3390/rs61111315
5	HU Y G , XIAO M Q , ZHANG K , et al. Aerial infrared target tracking in complex background based on combined tracking and detecting[J]. Mathematical Problems in Engineering, 2019, 18, 1- 17.
6	WANG X T , ZHANG K , LI S Y , et al. An optimal long-term aerial infrared object tracking algorithm with re-detection[J]. IEEE Access, 2019, 7, 114320- 114333. doi: 10.1109/ACCESS.2019.2929749
7	HU Y G , XIAO M Q , LI S Y , et al. Aerial infrared target tracking based on a Siamese network and traditional features[J]. Infrared Physics & Technology, 2020, 111, 103505.
8	HUANG H S , TONG Z X , CHAI S C , et al. Experimental and numerical study of chaff cloud kinetic performance under impact of high-speed airflow[J]. Chinese Journal of Aeronautics, 2018, 31 (11): 2080- 2092. doi: 10.1016/j.cja.2018.08.002
9	卢杨, 张磊, 郭立媛, 等. 基于改进纹理特征的红外目标跟踪算法[J]. 液晶与显示, 2018, 33 (12): 71- 77.
	LU Y , ZHANG L , GUO L Y , et al. Infrared target tracking based on improved LBP feature[J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33 (12): 71- 77.
10	钱琨. 基于机器学习理论的红外目标跟踪技术研究[D]. 西安: 西安电子科技大学, 2019.
	QIAN K. Study on infrared target tracking technology based on machine learning theory[D]. Xi'an: Xidian University, 2019.
11	LAMBERTI F , SANNA A , PARAVATI G . Improving robustness of infrared target tracking algorithms based on template matching[J]. IEEE Trans.on Aerospace & Electronics Systems, 2011, 47 (2): 1467- 1480.
12	MOULD N A, NGUYEN C T, HAVLICEK J P, et al. Infrared target tracking with AM-FM consistency checks[C]// Proc. of the IEEE Southwest Symposium on Image Analysis and Interpretation, 2008.
13	LECUN Y , BENGIO Y , HINTON G . Deep learning[J]. Nature, 2015, 521, 436- 444. doi: 10.1038/nature14539
14	NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 4293-4302.
15	SAMMEN S S , GHORBANI M A , MALIK A , et al. Enhanced artificial neural network with Harris Hawks optimization for predicting scour depth downstream of ski-jump spillway[J]. Applied Sciences-Basel, 2020, 10 (15): 1- 16.
16	WANG Z , WANG B , LIU C , et al. Improved BP neural network algorithm to wind power forecast[J]. The Journal of Engineering, 2017, 13, 940- 943.
17	XIE R, WANG X M, LI Y, et al. Research and application on improved BP neural network algorithm[C]//Proc. of the IEEE Industrial Electronics & Applications, 2010: 1462-1466.
18	HAN X D , KANG Y , SHENG J P , et al. Centrifugal pump impeller and volute shape optimization via combined NUMECA, genetic algorithm, and back propagation neural network[J]. Structural and Multidisciplinary Optimization, 2019, 61, 381- 409. doi: 10.1007/s00158-019-02367-8
19	YE Y F , WANG Z X , ZHANG X B . An optimal pointwise weighted ensemble of surrogates based on minimization of local mean square error[J]. Structural and Multidisciplinary Optimization, 2020, 62 (2): 529- 542. doi: 10.1007/s00158-020-02508-4
20	LIU W , POKHAREL P P , PRINCIPE J C . Correntropy: properties and applications in non-Gaussian signal processing[J]. IEEE Trans.on Signal Processing, 2007, 55 (11): 5286- 5298. doi: 10.1109/TSP.2007.896065
21	LI H C , WANG W Y , PAN L , et al. Robust capsule network based on maximum correntropy criterion for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13, 738- 751. doi: 10.1109/JSTARS.2020.2968930
22	YI S , MA H M , LI X , et al. WSODPB: weakly supervised object detection with PCSNet and box regression module[J]. Neurocomputing, 2020, 418, 232- 240. doi: 10.1016/j.neucom.2020.08.028
23	胡阳光, 肖明清, 刘兆政, 等. 基于序列复杂度的空中红外目标跟踪算法评估[J]. 系统工程与电子技术, 2020, 42 (4): 740- 748.
	HU Y G , XIAO M Q , LIU Z Z , et al. Aerial infrared target tracking algorithm evaluation based on complexity of sequence[J]. Systems Engineering and Electronics, 2020, 42 (4): 740- 748.
24	KRISTAN M, LEONARDIS A, MATAS J, et al. The visual object tracking VOT 2016 challenge results[C]//Proc. of the European Conference on Computer Vision, 2016.
25	SUN L F , YU H F , FU Z M , et al. A fast measurement partitioning algorithm for multiple extended target tracking[J]. Electronics Letters, 2020, 56 (16): 832- 834. doi: 10.1049/el.2020.0984
26	WANG F L , ZHEN W , ZHONG B N , et al. Robust infrared target tracking based on particle filter with embedded saliency detection[J]. Information Sciences: An International Journal, 2015, 301, 215- 226. doi: 10.1016/j.ins.2014.12.022
27	WANG D, LU H, YANG M H. Least soft-threshold squares tracking[C]//Proc. of the IEEE Conference on Computer Vision & Pattern Recognition, 2013: 583-596.
28	KALAL Z , MIKOLAJCZYK K , MATAS J . Tracking-learning-detection[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2012, 34 (7): 1409- 1422. doi: 10.1109/TPAMI.2011.239
29	HENRIQUES J F , CASEIRO R , MARTINS P , et al. High-speed tracking with kernelized correlation filters[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2015, 37 (3): 583- 596. doi: 10.1109/TPAMI.2014.2345390
30	MA C, YANG X K, ZHANG C Y, et al. Long-term correlation tracking[C]//Proc. of the Computer Vision & Pattern Recognition, 2015: 5388-5396.

