Abstract
We propose a novel online multiple object tracker taking structure information into account. State-of-the-art multi-object tracking (MOT) approaches commonly focus on discriminative appearance features, while neglect in different levels structure information and the core of data association. Addressing this, we design a new tracker fully exploiting structure information and encoding such information into the cost function of the graph matching model. Firstly, a new measurement is proposed to compare the structure similarity of two graphs whose nodes are equal. With this measurement, we define a complete matching which performs association in high efficiency. Secondly, for incomplete matching scenarios, a structure keeper net (SKnet) is designed to adaptively establish the graph for matching. Finally, we conduct extensive experiments on benchmarks including MOT2015 and MOT17. The results demonstrate the competitiveness and practicability of our tracker.
Similar content being viewed by others
Notes
More details about solution could be found in the FGM [55].
Since the global matrix is 30∗30 which is too large to show in the paper, we give the corresponding quantitative results of the examples in the Supplementary Materials.
We also compare the robustness of a few state-of-the-art online trackers with our tracker on MOT17 training sets. For saving space, the results and analyses are shown in Supplementary Materials.
In tracking, GT means the real trajectories of the objects in the video sequence.
Since our local evaluating toolkit does not contain it ,we only show it in the testing comparisons.
References
Touil DE, Terki N, Medouakh S (2018) Learning spatially correlation filters based on convolutional features via PSO algorithm and two combined color spaces for visual tracking. Appl Intell 48:2837–2846
Huang W, Gu J, Ma X, Li Y (2020) End-to-end multitask Siamese network with residual hierarchical attention for real-time object tracking. Appl Intell 50:1908–1921
Kumar A, Walia GS, Sharma K (2020) A novel approach for multi-cue feature fusion for robust object tracking. Appl Intell 50:3201–3218
Li T, Wu P, Ding F, et al. (2020) Parallel dual networks for visual object tracking applied intelligence. https://doi.org/10.1007/s10489-020-01783-4
Parate MR, Satpute VR, Bhurchandi KM (2018) Global-patch-hybrid template-based arbitrary object tracking with integral channel features. Appl Intell 48:300–314
Cao TP, Elton D, Deng G (2012) Fast buffering for FPGA implementation of vision-based object recognition systems. J Real-Time Image Proc 7(3):173–183
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR 2014, pp 580–587
Girshick R (2015) Fast r-cnn. In: ICCV 2015, pp 1440–1448
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR 2016, pp 770–778
Kaushal M, Khehra BS (2017) BBBCO and fuzzy entropy based modified background subtraction algorithm for object detection in videos. Appl Intell 47:1008–1021
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: NIPS 2015, pp 91–99
Bae SH, Yoon KJ (2018) Confidence-based data association and discriminative deep appearance learning for robust online multi-object tracking. PAMI 40(3):595–610
Yang M, Jia Y (2016) Temporal dynamic appearance modeling for online multi-person tracking. Comput Vis Image Underst 153:16–28
Bergmann P, Meinhardt T, Leal-Taixé L (2019) Tracking without bells and whistles. In: ICCV 2019, pp 941–951
Novak CL, Shafer SA (1992) Anatomy of a color histogram. In: CVPR 1992, pp 599–605
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: CVPR 2005, pp 886–893
Choi W (2015) Near-online multi-target tracking with aggregated local flow descriptor. In: ICCV 2015, pp 3029–3037
