首页 > 论文 > 激光与光电子学进展 > 55卷 > 9期(pp:91502--1)

基于核相关滤波器的多目标跟踪算法

Multiple Object Tracking Algorithm Based on Kernel Correlation Filter

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对多目标跟踪算法中经常会面临的各种挑战, 如相机的突然运动、遮挡、误检和外观相似等情况, 提出一种基于核相关滤波(KCF)的分步关联框架。首先, 该算法采用基于卷积神经网络的目标检测器检测目标, 获得准确的检测结果。然后, 为了更好地预测目标的运动状态, 通过加权融合三种特征的跟踪结果, 为每个目标建立一个基于KCF算法的快速跟踪器。此外, 为了有效地降低碎片化轨迹的数量, 该算法通过跟踪片的置信度分步关联轨迹, 并在遮挡的情况下, 利用在线随机蕨重新检测目标。最后利用关联成功的检测信息自适应更新KCF算法中的尺度。实验结果表明, 与现有算法相比, 所提算法能够在各种复杂的条件下, 表现出强大和高效的跟踪性能。

Abstract

A kernel correlation filter (KCF) with step-by-step association framework is proposed to aim at the various challenges, such as camera sudden movement, occlusion, false detection and appearance similarity in multi-target tracking algorithms. Firstly, the accurate detection results are obtained by utilizing a target detector based on the convolutional neural network. Then, a fast tracker based on the KCF algorithm is established for each target by weighted fusion of the tracking results of the three features to predict the motion state of the target. In addition, in order to effectively reduce the number of fragmented trajectories, this algorithm associates the trajectories step by step through the confidence of tracklets, and uses the online random fern to re-detect the target in the case of occlusion. Finally, the scale in the KCF algorithm is adaptively updated by using the associated successful detection information. Experimental results illustrate that the proposed algorithm displays powerful and efficient tracking performance under various complicated conditions compared with the existing excellent algorithms.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3788/lop55.091502

所属栏目:机器视觉

收稿日期:2018-03-21

修改稿日期:2018-04-07

网络出版日期:2018-04-09

作者单位    点击查看

周海英:中北大学大数据学院, 山西 太原 030051
杨阳:中北大学大数据学院, 山西 太原 030051
王守义:中北大学大数据学院, 山西 太原 030051

联系人作者:杨阳(1450518130@qq.com)

【1】Li S J, Fan X, Zhu B, et al. A method for small infrared targets detection based on the technology of motion blur recovery[J]. Acta Optica Sinica, 2017, 37(6): 0610001.
李思俭, 樊祥, 朱斌, 等. 基于运动模糊复原技术的红外弱小目标检测方法[J]. 光学学报, 2017, 37(6): 0610001.

【2】Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

【3】Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector[C]∥European Conference on Computer Vision, 2016:21-37.

【4】Li A D, Lin Z P, An W, et al. Infrared small target detection in compressive domain based on self-adaptive parameter configuration[J]. Chinese Journal of Lasers, 2015, 42(10): 1008003.
李安冬, 林再平, 安玮, 等. 基于自适应改进的压缩域红外弱小目标检测[J]. 中国激光, 2015, 42(10): 1008003.

【5】Zhang L J, Zhou Z P. An improved discrete-continuous energy minimization for multi-target tracking[J]. Laser & Optoelectronics Progress, 2017, 54(11): 111502.
张丽娟, 周治平. 一种改进的离散连续能量最小化多目标跟踪[J]. 激光与光电子学进展, 2017, 54(11): 111502.

【6】Kim C, Li F, Ciptadi A, et al. Multiple hypothesis tracking revisited: blending in modern appearance model[C]∥IEEE International Conference on Computer Vision, 2015: 4696-4704.

【7】Milan A, Schindler K, Roth S. Detection- and trajectory-level exclusion in multiple object tracking[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2013: 3682-3689.

【8】Bae S H, Yoon K.Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014: 1218-1225.

【9】Dicle C, Camps O I, Sznaier M. The way they move: tracking multiple targets with similar appearance[C]∥IEEE International Conference on Computer Vision, 2013: 2304-2311.

【10】Yoon J H, Yang M, Lim J, et al. Bayesian multi-object tracking using motion context from multiple objects[C]∥IEEE Conference on Applications of Computer Vision, 2015: 33-40.

【11】Yu F, Li W, Li Q, et al. POI: multiple object tracking with high performance detection and appearance feature[C]∥European Conference on Computer Vision, 2016: 36-42.

【12】Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015: 1-9.

【13】Kuhn H W. The Hungarian method for the assignment problem[J]. Naval Research Logistics, 2004, 52(1): 7-21.

【14】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.

【15】Yang Y, Zhou H Y,Wang S Y. Saliency tracking algorithm based on fusing multiple features[J]. Science Technology and Engineering, 2017, 17(26): 74-80.
杨阳, 周海英, 王守义. 基于多特征融合的显著性跟踪算法[J]. 科学技术与工程, 2017, 17(26): 74-80.

【16】zuysal M, Fua P, Lepetit V. Fast keypoint recognition in ten lines of code[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007: 1-8.

【17】Milan A, Lealtaixe L, Reid I D, et al. MOT16: a benchmark for multi-object tracking[EB/OL]. [2018-03-20]https:∥arxiv.org/pdf/1603.00831.pdf.

【18】Geiger A, Lauer M, Wojek C, et al. 3D traffic scene understanding from movable platforms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(5): 1012-1025.

【19】Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.

【20】Choi W. Near-online multi-target tracking with aggregated local flow descriptor[C]∥IEEE International Conference on Computer Vision, 2015: 3029-3037.

【21】Bewley A, Ge Z, Ott L, et al. Simple online and realtime tracking[C]. IEEE International Conference on Image Processing, 2016: 3464-3468.

引用该论文

Zhou Haiying,Yang Yang,Wang Shouyi. Multiple Object Tracking Algorithm Based on Kernel Correlation Filter[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091502

周海英,杨阳,王守义. 基于核相关滤波器的多目标跟踪算法[J]. 激光与光电子学进展, 2018, 55(9): 091502

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF