Multi-target Tracking Algorithm Based on Motion Information Optimized Correl-ation Filtering

doi:10.3778/j.issn.1673-9418.2005037

Abstract

Abstract:

In multi-target tracking tasks combined with detector detection information, missing detections often lead to some targets missed, target identity tag conversion, etc., thereby reducing tracking accuracy. To solve this problem, a multi-target tracking algorithm based on motion information optimization and correlation filter is proposed. After obtaining target detection information, kernelized correlation filter (KCF) is used to track target, and the target??s motion information and image information are integrated to handle the problem of missing tracking due to inaccu-rate detection, reducing the fragmented trajectory. At the same time, the smoothing constraint of confidence map is introduced on the basis of KCF to evaluate occlusion degree of targets, which achieves the adaptive update of target template in KCF and deals with the problem of template pollution caused by occlusion. Finally, the experimental results on the MOT Challenge MOT17 data set show that compared with the traditional detection and tracking algor-ithm, high-speed tracking-by-detection without using image information (IOU17), multiple object tracking accuracy (MOTA) of proposed algorithm is improved by 2.43%, and it has better stability and accuracy.

Key words: correlation filter, detection and tracking, smoothing filtering, template update

摘要：

在结合检测器检测信息的多目标跟踪任务中，目标漏检通常会导致目标漏跟，增加目标身份标签变换等问题，从而降低跟踪精度。针对该问题，提出了一种运动信息优化相关滤波的多目标跟踪算法。该算法在得到目标的检测信息后，采用核相关滤波（KCF）对目标进行跟踪，并融入目标的运动信息和图像信息，以处理检测器结果不精确，出现大量漏跟失跟问题，减少碎片化的轨迹。同时在核相关滤波的基础上引入置信图的平滑约束来评估目标被遮挡程度，实现核相关滤波中目标模板的自适应更新，处理目标由于遮挡而产生模板污染问题。最终在MOT Challenge的MOT17数据集上的实验结果表明，与传统的检测跟踪算法IOU17相比，在多目标跟踪正确度（MOTA）指标上提高了2.43%，具有更好的稳定性和精确度。

关键词: 相关滤波, 检测跟踪, 平滑滤波, 模板更新

MIAO Jiani, YANG Jinlong, CHENG Xiaoxue, GE Hongwei. Multi-target Tracking Algorithm Based on Motion Information Optimized Correl-ation Filtering[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(7): 1310-1321.

缪佳妮, 杨金龙, 程小雪, 葛洪伟. 运动信息优化相关滤波的多目标跟踪算法[J]. 计算机科学与探索, 2021, 15(7): 1310-1321.

