Collaborative Tracking Method in Multi-Camera System

doi:10.1007/s12204-020-2188-x

Abstract

Abstract: Visual tracking has been a popular task in computer vision in recent years, especially for long-term tracking. A novel object tracking framework is proposed in this paper. For surveillance cameras with overlapping areas, the target area is divided into several regions corresponding to each camera, and a simple re-matching method is used by matching the colors according to the segmented parts. For surveillance cameras without overlapping areas, a time estimation model is employed for continuously tracking objects in different fields of view (FoVs). A demonstration system for collaborative tracking in real time situation is realized finally. The experimental results show that compared with current popular algorithms, the proposed approach has good effect in accuracy and computation time for the application of continuously tracking the pedestrians.

Key words: multi-camera system| surveillance video| visual tracking| re-matching

摘要： Visual tracking has been a popular task in computer vision in recent years, especially for long-term tracking. A novel object tracking framework is proposed in this paper. For surveillance cameras with overlapping areas, the target area is divided into several regions corresponding to each camera, and a simple re-matching method is used by matching the colors according to the segmented parts. For surveillance cameras without overlapping areas, a time estimation model is employed for continuously tracking objects in different fields of view (FoVs). A demonstration system for collaborative tracking in real time situation is realized finally. The experimental results show that compared with current popular algorithms, the proposed approach has good effect in accuracy and computation time for the application of continuously tracking the pedestrians.

关键词: multi-camera system| surveillance video| visual tracking| re-matching

CLC Number:

TN 911.73

ZHOU Zhipeng, YIN Dong, DING Jinwen, LUO Yuhao, YUAN Mingyue, ZHU Chengfeng. Collaborative Tracking Method in Multi-Camera System[J]. J Shanghai Jiaotong Univ Sci, 2020, 25(6): 802-810.

References 33

[1]	DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE, 2005: 886-893.
[2]	FELZENSZWALB P, MCALLESTER D, RAMANAN D. A discriminatively trained, multiscale, deformable part model [C]//2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA:IEEE, 2008: 1-8.
[3]	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, 2015, 39(6):16880617.
[4]	REDMON J, FARHADI A. YOLO9000: Better, faster, stronger [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI,USA: IEEE, 2017: 7263-7271.
[5]	WANG H Y, YAN Y X, HUA J, et al. Pedestrian recognition in multi-camera networks using multilevel important salient feature and multicategory incremental learning [J]. Pattern Recognition, 2017, 67: 340-352.
[6]	ZHOU Z, WANG Y, TEOH E K. A framework for semantic people description in multi-camera surveillance systems [J]. Image and Vision Computing, 2016, 46:29-46.
[7]	ZHENG L, HUANG Y J, LU H C, et al.Pose invariant embedding for deep person reidentification[EB/OL]. (2017-01-27) [2018-01-15].https://arxiv.org/abs/1701.07732v1.
[8]	ZHAO H Y, TIAN M Q, SUN S Y, et al. Spindle net: Person re-identification with human body region guided feature decomposition and fusion [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 1077-1085.
[9]	YU H X, WU A C, ZHENG W S. Cross-view asymmetric metric learning for unsupervised person reidentification [C]//2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017:994-1002.
[10]	SENNA P, DRUMMOND I N, BASTOS G S.Real-time ensemble-based tracker with Kalman filter[C]//2017 30th SIBGRAPI Conference on Graphics,Patterns and Images (SIBGRAPI). Niter′oi, Brazil:IEEE, 2017: 338-344.
[11]	CAI Z Q, HU S G, SHI Y K, et al. Multiple human tracking based on distributed collaborative cameras[J]. Multimedia Tools and Applications, 2017, 76(2):1941-1957.
[12]	HUANG W X, HU R M, LIANG C, et al. Camera network based person re-identification by leveraging spatial-temporal constraint and multiple cameras relations [C]//International Conference on Multimedia Modeling. Switzerland: Springer, 2016: 174-186.
[13]	LI Q, SUN Z X, CHEN S C, et al. Dynamic node selection in camera networks based on approximate reinforcement learning [J]. Multimedia Tools and Applications,2016, 75(24): 17393-17419.
[14]	BHUVANA V P, SCHRANZ M, REGAZZONI C S, et al. Multi-camera object tracking using surprisal observations in visual sensor networks [J]. EURASIP Journal on Advances in Signal Processing, 2016, 2016: 50.
[15]	XIAO J, LIU Z, YANG H, et al. The invariant featuresbased target tracking across multiple cameras [J]. Multimedia Tools and Applications, 2017, 76(10): 12165-12179.
[16]	YOO H, KIM K, BYEON M, et al. Online scheme for multiple camera multiple target tracking based on multiple hypothesis tracking [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017,27(3): 454-469.
[17]	WAN J Q, LI A C. Multiple people tracking using camera networks with overlapping views [J]. International Journal of Distributed Sensor Networks, 2015, 11(1):591067.
[18]	MOTIIAN S, SIYAHJANI F, ALMOHSEN R, et al.Online human interaction detection and recognition with multiple cameras [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(3):649-663.
[19]	ARULAMPALAM M S, MASKELL S, GORDON N, et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking [J]. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188.
[20]	VOJIR T, NOSKOVA J, MATAS J. Robust scaleadaptive mean-shift for tracking [J]. Pattern Recognition Letters, 2014, 49: 250-258.
[21]	SENNA P, DRUMMOND I N, BASTOS G S.Real-time ensemble-based tracker with Kalman filter[C]//201730th SIBGRAPI Conference on Graphics,Patterns and Images (SIBGRAPI). Niter′oi, Brazil:IEEE, 2017: 338-344.
[22]	CHOPRA S, HADSELL R, LECUN Y. Learning a similarity metric discriminatively, with application to face verification [C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego, USA: IEEE, 2005: 539-546.
[23]	BERTINETTO L, VALMADRE J, GOLODETZ S, et al. Staple: Complementary learners for real-time tracking [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE,2016: 1401-1409.
[24]	COMANICIU D, RAMESH V, MEER P. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.
[25]	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.
[26]	XIEWF, PU F L, CHENG Y. Cooperation of multiple non-overlapping surveillance videos for mobile target tracking [J]. Computer Engineering and Design, 2016,37(3): 809-813.
[27]	XIAO J, LIU Z, YANG H, et al. The invariant featuresbased target tracking across multiple cameras [J]. Multimedia Tools and Applications, 2017, 76(10): 12165-12179.
[28]	DU W, PIATER J. Multi-camera people tracking by collaborative particle filters and principal axis-based integration [C]//8th Asian Conference on Computer Vision. Tokyo, Japan: Springer, 2007: 365-374.
[29]	LIN D T, HUANG K Y. Collaborative pedestrian tracking and data fusion with multiple cameras [J].IEEE Transactions on Information Forensics and Security,2011, 6(4): 1432-1444.
[30]	BLACK J, ELLIS T, ROSIN P. Multi view image surveillance and tracking [C]// Proceedings Workshop on Motion and Video Computing (MOTION 2002).Orlando, FL, USA: IEEE, 2002: 169-174.
[31]	DANELLJAN M, H¨AGER G, KHAN F S, et al.Accurate scale estimation for robust visual tracking[C]//British Machine Vision Conference. Nottingham,UK: BMVA Press, 2014: 1-9.
[32]	DANELLJAN M, KHAN F S, FELSBERG M, et al.Adaptive color attributes for real-time visual tracking [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, Ohio, USA:IEEE, 2014: 1090-1097.
[33]	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.