[1]齐楠楠,揭斐然,谢 熙,等.基于TLD的舰船目标跟踪方法研究[J].红外技术,2013,35(12):780-787.[doi:10.11846/j.issn.1001_8891.201312007]
 QI Nan-nan,JIE Fei-ran,XIE Xi,et al.Ship Target Tracking Based on Tracking-Learning-Detecting Tactics[J].Infrared Technology,2013,35(12):780-787.[doi:10.11846/j.issn.1001_8891.201312007]
点击复制

基于TLD的舰船目标跟踪方法研究
分享到:

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

卷:
35卷
期数:
2013年12期
页码:
780-787
栏目:
出版日期:
2013-12-20

文章信息/Info

Title:
Ship Target Tracking Based on Tracking-Learning-Detecting Tactics
文章编号:
1001-8891(2013)-12-0780-08
作者:
齐楠楠1揭斐然1谢 熙2吴 巍2
1.中航工业洛阳电光设备研究所 光电控制技术重点实验室,河南 洛阳 471009;
2.武汉理工大学 信息工程学院,湖北 武汉 430070
Author(s):
QI Nan-nan1JIE Fei-ran1XIE Xi2WU Wei2
1.Luoyang Institute of Electro-optical Equipment, Key Laboratory of Optical Electrics Control Technology, Luoyang 471009, China;
2. Wuhan University of Technology, School of Information Engineering, Wuhan 430070, China
关键词:
舰船跟踪随机蕨分类器TLD算法在线学习
Keywords:
ship trackingrandom ferns classifierTLD algorithmonline learning
分类号:
TP274;TN713
DOI:
10.11846/j.issn.1001_8891.201312007
文献标志码:
A
摘要:
复杂背景下进行舰船目标的跟踪时,在某些帧可能会有目标丢失。为了克服这个问题,采用联合检测-学习-跟踪的TLD算法。其过程是通过训练一种在线可更新的随机蕨分类器对目标跟踪结果进行检测,并使用一种基于时空约束的PN学习策略对分类器进行学习和更新,最后融合跟踪得到的结果对目标进行判别和确定。试验结果表明,该跟踪算法可适用于目标外形改变和遮挡的情况,鲁棒性强,识别率高,误检率低,同时实时性也较好,可以满足一般的在线跟踪系统的要求。
Abstract:
When warship targets are tracked in complex background, the targets loss may occur in some frames. In order to overcome the problem, a tracking-learning-detecting(TLD)algorithm is introduced. With the random ferns classifier which is trained online, the detection is performed based on the classification results. PN learning constrained by spatial and temporal features is used to update the classifier. The detection results and tracking results are fused to locate the target in each frame. Finally, experimental result shows that the TLD tracking algorithm has a high recognition rate and a low false detection rate. Benefitting from continuous learning with various target changes in each frame, the TLD algorithm is robust to target appearance changes and occlusion, and has a good real-time performance. The proposed algorithm can meet the requirements of general online tracking system.

参考文献/References:

[1] Huan W, Ming-wu R, Jingyu Y. Object Tracking Based on Genetic Algorithm and Kalman Filter[C]//International Conference on Computational Intelligence and Security, 2008: 80-85.
[2] Qin kun X, Xiangjun L, Mina L. Object tracking based on local feature matching[C]//Fifth International Symposium on Computational Intelligence and Design (ISCID), 2012: 399-402 .
[3] Nak Y K, Tae G K. Comparison of Kalman filter and particle filter used for localization of an underwater vehicle[C]//9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), 2012: 350-352 .
[4] Baohong Y, Dexiang Z, Kui F, et al. Video tracking of human with occlusion based on MeanShift and Kalman filter[C]//4th Electronic System-Integration Technology Conference (ESTC), 2012: 3672-3677.
[5] Jianfang D, Jianxun L, Zhi Z, et al. Face tracking with an Adaptive Adaboost-based Particle Filter[C]//24th Chinese Control and Decision Conference (CCDC), 2012: 3626 - 3631.
[6] Kalal Z, Matas J, Mikolajczyk K. Online learning of robust object detectors during unstable tracking[C]//12th IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 2009: 1417-1424.
[7] Kalal Z, Mikolajczyk K, Matas J. Face-TLD: Tracking -Learning- Detection applied to faces[C]//17th IEEE International Conference on Image Processing (ICIP), 2010: 3789-3792 .
[8] Ozuysal M, Calonder M, Lepetit V, et al. Fast keypoint recognition using random ferns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(3): 448-461.
[9] Villamizar M, Garrell A, Sanfeliu A, et al. Online human-assisted learning using Random Ferns[C]//21st International Conference on Pattern Recognition (ICPR), 2012: 2821-2824 .
[10] Bosch A, Zisserman A, Muoz X. Image classification using random forests and ferns[C]//11th IEEE International Conference on Computer Vision, 2007:1-8 .
[11] Suwon L, Sang-Wook L, Yeong N C, et al. Lightweight Random Ferns using binary representation[C]//21st International Conference on Pattern Recognition (ICPR), 2012: 1342-1345.
[12] Kalal Z, Matas J, Mikolajczyk K. P-N learning: Bootstrapping binary classifiers by structural constraints[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010: 49-56 .




备注/Memo

备注/Memo:
?收稿日期:2013-09-06;修订日期:2013-10-30.
作者简介:齐楠楠(1982-),女,硕士,工程师,主要研究方向为目标检测和图像跟踪。E-mail:eoei@vip.sina.com。
基金项目:国家自然科学基金资助项目,编号:61273241;航空科学基金,编号:20105179002。
更新日期/Last Update: 2013-12-26