Abstract
A robust MOT (multi-object tracking) is very crucial for computer vision applications such as crowd density estimation and autonomous vehicles. Most of the existing mot approaches perform object tracking in a two task manner such as motion estimation and Re-identification but these approaches pose some drawbacks like the model is not end-to-end trained, the Re-Id required lots of identity switches thus incurred computational overhead and the performance further degrades in complex crowd scenarios. To overcome such drawbacks we are motivated to design an end-to-end trained DNN for MOT. The proposed model utilizes a matching technique that utilizes the relative scale between the boundary boxes and relative position calculates the relative distance between the objects for MOT. To solve the problems, we proposed a matching technique that poses two subtasks to efficiently scale up a single shot DNN tracking approach for an indefinite number of objects in the video frames. The proposed method uses a relative scale and relative position to matching between the detected and targeted objects. The achieved state-of-the-art results of the tasks allow to obtain high accuracy of tracking with detection and surpasses existing state-of-the-art methods by a huge margin on various public datasets.
Similar content being viewed by others
References
Bae SH, Yoon KJ (2018) Confidence-based data association and discriminative deep appearance learning for robust online multi-object tracking. IEEE Trans Pattern Anal Mach Intell 40(3):595–610
Bajracharya M, Moghaddam B, Howard A, Brennan S, Matthies LH (2009) A fast stereo-based system for detecting and tracking pedestrians from a moving vehicle. Int J Rob Res 28(11–12):1466–1485
Bergmann P, Meinhardt T, Leal-Taixe L (2019) Tracking without bells and whistles. Proc. IEEE Int. Conf. Comput. Vis., vol. 2019-Octob, no. October, pp. 941–951
Bernardin K, Stiefelhagen R (2008) Evaluating Multiple Object Tracking Performance : The CLEAR MOT Metrics vol. 2008, 2008
Bewley A, Ge Z, Ott L, Ramos F, Upcroft B (2016) Simple online and realtime tracking. Proc. - Int. Conf. Image Process. ICIP, vol. 2016-Augus, pp. 3464–3468
Butler DJ,Wulff J, Stanley GB, Black MJ (2012) For Optical Flow Evaluation,” pp. 611–625
Chen L, Ai H, Shang C, Zhuang Z, Bai B (2018) Online multi-object tracking with convolutional neural networks. Proc. - Int. Conf. Image Process. ICIP, vol. 2017-Septe, pp. 645–649
Choi W, Savarese S (2010) Multiple target tracking in world coordinate with single, minimally calibrated camera, pp 553–567
Chu P, Fan H, Tan CC, Ling H (2019) Online multi-object tracking with instance-aware tracker and dynamic model refreshment. Proc. - 2019 IEEE Winter Conf. Appl. Comput. Vision, WACV 2019, pp. 161–170
Dash PP, Mishra SK, Sethi J (2012) Kernel based object tracking using color histogram technique 2 fundamentals of object tracking in video sequences. 2(4):28–35
Dicle C, Camps OI, Sznaier M (2013) The way they move: Tracking multiple targets with similar appearance. Proc. IEEE Int. Conf. Comput. Vis., pp 2304–2311
Fang K, Xiang Y, Li X, Savarese S (2018) Recurrent Autoregressive Networks for Online Multi-object Tracking. Proc. - 2018 IEEE Winter Conf. Appl. Comput. Vision, WACV 2018, vol. 2018-Janua, pp. 466–475
Feng W, Hu Z, Wu W, Yan J, Ouyang W (2019) Multi-object tracking with multiple cues and switcher-aware classification. arXiv, no. c
Fragkiadaki K, Zhang W, Zhang G, Shi J (2012) Two-granularity tracking: mediating trajectory and detection graphs for tracking under occlusions. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol 7576 LNCS, no. PART 5, pp 552–565
Fulkerson B, Vedaldi A, Soatto S (2008) Localizing objects with smart dictionaries. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol 5302 LNCS, no PART 1, pp 179–192
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol 2016-Decem, pp 770–778
Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Kalman RE (1960) A new approach to linear filtering and prediction problems. J Fluids Eng Trans ASME 82(1):35–45
Kampker A, Sefati M, Abdul Rachman AS, Kreisköther K, Campoy P (2018) Towards multi-object detection and tracking in urban scenario under uncertainties. VEHITS 2018 - Proc 4th Int Conf Veh Technol Intell Transp Syst vol 2018, no. Vehits 2018, pp 156–167. https://doi.org/10.5220/0006706101560167
Keuper M, Tang S, Andres B, Brox T, Schiele B (2018) Motion segmentation & multiple object tracking by correlation co-clustering. IEEE Trans Pattern Anal Mach Intell 8828(c):1–13
Kim C, Li F, Rehg JM (2018) Multi-object tracking with neural gating using bilinear LSTM, vol 11212 LNCS. Springer International Publishing
Kuhn HW (2005) The Hungarian method for the assignment problem. Nav Res Logist 52(1):7–21
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Mahmoudi N (2018) Multi-target tracking using CNN-based features : CNNMTT. https://doi.org/10.1007/s11042-018-6467-6
