[1]刘威,靳宝,周璇,等.基于特征融合及自适应模型更新的相关滤波目标跟踪算法[J].智能系统学报,2020,15(4):714-721.[doi:10.11992/tis.201803036]
 LIU Wei,JIN Bao,ZHOU Xuan,et al.Correlation filter target tracking algorithm based on feature fusion and adaptive model updating[J].CAAI Transactions on Intelligent Systems,2020,15(4):714-721.[doi:10.11992/tis.201803036]
点击复制

基于特征融合及自适应模型更新的相关滤波目标跟踪算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第15卷
期数:
2020年4期
页码:
714-721
栏目:
学术论文—机器学习
出版日期:
2020-07-05

文章信息/Info

Title:
Correlation filter target tracking algorithm based on feature fusion and adaptive model updating
作者:
刘威123 靳宝123 周璇123 付杰123 王薪予123 郭直清123 牛英杰123
1. 辽宁工程技术大学 理学院,辽宁 阜新 123000;
2. 辽宁工程技术大学 智能工程与数学研究院,辽宁 阜新 123000;
3. 辽宁工程技术大学 数学与系统科学研究所,辽宁 阜新 123000
Author(s):
LIU Wei123 JIN Bao123 ZHOU Xuan123 FU Jie123 WANG Xinyu123 GUO Zhiqing123 NIU Yingjie123
1. School of Sciences, Liaoning Technical University, Fuxin 123000, China;
2. Institute of Intelligence Engineering and Mathematics, Liaoning Technical University, Fuxin 123000, China;
3. Institute of Mathematics and Systems Science, Liaoning Technical University, Fuxin 123000, China
关键词:
目标跟踪相关滤波特征融合模型更新目标遮挡背景干扰计算机视觉奇异值分解
Keywords:
object trackingcorrelation filterfeature fusionmodel updatingobject occlusionbackground interferencecomputer visionsingular value decomposition
分类号:
TP301
DOI:
10.11992/tis.201803036
摘要:
针对单一特征目标跟踪算法因背景干扰、目标遮挡造成的跟踪失败问题,以及跟踪过程中每帧进行模型更新容易造成错误更新和实时性差的问题,提出了一种基于特征融合及自适应模型更新策略的相关滤波目标跟踪算法-多特征自适应相关滤波目标跟踪算法。该算法在特征提取阶段将边缘特征及HOG特征加权融合作为目标特征,加强对边缘特征的学习;在模型更新阶段通过计算预测区域与真实区域的奇异值特征向量相似度,并结合设定的阈值判断是否需要进行模型更新,通过自适应更新的方式减少模型的更新次数。在标准测试视频集下验证所提算法,并与两种经典相关滤波算法进行比较,结果表明该算法能够较好地适应背景干扰及目标遮挡问题,跟踪目标的平均中心误差减少了9.05像素,平均距离精度提高12.2%,平均重叠率提高4.53%。
Abstract:
For the problem of object tracking failure caused by background interference, object occlusion in object tracking algorithm based on a single feature, and the problem of error updating and poor real-time performance caused by model updating for each frame during tracking, a correlation filtering object tracking algorithm based on feature fusion and adaptive model updating is proposed in this paper. In the feature extraction phase, the edge feature and HOG feature are weighted together as the object features to enhance the learning of edge features. During the updating phase of the model, calculating the similarity of singular value eigenvector between the predicted region and the real region, and according to the set threshold to determine whether the model needs to be updated or not, and reducing the number of updates to the model by adaptively updating. The algorithm is verified under the standard test video set, and compared with two typical correlation filtering algorithms. The results show that the algorithm can better adapt to background interference and object occlusion problem. The average center location error is reduced by 9.05 pixels, the average distance precision is increased by 12.2%, and the average overlapping precision is increased by 4.53%.