Henschel R, Zou Y, Rosenhahn B (2019) Multiple people tracking using body and joint detections. In: CVPR 2019 Workshops
Henschel R, Leal-Taixé L, Cremers D, Rosenhahn B (2018) Fusion of head and full-body detectors for multi-object tracking. In: CVPR 2018 Workshops, pp 1428–1437
Xu Y, Osep A, Ban Y, Horaud R, Leal-Taixé L, Alamedapineda X (2020) How To Train Your Deep Multi-Object Tracker. In: CVPR 2020, pp 6787–6796
Andriyenko A, Schindler K (2011) Multi-target tracking by continuous energy minimization. In: CVPR 2011, 2(6), pp 7
Choi W, Savarese S (2010) Multiple target tracking in world coordinate with single, minimally calibrated camera. In: ECCV 2010, pp 553–567
Hong Yoon J, Lee CR, Yang MH, Yoon KJ (2016) Online multi-object tracking via structural constraint event aggregation. In: CVPR 2016, pp 1392–1400
Bochinski E, Eiselein V, Sikora T (2017) High-Speed tracking-by-detection without using image information. In: AVSS 2017, pp 1–6
Leal-Taixé L, Pons-Moll G, Rosenhahn B (2011) Everybody needs somebody: Modeling social and grouping behavior on a linear programming multiple people tracker. In: ICCV 2011 Workshops, pp 120–127
Pellegrini S, Ess A, Schindler K, Van Gool L (2009) You’ll never walk alone: Modeling social behavior for multi-target tracking. In: ICCV 2009, pp 261–268
Scovanner P, Tappen MF (2009) Learning pedestrian dynamics from the real world. In: ICCV 2009, pp 381–388
Yamaguchi K, Berg AC, Ortiz LE, Berg TL (2011) Who are you with and where are you going?. In: CVPR 2011, pp 1345–1352
Fang K, Xiang Y, Li X, Savarese S (2018) Recurrent autoregressive networks for online multi-object tracking. In: WACV 2018, pp 466–475
Kim C, Li F, Rehg JM (2018) Multi-object tracking with neural gating using bilinear lstm. In: ECCV 2018, pp 200–215
Milan A, Rezatofighi SH, Dick AR, Reid ID, Schindler K (2017) Online multi-target tracking using recurrent neural networks. In: AAAI 2017, pp 4225–4232
Sadeghian A, Alahi A, Savarese S (2017) Tracking the untrackable: Learning to track multiple cues with long-term dependencies. In: ICCV 2017, pp 300–311
Yoon YC, Boragule A, Song YM, Yoon K, Jeon M (2018) Online multi-object tracking with historical appearance matching and scene adaptive detection filtering. In: AVSS 2018, pp 1–6
Chu Q, Ouyang W, Li H, Wang X, Liu B, Yu N (2017) Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism. In: ICCV 2017, pp 4846–4855
Leal-Taixé L, Canton-Ferrer C, Schindler K. (2016) Learning by tracking: Siamese CNN for robust target association. In: CVPR 2016 Workshops, pp 33–40
Wang N, Zou Q, Ma Q, et al. (2020) A light tracker for online multiple pedestrian tracking. J Real-Time Image Proc. https://doi.org/10.1007/s11554-020-00962-3
Tang S, Andriluka M, Andres B, Schiele B (2017) Multiple people tracking by lifted multicut and person re-identification. In: CVPR 2017, pp 3539–3548
Brasó G, Leal-Taixe L (2020) Learning a neural solver for multiple object tracking. In: CVPR 2020, pp 6247–6257
Leibe B, Schindler K, Van Gool L (2007) Coupled detection and trajectory estimation for multi-object tracking. In: ICCV 2007, pp 1–8
Keuper M, Tang S, Zhongjie Y, Andres B, Brox T, Schiele B (2016) A multi-cut formulation for joint segmentation and tracking of multiple objects. arXiv:1607.06317
Kim S, Kwak S, Feyereisl J, Han B (2012) Online multi-target tracking by large margin structured learning. In: ACCV 2012, pp 98–111
Bae SH, Yoon KJ (2014) Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. In: CVPR2014, pp 1218–1225
Wang G, Wang Y, Zhang H, Gu R, Hwang JN (2018) Exploit the connectivity: Multi-object tracking with trackletnet. arXiv:1811.07258
