[1]李继泉,时勤功,胡春松.一种复杂背景下红外目标稳定跟踪算法[J].红外技术,2020,42(5):434-439.[doi:10.11846/j.issn.1001_8891.202005004]
 LI Jiquan,SHI Qingong,HU Chunsong.Stable Infrared Target Tracking Algorithm Under Complicated Background[J].Infrared Technology,2020,42(5):434-439.[doi:10.11846/j.issn.1001_8891.202005004]
点击复制

一种复杂背景下红外目标稳定跟踪算法
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
42卷
期数:
2020年第5期
页码:
434-439
栏目:
出版日期:
2020-05-23

文章信息/Info

Title:
Stable Infrared Target Tracking Algorithm Under Complicated Background
文章编号:
1001-8891(2020)05-0434-06
作者:
李继泉时勤功胡春松
湖南华南光电(集团)有限责任公司
Author(s):
LI JiquanSHI QingongHU Chunsong
Hunan Huanan Opto-Electro-Sci-Tech Co., LTD
关键词:
红外目标压缩跟踪算法TLD算法HOG特征卡尔曼滤波器
Keywords:
compressive trackingtracking-learning-detectionHOG featuresKalman filter
分类号:
TP391.4
DOI:
10.11846/j.issn.1001_8891.202005004
文献标志码:
A
摘要:
针对红外单目标在长期跟踪过程中的强背景干扰、遮挡、形变以及目标特征信息减弱等实际问题,提出了一种基于跟踪-学习-检测(Tracking-Learning-Detection,TLD)框架的红外目标稳定跟踪方法。该方法在压缩跟踪算法(Compressive Tracking,CT)的基础上替换广义的类Harr特征为HOG特征,引入互补随机测量矩阵,优化纹理和灰度特征信息的权重,同时引入卡尔曼滤波器记录空间上下文位置信息,以解决CT算法和TLD算法在目标被遮挡时的跟踪失效和全局检索问题。基于TLD算法框架和改进CT算法相结合的红外图像跟踪算法有效地解决了遮挡和强干扰问题,提升了算法的跟踪准确性和长期跟踪稳定性。实验结果表明,本文提出的算法在红外地面环境中能较好地实时稳定跟踪并保持良好的准确性和鲁棒性。
Abstract:
During the long-term tracking process of a single infrared target, many technical problems occur, such as strong background interference, occlusion, deformation, and target feature attenuation. An infrared target-tracking algorithm based on tracking-learning-detection (TLD) was proposed to solve these problems. Based on compressive tracking (CT), generalized Harr-like features were replaced by histograms of oriented gradient features. In our proposed method, a complementary random measurement matrix, which extracted texture and optimized grayscale feature-weights, was introduced. Moreover, a Kalman filter, used to record the space context location information, was adopted. Hence, the tracking failure and global retrieval problem of traditional CT and TLD algorithms can be solved when the target is occluded or deformed. The infrared image-tracking algorithm based on the combination of the TLD algorithm framework and improved CT algorithm effectively solves the problem of occlusion and strong interference and improves the tracking accuracy and long-term tracking stability of the algorithm. Experimental results show that the proposed algorithm can track well in real time and maintain good accuracy and robustness in an infrared ground environment.

参考文献/References:

[1] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean Shift[C]//IEEE Computer Vision and Pattern Recognition, 2000: 142-149.
[2] YANG Yue, LIU Xingmiao, GUO Qiwang, et al. Infrared Object Matching Tracking Algorithm Based on Improved Mutual Information[J]. Infrared Technology, 2013, 35(6): 350-354.
[3] Elad M, Aharon M. Image denoising via sparse and redundant representations over learned dictionaries[J]. Image Processing, IEEE Transactions on, 2006, 15(12): 3736-3745.
[4] ZHANG K, ZHANG L, YANG M H. Real-time compressive tracking[C]//European Conference on Computer Vision, 2012: 864-877.
[5] Kalal Z, Mikolajczyk K, Matas J. Tracking-Learning-Detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2012, 34(7): 1409-1422.
[6] ZHANG Kaihua, ZHANG Lei, YANG Mingsuan. Real-time object tracking via online discriminative feature selection[J]. Image Processing, IEEE Transactions on, 2013, 22(12): 4664-4677.
[7] Navneet Dalal, Bill Triggs. Histograms of oriented gradients for human detection[C]//IEEE Computer Vision and Pattern Recognition, 2005: 886-893.
[8] YANG H R. Research on tracking algorithm of infrared ground target [D]. Chengdu: University of Electronic Science and Technology of China, 2017.
[9] ZHANG Kaihua, ZHANG Lei, YANG Mingsuan. Fast compressive tracking Pattern Analysis and Machine Intelligence[J]. IEEE Transactions on, 2014, 36(10): 2002-2015.
[10] Ross D A, Lim J, Lin R, et al. Incremental Learning for Robust Visual Tracking[J]. International Journal of Computer Vision, 2008, 77(1): 125-141.
[11] Kalal Z, Matas J, Mikolajczyk K. P-N learning: Bootstrapping binary classifiers by structural constraints[C]//Computer Vision and Pattern Recognition, IEEE Xplore, 2010: 49-56.
[12] Felsberg Michael, Berg Amanda, Hager Gustav. The Thermal Infrared Visual Object Tracking VOT-TIR2015 Challenge Results[C]//2015 IEEE International Conference on Computer Vision Workshop (ICCVW), 2015: 639-651.

相似文献/References:

[1]赵忠伟,程玉宝,张玉钧.红外目标温度变化对被发现距离的影响研究[J].红外技术,2011,33(09):530.
 ZHAO Zhong-wei,CHENG Yu-bao,ZHANG Yu-jun.Research on the Effect of Infrared Target Temperature Variation?on Detection Distance[J].Infrared Technology,2011,33(5):530.
[2]师帅,付冬梅.基于红外图像的遮挡标准几何体重构方法的研究[J].红外技术,2008,30(十一):655.
 SHI Shuai,FU Dong-mei.A Research for 3D Reconstruction of Concealed Standard Geometrical SolidsBased on Two Infrared Images[J].Infrared Technology,2008,30(5):655.
[3]张毅,赵亦工,胡文江.基于高阶累计量的红外图像弱小点目标检测[J].红外技术,2006,28(10):585.
 ZHANG Yi,ZHAO Yi-gong,HU Wen-jiang.Detecting Dim Point Target in Infrared Images Using High-Order Cumulant[J].Infrared Technology,2006,28(5):585.
[4]张志彦,付冬梅.基于红外热图像的标准几何体重构方法的研究[J].红外技术,2006,28(12):691.
 ZHANG Zhi-yan,FU Dong-mei.A Research for 3D Reconstruction of Standard Geometrical Solids?Based on Single Infrared Image[J].Infrared Technology,2006,28(5):691.
[5]曾金发,吴恩斯,李能勇.基于双核协同学习模型的红外目标跟踪算法[J].红外技术,2018,40(5):438.[doi:10.11846/j.issn.1001_8891.201805006]
 ZENG Jinfa,WU Ensi,LI Nengyong.Infrared Object-Tracking Algorithm Based on Dual-kernelized Collaborative Learning[J].Infrared Technology,2018,40(5):438.[doi:10.11846/j.issn.1001_8891.201805006]

备注/Memo

备注/Memo:
收稿日期:2018-12-19;修订日期:2020-03-25.
作者简介:李继泉(1985-),男,本科,主要从事光电系统设计。E-mail: jiquan_li@163.com.

更新日期/Last Update: 2020-05-19