基于自适应多模型联合的目标跟踪算法

doi:10.19678/j.issn.1000-3428.0052593

计算机工程 ›› 2019, Vol. 45 ›› Issue (8): 266-274. doi: 10.19678/j.issn.1000-3428.0052593

基于自适应多模型联合的目标跟踪算法

王任华¹, 沈剑宇², 蒋敏²

1. 中国人民公安大学信息技术与网络安全学院, 北京 100038;
2. 江南大学物联网工程学院, 江苏无锡 214122

收稿日期:2018-09-07 修回日期:2018-10-24 出版日期:2019-08-15 发布日期:2019-08-08
作者简介:王任华(1972-),女,副教授、硕士,主研方向为视频侦查、模式识别;沈剑宇,硕士研究生;蒋敏,教授、博士。
基金资助:
国家自然科学基金（61362030，61201429）；中国博士后科学基金（2015M581720，2016M600360）；科技援疆专项计划（2017E0279）；公安部技术研究计划（2018JSYJA01）。

Target Tracking Algorithm Based on Adaptive Multi-Model Joint

WANG Renhua¹, SHEN Jianyu², JIANG Min²

1. College of Information Technology and Network Security, People's Public Security University of China, Beijing 100038, China;
2. School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China

Received:2018-09-07 Revised:2018-10-24 Online:2019-08-15 Published:2019-08-08

摘要/Abstract

摘要： 基于核相关滤波器的跟踪算法对于目标的空间结构具有较强的依赖性，无法有效应对遮挡、形变等干扰因素，且单一的特征模型在复杂的跟踪场景下无法准确表述目标信息。为此，提出一种基于自适应多模型联合的算法。通过自适应权重将相关滤波模型与颜色直方图模型进行联合，并将稀疏表示的思想引入相关滤波模型的训练过程中，以增强算法的鲁棒性。OTB视频序列数据集上的实验结果表明，该算法可有效缓解跟踪过程中的遮挡、形变等因素的干扰，与Staple算法、KCF算法相比，目标跟踪的精度显著提升。

关键词: 目标跟踪, 自适应权重, 核相关滤波器, 联合模型, L1范数

Abstract: The tracking algorithm based on Kernelized Correlation Filter(KCF) has strong dependence on the spatial structure of the target,cannot effectively deal with the occlusion,deformation and other interference factors,and the single feature model is unable to accurately represent the target information in complex tracking occasions.Therefore,an adaptive multi-model tracking algorithm is proposed.The correlation filter model and the color histogram model are combined by adaptive weight,and the idea of sparse representation is introduced into the training process of the correlation filter model to further enhance the robustness of the algorithm.Experimental results on the OTB dataset show that the algorithm can effectively mitigate the interferences from various factors such as occlusion and deformation in the tracking process,and compred with Staple algorithm,KCF algorithm and others,the algorithm achieves significant improvement in target tracking accuracy.

Key words: target tracking, adaptive weight, Kernelized Correlation Filter(KCF), joint model, L1 norm

中图分类号:

TP391

王任华, 沈剑宇, 蒋敏. 基于自适应多模型联合的目标跟踪算法[J]. 计算机工程, 2019, 45(8): 266-274.

WANG Renhua, SHEN Jianyu, JIANG Min. Target Tracking Algorithm Based on Adaptive Multi-Model Joint[J]. Computer Engineering, 2019, 45(8): 266-274.