Sheng H, Zhang Y, Chen J, Xiong Z, Zhang J (2018) Heterogeneous association graph fusion for target association in multiple object tracking. IEEE Trans Circuits Syst Video Technol 29(11):3269–3280
Yang M, Wu Y, Jia Y (2017) A hybrid data association framework for robust online multi-object tracking. IEEE Trans Image Process 26(12):5667–5679
Kim C, Li F, Ciptadi A, Rehg JM (2015) Multiple hypothesis tracking revisited. In: ICCV 2015, pp 4696–4704
Sheng H, Chen J, Zhang Y, Ke W, Xiong Z, Yu J (2018) Iterative multiple hypothesis tracking with tracklet-level association. IEEE Trans Circuits Syst Video Technol 29(12):3660– 3672
Son J, Baek M, Cho M, Han B (2017) Multi-object tracking with quadruplet convolutional neural networks. In: CVPR 2017, pp 5620–5629
Wang B, Wang L, Shuai B, Zuo Z, Liu T, Luk Chan K, Wang G (2016) Joint learning of convolutional neural networks and temporally constrained metrics for tracklet association. In: CVPR 2016 Workshops, pp 1–8
Shen X, Sui X, Pan K, Tao Y (2016) Adaptive pedestrian tracking via patch-based features and spatial–temporal similarity measurement. Pattern Recogn 53:163–173
Battaglia PW, Hamrick JB, Bapst V, et al. (2018) Relational inductive biases, deep learning, and graph networks. arXiv:1806.01261
Li Y, Gu C, Dullien T, Vinyals O, Kohli P (2019) Graph matching networks for learning the similarity of graph structured objects. arXiv:1904.12787
Yu HX, Wu A, Zheng WS (2020) Unsupervised person re-identification by deep asymmetric metric embedding. PAMI 42(4):956–973
Li J, Liu H (2017) Projective low-rank subspace clustering via learning deep encoder. In: IJCAI 2017, pp 2145–2151
Zhou F, De la Torre F (2012) Factorized graph matching. In: CVPR 2012, pp 127–134
Leal-Taixé L, Milan A, Reid I, Roth S, Schindler K (2015) Motchallenge 2015: Towards a benchmark for multi-target tracking. arXiv:1504.01942
Milan A, Leal-Taixé L, Reid I, Roth S, Schindler K (2016) MOT16: A benchmark for multi-object tracking. arXiv:1603.00831
Dollár P, Appel R, Belongie S, Perona P (2014) Fast feature pyramids for object detection. PAMI 36(8):1532–1545
Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: CVPR 2008, pp 1–8
Yang F, Choi W, Lin Y (2016) Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers. In: CVPR 2016, pp 2129–2137
Vedaldi A, Lenc K (2015) Matconvnet: Convolutional neural networks for matlab. In: Proceedings of the 23rd ACM international conference on Multimedia 2015, pp 689–692
Bernardin K, Stiefelhagen R (2008) Evaluating multiple object tracking performance: The CLEAR MOT metrics. J Image Video Process 2008(1):1–10
Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV workshop on benchmarking multi-target tracking
Munkres J (1957) Algorithms for the assignment and transportation problems. J Soc Ind Appl Math 5(1):32–38
Xu J, Cao Y, Zhang Z, Hu H (2019) Spatial-temporal relation networks for multi-object tracking. In: ICCV 2019, pp 3988–3998
Xiang J, Xu G, Ma C, Hou J (2020) End-to-end learning deep crf models for multi-object tracking. IEEE Transactions on Circuits and Systems for Video Technology
Chen L, Ai H, Shang C, Zhuang Z, Bai B (2017) Online multi-object tracking with convolutional neural networks. In: ICIP 2017, pp 645–649
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: CVPR 2009, pp 248–255
Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: A benchmark. In: ICCV 2015, pp 1116–1124
Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: Deep filter pairing neural network for person re-identification. In: CVPR 2014, pp 152–159
Sanchez-Matilla R, Poiesi F, Cavallaro A (2016) Online multi-target tracking with strong and weak detections. In: ECCV 2016, pp 84–99
