[1]邵江南,葛洪伟.一种基于深度学习目标检测的长时目标跟踪算法[J].智能系统学报,2021,16(3):433-441.[doi:10.11992/tis.201910029]
 SHAO Jiangnan,GE Hongwei.A long-term object tracking algorithm based on deep learning and object detection[J].CAAI Transactions on Intelligent Systems,2021,16(3):433-441.[doi:10.11992/tis.201910029]
点击复制

一种基于深度学习目标检测的长时目标跟踪算法(/HTML)
分享到:

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

卷:
第16卷
期数:
2021年3期
页码:
433-441
栏目:
学术论文—机器感知与模式识别
出版日期:
2021-05-05

文章信息/Info

Title:
A long-term object tracking algorithm based on deep learning and object detection
作者:
邵江南12 葛洪伟12
1. 江南大学 江苏省模式识别与计算智能工程实验室,江苏 无锡 214122;
2. 江南大学 物联网工程学院,江苏 无锡 214122
Author(s):
SHAO Jiangnan12 GE Hongwei12
1. Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, Jiangnan University, Wuxi 214122, China;
2. School of Internet of Things, Jiangnan University, Wuxi 214122, China
关键词:
目标跟踪长时跟踪神经网络卷积特征类不均衡问题损失函数特征提取深度学习
Keywords:
object trackinglong-term trackingneural networkconvolutional featuresclass imbalance problemloss functionfeature extractiondeep learning
分类号:
TP391.4
DOI:
10.11992/tis.201910029
摘要:
针对长时目标跟踪所面临的目标被遮挡、出视野等常常会导致跟踪漂移或丢失的问题,基于MDNet提出一种深度长时目标跟踪算法(long-term object tracking based on MDNet, LT-MDNet)。首先,引入了一种改进的收缩损失函数,以解决模型训练时正负样本不均衡的问题;其次,设计了一种高置信度保留样本池,对在线跟踪时的每一帧的有效并且置信度最高结果进行保留,并在池满时替换最低置信度的保留样本;最后,在模型检测到跟踪失败或连续跟踪帧数达到特定阈值时,利用保留样本池进行在线训练更新模型,从而使模型在应对长时跟踪时保持鲁棒和高效。实验结果表明,LT-MDNet在跟踪精度和成功率上都展现了极强的竞争力,并且在目标被遮挡、出视野等情况下保持了优越的跟踪性能和可靠性。
Abstract:
Aiming at the problem of tracking drift or loss caused by the occlusion and the out-of-view of the target in long-term tracking, this paper proposes a new deep, long-term tracking algorithm based on MDNet (LT-MDNet). First, an improved shrinkage loss function is introduced to solve the problem of the positive-negative class imbalance in the model training. Second, a high confidence retention sample pool is designed to retain the valid and highest confidence results of each frame during online tracking and to replace the lowest confidence retention samples when the pool is full. Finally, when the model detects a tracking failure or when the continuous tracking frame number reaches a specific threshold, the reserved sample pool is used for online training to update the model to make the model robust and efficient in dealing with long-term tracking. Experimental results show that LT-MDNet is highly competitive in its tracking accuracy and success rate and maintains excellent tracking performance and reliability in the case of target occlusion and out-of-view.

参考文献/References:

[1] ARULAMPALAM M S, MASKELL S, GORDON N, et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking[J]. IEEE transactions on signal processing, 2002, 50(2):174-188.
[2] COMANICIU D, MEER P. Mean shift:a robust approach toward feature space analysis[J]. IEEE transactions on pattern analysis and machine intelligence, 2002, 24(5):603-619.
[3] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA, 2010:2544-2550.
[4] 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.
[5] MUELLER M, SMITH N, GHANEM B. Context-aware correlation filter tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017:1396-1404.
[6] DANELLJAN M, H?GER G, SHAHBAZ KHAN F, et al. Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015:4310-4318.
[7] KIANI GALOOGAHI H, FAGG A, LUCEY S. Learning background-aware correlation filters for visual tracking[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017:1135-1143.
[8] 宁欣, 李卫军, 田伟娟, 等. 一种自适应模板更新的判别式KCF跟踪方法[J]. 智能系统学报, 2019, 14(1):121-126
NING Xin, LI Weijun, TIAN Weijuan, et al. Adaptive template update of discriminant KCF for visual tracking[J]. CAAI transactions on intelligent systems, 2019, 14(1):121-126
[9] NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016:4293-4302.
[10] BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-convolutional Siamese networks for object tracking[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands, 2016:850-865.
[11] WANG Qiang, TENG Zhu, XING Junliang, et al. Learning attentions:residual attentional Siamese network for high performance online visual tracking[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:4854-4863.
[12] SUNG K K, POGGIO T. Example-based learning for view-based human face detection[J]. IEEE transactions on pattern analysis and machine intelligence, 1998, 20(1):39-51.
[13] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017:2980-2988.
[14] VALMADRE J, BERTINETTO L, HENRIQUES J, et al. End-to-end representation learning for correlation filter based tracking[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017:2805-2813.
[15] WU Yi, LIM J, YANG M H. Object tracking benchmark[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(9):1834-1848.
[16] MUELLER M, SMITH N, GHANEM B. A benchmark and simulator for uav tracking[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands, 2016:445?461.
[17] CHATFIELD K, SIMONYAN K, VEDALDI A, et al. Return of the devil in the details:Delving deep into convolutional nets[EB/OL].(2014-11-05)[2019-10-01]https://arxiv.org/abs/1405.3531.
[18] LU Xiankai, MA Chao, NI Bingbing, et al. Deep regression tracking with shrinkage loss[C]//Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich, Germany, 2018:353-369.
[19] LI Xin, MA Chao, WU Baoyuan, et al. Target-aware deep tracking[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019:1369-1378.
[20] LI Bo, YAN Junjie, WU Wei, et al. High performance visual tracking with Siamese region proposal network[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018:8971-8980.
[21] ZHANG Zhipeng, PENG Houwen. Deeper and wider Siamese networks for real-time visual tracking[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019:4591-4600.
[22] HONG Zhibin, CHEN Zhe, WANG Chaohui, et al. Multi-store tracker (muster):a cognitive psychology inspired approach to object tracking[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015:749-758.
[23] RUSSAKOVSKY O, DENG Jia, SU Hao, et al. ImageNet large scale visual recognition challenge[J]. International journal of computer vision, 2015, 115(3):211-252.
[24] ZHANG Shunli, LU Wei, XING Weiwei, et al. Using fuzzy least squares support vector machine with metric learning for object tracking[J]. Pattern recognition, 2018, 84:112-125.

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(3):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(3):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(3):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(3):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(3):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(3):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(3):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(3):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(3):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(3):775.[doi:10.11992/tis.201410009]

备注/Memo

备注/Memo:
收稿日期:2019-10-24。
基金项目:江苏省研究生创新计划项目(KYLX16_0781);江苏高校优势学科建设工程项目(PAPD)
作者简介:邵江南,硕士研究生,主要研究方向为目标跟踪、深度学习;葛洪伟,教授,博士生导师,主要研究方向为人工智能与模式识别、机器学习、图像处理与分析。主持和参与国家自然科学基金等国家级项目5项,省部级重点项目4项。发表学术论文100余篇
通讯作者:葛洪伟.E-mail:ghw8601@163.com
更新日期/Last Update: 2021-06-25