	参数	跟踪算法
	参数	SPMDnetOurs	MDNet	KCF	LCT	TLD	LSST
lwir_1608	DPR/%	100.0	100.0	68.3	94.5	85.20	84.10
	OSR/%	67.2	57.6	1.7	13.8	0.30	73.80
	FPS	6.2	6.4	273.0	20.1	41.20	7.80
lwir_1913	DPR/%	94.0	59.2	60.0	63.0	91.30	99.60
	OSR/%	61.5	41.1	51.7	22.6	0.40	48.70
	FPS	4.2	4.3	177.0	16.9	26.30	6.50
平均值	DPR/%	97.0	79.6	64.2	78.8	88.30	91.85
	OSR/%	64.4	49.4	26.7	18.2	0.35	61.25
	FPS	5.2	5.4	225.0	18.5	33.80	7.15

[1]	韩啸, 陈世文, 陈蒙, 杨锦程. 基于互易点学习的LPI信号开集识别[J]. 系统工程与电子技术, 2022, 44(9): 2752-2759.
[2]	仇祝令, 查宇飞, 李振宇, 李禹铭, 张鹏, 朱川. 基于多模型蒸馏的时间正则化相关滤波跟踪算法[J]. 系统工程与电子技术, 2022, 44(8): 2448-2456.
[3]	侯子林, 程婷, 彭瀚. 基于量测转换序贯滤波的GMPHD机动目标跟踪[J]. 系统工程与电子技术, 2022, 44(8): 2474-2482.
[4]	张立民, 谭凯文, 闫文君, 张聿远. 基于多级跳线残差网络的雷达辐射源识别[J]. 系统工程与电子技术, 2022, 44(7): 2148-2156.
[5]	史浩然, 卢发兴, 祁江鑫, 杨光. 基于辅助信标的无人机协同目标跟踪[J]. 系统工程与电子技术, 2022, 44(7): 2302-2310.
[6]	金国栋, 薛远亮, 谭力宁, 许剑锟. 基于孪生神经网络的目标跟踪算法进展研究[J]. 系统工程与电子技术, 2022, 44(6): 1805-1822.
[7]	翟光, 王妍欣, 孙一勇. 基于低轨星网的多目标协同跟踪滤波技术[J]. 系统工程与电子技术, 2022, 44(6): 1957-1967.
[8]	赵晓枫, 徐叶斌, 吴飞, 牛家辉, 蔡伟, 张志利. 基于全局感知机制的地面红外目标检测方法[J]. 系统工程与电子技术, 2022, 44(5): 1461-1467.
[9]	王帅, 向建军, 彭芳, 唐书娟. 基于新最速下降法的目标跟踪算法[J]. 系统工程与电子技术, 2022, 44(5): 1512-1519.
[10]	邹虹, 白陈阳, 何鹏, 崔亚平, 王汝言, 吴大鹏. 基于分布式深度学习的边缘服务放置策略[J]. 系统工程与电子技术, 2022, 44(5): 1728-1737.
[11]	辛怀声, 曹晨. 基于交互多模型的分组δ-广义标签多伯努利算法[J]. 系统工程与电子技术, 2022, 44(4): 1128-1138.
[12]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[13]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[14]	谢家豪, 黄树彩, 韦道知, 张曌宇, 王文豪. 基于P_EV准则的不确定混合多传感器联盟求解[J]. 系统工程与电子技术, 2022, 44(3): 819-826.
[15]	宋子壮, 杨嘉伟, 张东方, 王诗强, 张硕. 基于无锚框的红外多类别多目标实时跟踪网络[J]. 系统工程与电子技术, 2022, 44(2): 401-409.

基于多域网络的红外目标跟踪算法

Infrared target tracking algorithm based on multi-domain network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价