Liu Q, Liu B, Wu Y, Li W, Yu N (2019) Real-time online multi-object tracking in compressed domain. IEEE Access 7:76489–76499
Chu P, Ling H (2019) FAMNet: joint learning of feature. In: Affinity and multi-dimensional assignment for online multiple object tracking. arXiv:1904.04989
Chu P, Fan H, Tan CC, Ling H (2019) Online multi-object tracking with instance-aware tracker and dynamic model refreshment. In: WACV 2019, pp 161–170
Sheng H, Hao L, Chen J, Zhang Y, Ke W (2017) Robust local effective matching model for multi-target tracking. In: Pacific Rim conference on multimedia, pp 233–243
Wojke N, Paulus D (2016) Global data association for the probability hypothesis density filter using network flows. In: ICRA 2016, pp 567–572
Mahgoub H, Mostafa K, Wassif KT, Farag I (2017) Multi-target tracking using hierarchical convolutional features and motion cues. International Journal of Advanced Computer Science and Applications, 8(11):217–222
Manen S, Timofte R, Dai D, Van Gool L (2016) Leveraging single for multi-target tracking using a novel trajectory overlap affinity measure. In: WACV 2016, pp 1–9
Wu H, Hu Y, Wang K, Li H, Nie L, Cheng H (2019) Instance-aware representation learning and association for online multi-person tracking. Pattern Recogn 94:25–34
Zhou H, Ouyang W, Cheng J, Wang X, Li H (2018) Deep continuous conditional random fields with asymmetric inter-object constraints for online multi-object tracking. IEEE Trans Circ Syst Video Technol 29(4):1011–1022
Xiang Y, Alahi A, Savarese S (2015) Learning to track: online multi-object tracking by decision making. In: ICCV 2015, pp 4705–4713
Zhou X, Jiang P, Wei Z, Dong H, Wang F (2018) Online multi-object tracking with structural invariance constraint. In: BMVC
Kieritz H, Becker S, Hübner W, Arens M (2016) Online multi-person tracking using integral channel features. In: AVSS 2016, pp 122–130
Maksai A, Fua P (2019) Eliminating exposure bias and metric mismatch in multiple object tracking. In: CVPR 2019, pp 4639–4648
Chen J, Sheng H, Zhang Y, Xiong Z Enhancing detection model for multiple hypothesis tracking. In: CVPR 2017 Workshops, pp 18–27
Yoon K, Gwak J, Song YM, Yoon YC, Jeon MG (2020) OneShotDA: Online multi-object tracker with one-shot-learning-based data association. IEEE Access 8:38060–38072
Fu Z, Angelini F, Chambers J, Naqvi SM (2019) Multi-level cooperative fusion of GM-PHD filters for online multiple human tracking. IEEE Trans Multimed 21(9):2277–2291
Chu Q, Ouyang W, Liu B, Zhu F, Yu N (2020) DASOT: a unified framework integrating data association and single object tracking for online multi-object tracking. Proc AAAI Confer Artif Intell 34(7):10672–10679
Zhu J, Yang H, Liu N, Kim M, Zhang W, Yang MH (2018) Online multi-object tracking with dual matching attention networks. In: ECCV 2018, pp 366–382
Lee SH, Kim MY, Bae SH (2018) Learning discriminative appearance models for online multi-object tracking with appearance discriminability measures. IEEE Access 6:67316–67328
Fu Z, Feng P, Angelini F, Chambers J, Naqvi SM (2018) Particle phd filter based multiple human tracking using online group-structured dictionary learning. IEEE Access 6:14764– 14778
Peng J, Wang T, Lin W, Wang J, See J, Wen S, Ding E (2020) TPM: multiple object tracking with tracklet-plane matching pattern recognition. https://doi.org/10.1016/j.patcog.2020.107480
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Wang, N., Zou, Q., Ma, Q. et al. An online multiple object tracker based on structure keeper net. Appl Intell 51, 8010–8029 (2021). https://doi.org/10.1007/s10489-021-02294-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02294-6