http://www.ecice06.com/CN/Y2019/V45/I8/266

参考文献 20

[1]	张晶,王旭,范洪博.自适应学习的时空上下文目标跟踪算法[J].计算机工程,2018,44(6):294-299.
[2]	WANG Naiyan,SHI Jianping,YEUNG D Y,et al.Understanding and diagnosing visual tracking systems[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:3101-3109.
[3]	孔军,成静,蒋敏,等.组合范数正则化稀疏编码和自适应加权残差的鲁棒跟踪[J].计算机辅助设计与图形学学报,2018,30(4):634-641.
[4]	魏全禄,老松杨,白亮.基于相关滤波器的视觉目标跟踪综述[J].计算机科学,2016,43(11):1-5.
[5]	BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:2544-2550.
[6]	HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2012:702-715.
[7]	HENRIQUES J F,RUI C,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.
[8]	DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2005:886-893.
[9]	YAO Rui,XIA Shixiong,ZHANG Zhen,et al.Real-time correlation filter tracking by efficient dense belief propagation with structure preserving[J].IEEE Transactions on Multimedia,2017,19(4):772-784.
[10]	李冠彬,吴贺丰.基于颜色纹理直方图的带权分块均值漂移目标跟踪算法[J].计算机辅助设计与图形学学报,2011,23(12):2059-2066.
[11]	POSSEGGER H,MAUTHNER T,BISCHOF H.In defense of color-based model-free tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:2113-2120.
[12]	BERTINETTO L,VALMADRE J,GOLODETZ S,et al.Staple:complementary learners for real-time tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:1401-1409.
[13]	BAO Chenglong,WU Yi,LING Haibin,et al.Real time robust L1 tracker using accelerated proximal gradient approach[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:1830-1837.
[14]	WILLIAMS C K I.Learning with kernels:support vector machines,regularization,optimization,and beyond[J].Publications of the American Statistical Association,2003,98(462):489-489.
[15]	RIFKIN R,YEO G,POGGIO T.Regularized least-squares classification[EB/OL].[2018-08-25].http://cbcl.mit.edu/publications/ps/rlsc.pdf. URL
[16]	JIANG Min,SHEN Jianyu,KONG Jun,et al.Robust visual tracking based on kernelized correlation filters[C]//Proceedings of IEEE International Conference on Information and Automation.Washington D.C.,USA:IEEE Press,2017:110-115.
[17]	BECK A,TEBOULLE M.A fast iterative shrinkage-thresholding algorithm for linear inverse problems[J].SIAM Journal on Imaging Sciences,2009,2(1):183-202.
[18]	DANELLJAN M,H GER G,KHAN F S,et al.Accurate scale estimation for robust visual tracking[C]//Proceedings of British Machine Vision Conference.[S.l.]:BMVA Press,2014:1-11.
[19]	WU Yi,LIM J,YANG Minghuan.Online object tracking:a benchmark[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:2411-2418.
[20]	BIBI A,GHANEM B.Multi-template scale-adaptive kernelized correlation filters[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:613-620.

选择文件类型/文献管理软件名称

选择包含的内容

基于自适应多模型联合的目标跟踪算法

Target Tracking Algorithm Based on Adaptive Multi-Model Joint

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王春雷, 张建林, 李美惠, 徐智勇, 魏宇星. 结合卷积Transformer的目标跟踪算法[J]. 计算机工程, 2023, 49(4): 281-288,296.
[2]	周海赟, 项学智, 王馨遥, 任文凯. 多特征融合的端到端链式行人多目标跟踪网络[J]. 计算机工程, 2022, 48(9): 305-313.
[3]	杨帅东, 谌海云, 徐钒诚, 赵书朵, 袁杰敏. 基于孪生区域建议网络的无人机目标跟踪算法[J]. 计算机工程, 2022, 48(1): 288-295,304.
[4]	李伟, 黄鹤鸣, 武风英, 张会云. 基于深度多特征融合的自适应CNN图像分类算法[J]. 计算机工程, 2021, 47(9): 235-239,251.
[5]	张海涛, 秦鹏程. 基于GMS与FPME的视频目标跟踪方法[J]. 计算机工程, 2021, 47(7): 226-231.
[6]	任立成, 杨嘉棋, 魏宇星, 张建林. 基于特征融合与双模板嵌套更新的孪生网络跟踪算法[J]. 计算机工程, 2021, 47(7): 239-248.
[7]	苏超群, 朱正为, 郭玉英. 基于高效卷积算子的异常抑制目标跟踪算法[J]. 计算机工程, 2021, 47(7): 266-272,288.
[8]	李志鹏, 张睿. 一种基于对抗学习的实时跟踪模型设计[J]. 计算机工程, 2021, 47(6): 262-270.
[9]	黄彬, 胡立坤, 张宇. 基于自适应权重的改进Census立体匹配算法[J]. 计算机工程, 2021, 47(5): 189-196.
[10]	文斌, 朱晗. 基于自适应权重的立体匹配优化算法[J]. 计算机工程, 2021, 47(4): 268-276.
[11]	尚桠朝, 孟令军. 基于多特征和尺度估计的KCF_MTSA算法[J]. 计算机工程, 2021, 47(3): 102-108,116.
[12]	罗朔, 侯进, 谭光鸿, 韩雁鹏. 一种低参数的孪生卷积网络实时目标跟踪算法[J]. 计算机工程, 2021, 47(2): 84-89.
[13]	贾旭楠, 魏庭新, 曲维光, 顾彦慧, 周俊生. 基于神经网络的复句判定及其关系识别研究[J]. 计算机工程, 2021, 47(11): 54-61.
[14]	张腾飞, 周书仁, 彭建. 基于双孪生网络的自适应选择跟踪系统[J]. 计算机工程, 2020, 46(6): 103-107.
[15]	沈泽君, 丁飞飞, 杨文元. 多粒度相关滤波视频跟踪方法[J]. 计算机工程, 2020, 46(5): 274-281.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于自适应多模型联合的目标跟踪算法

Target Tracking Algorithm Based on Adaptive Multi-Model Joint

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 15

编辑推荐

Metrics

本文评价