Eﬃcient Online Vehicle Tracking for Real–Virtual Mapping Systems

doi:10.1007/s12204-021-2349-6

摘要/Abstract

Abstract: Multi-object tracking is a vital problem as many applications require better tracking approaches. Although learning-based detectors are becoming extremely powerful, there are few tracking methods designed to work with them in real time. We explored an effcient fiexible online vehicle tracking-by-detection framework suitable for real–virtual mapping systems, which combines a non-recursive temporal window search with delayed output and produces stable trajectories despite noisy detection responses. Its computation speed meets the real-time requirements, whereas its performance is comparable with that of state-of-the-art online trackers on the DETRAC dataset. The trajectories from our approach also contain the target class and color information important for virtual vehicle motion reconstruction.

中图分类号:

TP 274

. [J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 598-606.

CHEN Jiacheng (陈佳诚), LI Lin(李霖), YANG Xubo (杨旭波). Eﬃcient Online Vehicle Tracking for Real–Virtual Mapping Systems[J]. J Shanghai Jiaotong Univ Sci, 2021, 26(5): 598-606.

参考文献 35

[1]	BEWLEY A, GE Z Y, OTT L, et al. Simple online and realtime tracking [C]//2016 IEEE International Conference on Image Processing (ICIP). Phoenix, AZ: IEEE, 2016: 3464-3468.
[2]	HUANG C, WU B, NEVATIA R. Robust object tracking by hierarchical association of detection re-sponses [C]//European Conference on Computer Vi-sion. Berlin, Heidelberg: Springer, 2008: 788-801.
[3]	BREITENSTEIN M D, REICHLIN F, LEIBE B, et al. Robust tracking-by-detection using a detector con?-dence particle ?lter [C]//2009 IEEE 12th International Conference on Computer Vision. Kyoto: IEEE, 2009: 1515-1522.
[4]	ANDRIYENKO A, SCHINDLER K. Globally op-timal multi-target tracking on a hexagonal lat-tice [C]//European Conference on Computer Vision. Berlin, Heidelberg: Springer, 2010: 466-479.
[5]	BERCLAZ J, FLEURET F, TURETKEN E, et al. Multiple object tracking using K-shortest paths opti-mization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(9): 1806-1819.
[6]	PIRSIAVASH H, RAMANAN D, FOWLKES C C. Globally-optimal greedy algorithms for tracking a vari-able number of objects [C]//2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Colorado Springs, CO: IEEE, 2011: 1201-1208. [7] ANDRIYENKO A, SCHINDLER K. Multi-target tracking by continuous energy minimization [C]//2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Colorado Springs, CO: IEEE, 2011: 1265-1272.
[8]	MILAN A, ROTH S, SCHINDLER K. Continuous en-ergy minimization for multitarget tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intel-ligence, 2014, 36(1): 58-72.
[9]	LEE B, ERDENEE E, JIN S, et al. Multi-class multi-object tracking using changing point detec-tion [C]//European Conference on Computer Vision. Cham: Springer, 2016: 68-83.
[10]	BENFOLD B, REID I. Stable multi-target tracking in real-time surveillance video [C]//2011 IEEE Con-ference on Computer Vision and Pattern Recognition (CVPR). Colorado Springs, CO: IEEE, 2011: 3457-3464.
[11]	BREITENSTEIN M D, REICHLIN F, LEIBE B, et al. Online multiperson tracking-by-detection from a single, uncalibrated camera [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(9): 1820-1833.
[12]	BAE S H, YOON K J. Robust online multi-object tracking based on tracklet con?dence and online dis-criminative appearance learning [C]//2014 IEEE Con-ference on Computer Vision and Pattern Recognition (CVPR). Columbus, OH: IEEE, 2014: 1218-1225.
[13]	XIANG Y, ALAHI A, SAVARESE S. Learning to track: Online multi-object tracking by decision mak-ing [C]//2015 IEEE International Conference on Com-puter Vision (ICCV ). Santiago: IEEE, 2015: 4705-4713.
[14]	MILANA,REZATOFIGHIS H,DICK A,et al. Online multi-target tracking using recurrent neural networks [C]//Thirty-First AAAI Conference on Arti?cial Intel-ligence (AAAI-17 ). San Francisco California: AAAI, 2017: 4225-4232.