References

[1] FU Z Y, FENG P, ANGELINI F, et al. Particle PHD filter based multiple human tracking using online group-structured dictionary learning[J]. IEEE Access, 2018(6): 14764-14778.
[2] KUTSCHBACH T, BOCHINSKI E, EISELEIN V, et al. Se-quential sensor fusion combining probability hypothesis den-sity and kernelized correlation filters for multi-object trac-king in video data[C]//Proceedings of the 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, Lecce, Aug 29-Sep 1, 2017. Washington: IEEE Computer Society, 2017: 1-5.
[3] FU Z Y, ANGELINI F, CHAMBERS J, et al. Multi-level co-operative fusion of GM-PHD filters for online multiple hu-man tracking[J]. IEEE Transactions on Multimedia, 2019, 21(9): 2277-2291.
[4] HENSCHEL R, LEAL-TAIXé L, CREMERS D, et al. Fusion of head and full-body detectors for multi-object tracking[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 1428-1437.
[5] FU Z Y, NAQVI S M, CHAMBERS J A. Collaborative de-tector fusion of data-driven PHD filter for online multiple human tracking[C]//Proceedings of the 21st International Conference on Information Fusion, Cambridge, Jul 10-13, 2018. Piscataway: IEEE, 2018: 1976-1981.
[6] FU Z Y, ANGELINI F, NAQVI S M, et al. GM-PHD filter based online multiple human tracking using deep discrimina-tive correlation matching[C]//Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Apr 15-20, 2018. Piscataway: IEEE, 2018: 4299-4303.
[7] YANG J L, TANG Y, ZHANG G N. Visual multi-object track-ing using convolution feature and multi-Bernoulli filter[J]. Journal of Frontiers of Computer Science and Technology, 2019, 13(11): 1945-1957.
杨金龙, 汤玉, 张光南. 卷积特征多伯努利视频多目标跟踪算法[J]. 计算机科学与探索, 2019, 13(11): 1945-1957.
[8] YANG J L, CHENG X X, MIAO J N, et al. Detection opti-mized multi-Bernoulli algorithm for visual multi-target track-ing[J]. Journal of Frontiers of Computer Science and Tech-nology, 2020, 14(10): 1762-1775.
杨金龙, 程小雪, 缪佳妮, 等. 检测优化的多伯努利视频多目标跟踪算法[J]. 计算机科学与探索, 2020, 14(10): 1762-1775.
[9] KIM Y, KANG B N, KIM D. SAN: learning relationship be-tween convolutional features for multi-scale object detection [C]//LNCS 11209: Proceedings of the 15th European Con-ference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 328-343.
[10] DAI J F, LI Y, HE K M, et al. R-FCN: object detection via region-based fully convolutional networks[C]//Proceedings of the 30th Annual Conference on Neural Information Processing Systems, Barcelona, Dec 5-10, 2016. Red Hook: Curran Associates, 2016: 379-387.
[11] REN S Q, HE K M, GIRSHICK R B, et al. Faster R-CNN: towards real-time object detection with region proposal net-works[J]. IEEE Transactions on Pattern Analysis and Mach-ine Intelligence, 2017, 39(6): 1137-1149.
[12] YANG F, CHOI W, LIN Y Q. Exploit all the layers: fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifiers[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Re-cognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 2129-2137.
[13] JOSEPH R, ALI F. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vi-sion and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 6517-6525.
[14] FENG W T, HU Z H, WU W, et al. Multi-object tracking with multiple cues and switcher-aware classification[J]. arXiv: 1901.06129, 2019.
[15] BERGMANN P, MEINHARDT T. Tracking without bells and whistles[J]. arXiv:1903.05625, 2019.
[16] BOCHINSKI E, EISELEIN V, SIKORA T. High-speed tracking- by-detection without using image information[C]//Proceed-ings of the 2017 14th International Conference on Advanced Video and Signal Based Surveillance, Lecce, Aug 29-Sep 1, 2017. Washington: IEEE Computer Society, 2017: 1-6.
[17] BOCHINSKI E, SENST T, SIKORA T, et al. Extending IOU based multi-object tracking by visual information[C]//Pro-ceedings of the 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance, Auck-land, Nov 27-30, 2018. Piscataway: IEEE, 2018: 1-6.
[18] SANCHEZ-MATILLA R, POIESI F, CAVALLARO A. On-line multi-target tracking with strong and weak detections[C]//LNCS 9914: Proceedings of the 14th European Con-ference on Computer Vision, Amsterdam, Oct 11-14, 2016. Cham: Springer, 2016: 84-99.
[19] PAUL V, MICHAEL K, ALJOSA O, et al. MOTS: multi-object tracking and segmentation[J]. arXiv:1902.03604, 2019.
[20] XIANG Y, ALAHI A, SILVIO S. Learning to track: online multi-object tracking by decision making[C]//Proceedings of the 2015 IEEE International Conference on Computer Vi-sion, Santiago, Dec 7-13, 2015. Washington: IEEE Computer Society, 2015: 4705-4713.
[21] 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, 2014, 37(3): 583-596.
[22] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the 2005 IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition, San Diego, Jun 20-25, 2005. Washington: IEEE Computer Society, 2005: 886-893.
[23] MARTIN D, GUSTAV H, FAHAD S K, et al. Accurate scale estimation for robust visual tracking[C]//Proceedings of the 25th British Machine Vision Conference, Nottingham, Sep 1-5, 2014. BMVA Press, 2014: 1-11.
[24] HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploi-ting the circulant structure of tracking-by-detection with kernels[C]//LNCS 7575: Proceedings of the 12th European Conference on Computer Vision, Florence, Oct 7-13, 2012. Berlin, Heidelberg: Springer, 2012: 702-715.
[25] DANELLJAN M, H?GER G, KHAN F S, et al. Discrimin-ative scale space tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(8): 1561-1575.
[26] LIU T, WANG G, YANG Q X. Real-time part-based visual tracking via adaptive correlation filters[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, Jun 7-12, 2015. Washington: IEEE Com-puter Society, 2015: 4902-4912.
[27] SUN S J, AKHTAR N, SONG H S, et al. Deep affinity net-work for multiple object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(1): 104-119.
[28] WOJKE N, BEWLEY A, PAULUS D. Simple online and real-time tracking with a deep association metric[C]//Proceed-ings of the 2017 IEEE International Conference on Image Processing, Beijing, Sep 17-20, 2017. Piscataway: IEEE, 2017: 3645-3649.
[29] BEWLEY A, GE Z Y, OTT L, et al. Simple online and real-time tracking[C]//Proceedings of the 2016 IEEE Interna-tional Conference on Image Processing, Phoenix, Sep 25-28, 2016. Piscataway: IEEE, 2016: 3464-3468.
[30] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D A, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.
[31] ANTON M, LAURA L, IAN R, et al. MOT16: a benchmark for multi-object tracking[J]. arXiv:1603.00831, 2016.