Milan A, Schindler K, Roth S (2016) Multi-target tracking by discrete-continuous energy minimization. IEEE Trans Pattern Anal Mach Intell 38(10):2054–2068
Milan A, Rezatofighi SH, Dick A, Reid I, Schindler K (2017) Online multi-target tracking using recurrent neural networks. 31st AAAI Conf. Artif Intell AAAI 2017, pp 4225–4232
Mitzel D (2012) Taking mobile multi-object tracking to the next level. Eccv
Pang B, Li Y, Zhang Y, Li M, Lu C (2020) Tubetk: Adopting tubes to track multi-object in a one-step training model. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, pp 6307–6317
Pellegrini S, Ess A, Schindler K, Van Gool L (2009) You ’ ll never walk alone : modeling social behavior for multi-target tracking, no. Iccv, pp 261–268. https://doi.org/10.1109/ICCV.2009.5459260
Peng J et al (2020) Chained-Tracker: Chaining paired attentive regression results for end-to-end joint multiple-object detection and tracking
Qin Z, Shelton CR (2016) Social grouping for multi-target tracking and head pose estimation in video. IEEE Trans Pattern Anal Mach Intell 38(10):2082–2095
Roth M, Bauml M, Nevatia R, Stiefelhagen R (2012) Robust multi-pose face tracking by multi-stage tracklet association. Proc. - Int. Conf. Pattern Recognit., pp 1012–1016
Sadeghian A, Alahi A,Savarese S (2017) Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies. Proc IEEE Int Conf Comput Vis, vol 2017-Octob, pp 300–311
Sanchez-Matilla R, Poiesi F, Cavallaro A (2016) Online multi-target tracking with strong and weak detections. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol 9914 LNCS, pp 84–99
Sun SJ, Akhtar N, Song HS, Mian A, Shah M (2018) Deep affinity network for multiple object tracking. arXiv 13(9):1–15
Wang Z, Zheng L, Liu Y, Wang S (2019) Towards real-time multi-object tracking
Wojke N, Bewley A, Paulus D (2018) Simple online and realtime tracking with a deep association metric. Proc - Int Conf Image Process ICIP, vol 2017-September, pp 3645–3649
Wu Z, Thangali A, Sclaroff S, Betke M (1927) Coupling detection and data association for multiple object tracking. https://doi.org/10.1109/CVPR.2012.6247896
Wu B, Wan A, Yue X, Keutzer K (2018) SqueezeSeg: convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR Point Cloud. Proc - IEEE Int Conf Robot Autom, pp 1887–1893
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 Recognit 94:25–34
Xiang Y, Alahi A, Savarese S (2015) Learning to track: Online multi-object tracking by decision making. Proc IEEE Int Conf Comput Vis, vol. 2015 Inter, pp 4705–4713. https://doi.org/10.1109/ICCV.2015.534
Xie C, Xiang Y, Harchaoui Z, Fox D Object discovery in videos as foreground motion clustering
Xu J, Cao Y, Zhang Z, Hu H (2019) Spatial-temporal relation networks for multi-object tracking. Proc IEEE Int Conf Comput Vis 2019:3987–3997
Yang B, Nevatia R (2012) An online learned CRF model for multi-target tracking. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp 2034–2041. https://doi.org/10.1109/CVPR.2012.6247907
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
Yoon YC, Boragule A, Song YM, Yoon K, Jeon M (2018) Online multi-object tracking with historical appearance matching and scene adaptive detection filtering
Yu F, Li W, Li Q, Liu Y, Shi X, Yan J (2016) POI: Multiple object tracking with high performance detection and appearance feature. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol 9914 LNCS, pp 36–42
Zhang J et al (2020) Multiple object tracking by flowing and fusing
Zhang Y, Wang C, Wang X, Zeng W, Liu W (2020) FairMOT: on the fairness of detection and re-identification in multiple object tracking, pp 1–13
Zhao Q, Road WX (2018) MULTI-OBJECT TRACKING USING ONLINE METRIC LEARNING WITH LONG SHORT-TERM MEMORY Xingyu Wan Jinjun Wang Zhifeng Kong Xi’an Jiaotong University Institute of Artificial Intelligence and Robotics No . 1 Tanhu 2nd Road, Canglong island, Jiangxia district 2018 25th IEEE Int. Conf. Image Process, pp 788–792. https://doi.org/10.1109/ICIP.2018.8451174
Zhou Z, Xing J, Zhang M, Hu W (2018) Online multi-target tracking with tensor-based high-order graph matching. Proc Int Conf Pattern Recognit 2018:1809–1814. https://doi.org/10.1109/ICPR.2018.8545450
Zhou X, Koltun V, Krähenbühl P, Austin UT, Labs I (2020) Tracking objects as points
Zhu J, Yang H, Liu N, Kim M, Zhang W, Yang MH (2018) Online multi-object tracking with dual matching attention networks. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol 11209 LNCS, pp 379–396
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.
Rights and permissions
About this article
Cite this article
Singh, D., Srivastava, R. An end to end trained hybrid CNN model for multi-object tracking. Multimed Tools Appl 81, 42209–42221 (2022). https://doi.org/10.1007/s11042-021-11463-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11463-1