[15]	BOCHINSKI E, EISELEIN V, SIKORA T. High-speed tracking-by-detection without using image information [C]//2017 14th IEEE International Conference on Ad-vanced Video and Signal Based Surveillance (AVSS ). Lecce: IEEE, 2017: 1-6.
[16]	BOCHINSKI E, SENST T, SIKORA T. Extending IOU based multi-object tracking by visual information [C]//2018 15th IEEE International Conference on Ad-vanced Video and Signal Based Surveillance (AVSS ). Auckland: IEEE, 2018: 1-6.
[17]	WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric [C]//2017 IEEE International Conference on Image Processing (ICIP). Beijing: IEEE, 2017: 3645-3649.
[18]	WEN L Y, DU D W, CAI Z W, et al. UA-DETRAC: A new benchmark and protocol for multi-object de-tection and tracking [J]. Computer Vision and Image Understanding, 2020, 193: 102907. [19] LYU S W, CHANG M C, DU D W, et al. UA-DETRAC 2018: Report of AVSS2018 & IWT4S chal-lenge on advanced tra?c monitoring [C]//2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS ). Auckland: IEEE, 2018: 1-6.
[20]	NAPHADE M, ANASTASIU D C, SHARMA A, et al. The NVIDIA AI City challenge [C]//2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, In-ternet of People and Smart City Innovation. San Fran-cisco, CA: IEEE, 2017: 1-6.
[21]	NAPHADE M, CHANG M C, SHARMA A, et al. The 2018 NVIDIA AI City challenge [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recogni-tion Workshops (CVPRW ). Salt Lake City, UT: IEEE, 2018: 53-537.
[22]	NAPHADE M, WANG S, ANASTASIU D C, et al. The 4th AI City challenge [C]//2020 IEEE/CVF Con-ference on Computer Vision and Pattern Recogni-tion Workshops (CVPRW ). Seattle, WA: IEEE, 2020: 2665-2674.
[23]	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Uni?ed, real-time object detection [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV: IEEE, 2016: 779-788. [25] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector [M]//Computer vision–ECCV 2016. Cham: Springer International Publishing, 2016:
21	- 37.
[26]	OH S, RUSSELL S, SASTRY S. Markov chain Monte Carlo data association for general multiple-target tracking problems [C]// 2004 43rd IEEE Confer-ence on Decision and Control (CDC)(IEEE Cat. No.04CH37601 ). Nassau: IEEE, 2004: 735-742. challenge 2018 [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW ). Salt Lake City, UT: IEEE, 2018: 77-777.
[28]	DUBSK ′AM,HEROUTA,JUR′ANEK R, et al. Fully automatic roadside camera calibration for traf-?c surveillance [J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(3): 1162-1171.
[29]	DUBSKA′ M, HEROUT A, SOCHOR J. Automatic camera calibration for tra?c understanding [EB/OL].[2021-02-08]. http://dx.doi.org/10.5244/C.28.42.
[30]	TANG Z, WANG G A, XIAO H, et al. Single-camera and inter-camera vehicle tracking and 3D speed esti-mation based on fusion of visual and semantic features [C]//2018 IEEE/CVF Conference on Computer Vi-sion and Pattern Recognition Workshops (CVPRW ). Salt Lake City, UT: IEEE, 2018: 108-1087.
[31]	HUA S, KAPOOR M, ANASTASIU D C. Vehicle tracking and speed estimation from tra?c videos [C]//2018 IEEE/CVF Conference on Computer Vi-sion and Pattern Recognition Workshops (CVPRW ). Salt Lake City, UT: IEEE, 2018: 153-1537.
[32]	ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: Faster and better learning for bounding box re-gression [J]. Proceedings of the AAAI Conference on Arti?cial Intelligence, 2020, 34(7): 12993-13000.
[33]	BERNARDIN K, STIEFELHAGEN R. Evaluating multiple object tracking performance: The CLEAR MOT metrics [J]. EURASIP Journal on Image and Video Processing, 2008, 2008: 1-10.
[34]	WANG L, LU Y, WANG H, et al. Evolving boxes for fast vehicle detection [C]//2017 IEEE International Conference on Multimedia and Expo (ICME ). Hong Kong: IEEE, 2017: 1135-1140.
[35]	HEKM,GKIOXARIG,DOLLA′ R P, et al. Mask
	R- CNN [C]//2017 IEEE International Conference on Computer Vision (ICCV ). Venice: IEEE, 2017: 2980-2988.