参考文献/References:

[1] CHEN Zhe, HONG Zhibin, TAO Dacheng. An experimental survey on correlation filter-based tracking[J]. arXiv: 1509.05520, 2015.
[2] 张微, 康宝生. 相关滤波目标跟踪进展综述[J]. 中国图象图形学报, 2017, 22(8): 1017-1033
ZHANG Wei, KANG Baosheng. Recent advances in correlation filter-based object tracking: a review[J]. Journal of image and graphics, 2017, 22(8): 1017-1033
[3] VALMADRE J, BERTINETTO L, HENRIQUES J F, et al. End-to-end tracking[J]. arXiv: 1704.06036, 2017.
[4] 刘新卉. 基于深度信息的核相关滤波目标跟踪算法研究[D]. 深圳: 哈尔滨工业大学, 2017.
LIU Xinhui. Research on kernel correlation filter object tracking algorithm based on depth information[D]. Shenzhen: Harbin Institute of Technology, 2017
[5] 董艳梅. 基于相关滤波器的目标跟踪技术[D]. 北京: 北京理工大学, 2015.
DONG Yanmei. Visual object tracking based on correlation filters[D]. Beijing: Beijing Institute of Technology, 2015.
[6] 朱明敏, 胡茂海. 基于相关滤波器的长时视觉目标跟踪方法[J]. 计算机应用, 2017, 37(5): 1466-1470
ZHU Mingmin, HU Maohai. Long-term visual object tracking algorithm based on correlation filter[J]. Journal of computer applications, 2017, 37(5): 1466-1470
[7] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object representation learning for correlation filter based tracking using adaptive correlation filters[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA, 2010: 2544-2550.
[8] HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//European conference on computer vision. Berlin, Germany, 2012: 702-715.
[9] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(3): 583-596.
[10] DANELLJAN M, SHAHBAZ K F, FELSBERG M, et al. Adaptive color attributes for real-time visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA, 2014: 1090-1097.
[11] WU Y, LIM J, YANG M H. Online object tracking: A benchmark[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 2411-2418.
[12] DANELLJAN M, HAGER G, KHAN F, et al. Accurate scale estimation for robust visual tracking[C]//British Machine Vision Conference. Nottingham, UK, 2014:1-11.
[13] DANELLJAN M, HAGER G, SHAHBAZ K F, et al. Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 4310-4318.
[14] LI Y, ZHU J. A scale adaptive kernel correlation filter tracker with feature integration[C]//European Conference on Computer Vision. Zurich, Switzerland, 2014: 254-265.
[15] DANELLJAN M, HAGER G, KHAN F S, et al. Con volutional features for correlation filter based visual tracking[C]//IEEE International Conference on Computer Vision Workshop. Santiago, Chile, 2015: 621-629.
[16] 白冰, 钟必能, 欧阳谷. 融合分层卷积特征和尺度自适应核相关滤波器的目标跟踪[J]. 小型微型计算机系统, 2017, 38(9): 2062-2066
BAI Bing, ZHONG Bineng, OUYANG Gu. Object tracking based on hierarchical convolution feature and scale adaptive kernel correlation filter[J]. Journal of chinese computer systems, 2017, 38(9): 2062-2066
[17] MA C, HUANG J B, YANG X, et al. Hierarchical convo- lutional features for visual tracking[C]//IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 30 74-3082.
[18] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking- learning-detection[J]. IEEE Transactions on software engineering, 2011, 34(7): 1409-1422.
[19] BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-convolutional siamese networks for object tracking[C]//European Conference on Computer Vision. Amsterdam, Netherlands, 2016: 850-865.
[20] 洪子泉, 杨静宇. 用于图像识别的图像代数特征抽取[J]. 自动化学报, 1992, 18(2): 233-238
HONG Ziquan, YANG Jingyu. Algebraic feature extraction of images for recognition[J]. Acta automatica sinica, 1992, 18(2): 233-238

相似文献/References:

[1]王绍钰 蔡自兴,陈爱斌.改进的粒子滤波器目标跟踪方法[J].智能系统学报,2008,3(03):189.
 WANG Shao-yu,CAI Zi-xing,CHEN Ai-bin.Improved object tracking method for particle filters[J].CAAI Transactions on Intelligent Systems,2008,3(4):189.
[2]刘 清,吴志刚,窦 琴,等.粒子滤波的视频目标跟踪算法研究[J].智能系统学报,2009,4(06):538.[doi:10.3969/j.issn.1673-4785.2009.06.012]
 LIU Qing,WU Zhi-gang,DOU Qin,et al.A particle filtering algorithm for tracking moving objects in videos[J].CAAI Transactions on Intelligent Systems,2009,4(4):538.[doi:10.3969/j.issn.1673-4785.2009.06.012]
[3]伍 明,孙继银.一种机器人未知环境下动态目标跟踪交互多模滤波算法[J].智能系统学报,2010,5(02):127.
 WU Ming,SUN Ji-yin.An interacting multiple model filtering algorithm for mobile robots to improve tracking of moving objects in unknown environments[J].CAAI Transactions on Intelligent Systems,2010,5(4):127.
[4]李 金,胡文广.基于颜色的快速人体跟踪及遮挡处理[J].智能系统学报,2010,5(04):353.
 LI Jin,HU Wen-guang.Tracking fast movement using colors while accommodating occlusion[J].CAAI Transactions on Intelligent Systems,2010,5(4):353.
[5]刘侠,陶冶,邢春.统计差分与自启动的Camshift跟踪算法[J].智能系统学报,2011,6(04):355.
 LIU Xia,TAO Ye,XING Chun.An objective tracking Camshift algorithm based onautomatic startup and the statistical differential method[J].CAAI Transactions on Intelligent Systems,2011,6(4):355.
[6]伍明,孙继银.基于粒子滤波的未知环境下机器人同时定位、地图构建与目标跟踪[J].智能系统学报,2013,8(02):168.[doi:10.3969/j.issn.1673-4785.201202001]
 WU Ming,SUN Jiyin.Simultaneous localization, mapping and object tracking in an unknown environment using particle filtering[J].CAAI Transactions on Intelligent Systems,2013,8(4):168.[doi:10.3969/j.issn.1673-4785.201202001]
[7]贺超,刘华平,孙富春,等.采用Kinect的移动机器人目标跟踪与避障[J].智能系统学报,2013,8(05):426.[doi:10.3969/j.issn.1673-4785.201301028]
 HE Chao,LIU Huaping,SUN Fuchun,et al.Target tracking and obstacle avoidance of mobile robot using Kinect[J].CAAI Transactions on Intelligent Systems,2013,8(4):426.[doi:10.3969/j.issn.1673-4785.201301028]
[8]王熙,吴为,钱沄涛.基于轨迹聚类的超市顾客运动跟踪[J].智能系统学报,2015,10(02):187.[doi:10.3969/j.issn.1673-4785.201401002]
 WANG Xi,WU Wei,QIAN Yuntao.Trajectory clustering based customer movement tracking in a supermarket[J].CAAI Transactions on Intelligent Systems,2015,10(4):187.[doi:10.3969/j.issn.1673-4785.201401002]
[9]陈真,王钊.元认知粒子滤波目标跟踪算法[J].智能系统学报,2015,10(03):387.[doi:10.3969/j.issn.1673-4785.201405052]
 CHEN Zhen,WANG Zhao.Object tracking algorithm with metacognitive model-based particle filters[J].CAAI Transactions on Intelligent Systems,2015,10(4):387.[doi:10.3969/j.issn.1673-4785.201405052]
[10]王杰,蒋明敏,花晓慧,等.基于投影直方图匹配的双目视觉跟踪算法[J].智能系统学报,2015,10(5):775.[doi:10.11992/tis.201410009]
 WANG Jie,JIANG Mingmin,HUA Xiaohui,et al.Binocular object tracking method using projection histogram matching[J].CAAI Transactions on Intelligent Systems,2015,10(4):775.[doi:10.11992/tis.201410009]
[11]戴煜彤,陈志国,傅毅.相关滤波的运动目标抗遮挡再跟踪技术[J].智能系统学报,2021,16(4):630.[doi:10.11992/tis.202005027]
 DAI Yutong,CHEN Zhiguo,FU Yi.Anti-occlusion retracking technology for a moving target based on correlation filtering[J].CAAI Transactions on Intelligent Systems,2021,16(4):630.[doi:10.11992/tis.202005027]

备注/Memo

备注/Memo:
收稿日期:2018-03-22。
基金项目:国家自然科学基金项目(51974144,71771111)
作者简介:刘威,副教授,博士,中国人工智能学会会员,中国计算机学会会员,主要研究方向为深度神经网络、机器学习、矿业系统工程;靳宝,硕士研究生,主要研究方向为强化学习、机器学习;周璇,硕士研究生,中国计算机学会会员,主要研究方向为深度神经网络、机器学习
通讯作者:刘威.E-mail:lv8218218@126.com
更新日期/Last Update: 2020-07-25