Dynamic visible light positioning based on enhanced visual target tracking

被引:1
作者
Liu, Xiangyu [1 ,2 ]
Hao, Jingyu [3 ]
Guo, Lei [4 ,5 ]
Song, Song [4 ,6 ]
机构
[1] Shenyang Ligong Univ, Sch Informat Sci & Engn, Shenyang 110158, Peoples R China
[2] Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen 518055, Peoples R China
[3] Northeastern Univ, Sch Comp Sci & Engn, Shenyang 110819, Peoples R China
[4] Chongqing Univ Posts & Telecommun, Sch Commun & Informat Engn, Chongqing 400065, Peoples R China
[5] Hangzhou Inst Adv Technol, Hangzhou 310056, Peoples R China
[6] Chongqing Univ Posts & Telecommun, Inst Intelligent Commun & Network Secur, Chongqing 400065, Peoples R China
基金
中国国家自然科学基金;
关键词
Light emitting diodes; Image color analysis; Target tracking; Visualization; Kalman filters; Real-time systems; Filtering; visible light positioning; visual target tracking; gaussian mixture model; kalman filtering; system performance; INDOOR; LOCALIZATION; SYSTEMS; MODEL;
D O I
10.23919/JCC.ea.2021-0765.202302
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
In visible light positioning systems, some scholars have proposed target tracking algorithms to balance the relationship among positioning accuracy, real-time performance, and robustness. However, there are still two problems: (1) When the captured LED disappears and the uncertain LED reappears, existing tracking algorithms may recognize the landmark in error; (2) The receiver is not always able to achieve positioning under various moving statuses. In this paper, we propose an enhanced visual target tracking algorithm to solve the above problems. First, we design the lightweight recognition/demodulation mechanism, which combines Kalman filtering with simple image preprocessing to quickly track and accurately demodulate the landmark. Then, we use the Gaussian mixture model and the LED color feature to enable the system to achieve positioning, when the receiver is under various moving statuses. Experimental results show that our system can achieve high-precision dynamic positioning and improve the system's comprehensive performance.
引用
收藏
页码:276 / 291
页数:16
相关论文
共 51 条
[1]   Pedestrian detection for UAVs using cascade classifiers with Meanshift [J].
Aguilar, Wilbert G. ;
Luna, Marco A. ;
Moya, Julio F. ;
Abad, Vanessa ;
Parra, Humberto ;
Ruiz, Hugo .
2017 11TH IEEE INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING (ICSC), 2017, :509-514
[2]  
Allen J. G., 2004, ACM VIP
[3]   Visible Light Positioning Using Bayesian Filters [J].
Amsters, Robin ;
Holm, Dimiter ;
Joly, Joren ;
Demeester, Eric ;
Stevens, Nobby ;
Slaets, Peter .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2020, 38 (21) :5925-5936
[4]  
[Anonymous], 2014, ACM MOBICOM
[5]  
[Anonymous], 2015, P ACM MOBISYS
[6]  
[Anonymous], 2001, P SIGGRAPH COURS
[7]   MODEL-BASED OBJECT RECOGNITION IN DENSE-RANGE IMAGES - A REVIEW [J].
ARMAN, F ;
AGGARWAL, JK .
COMPUTING SURVEYS, 1993, 25 (01) :5-43
[8]  
Bay H., 2006, P EUROPEAN C COMPUTE
[9]   Spatiotemporal GMM for Background Subtraction with Superpixel Hierarchy [J].
Chen, Mingliang ;
Wei, Xing ;
Yang, Qingxiong ;
Li, Qing ;
Wang, Gang ;
Yang, Ming-Hsuan .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (06) :1518-1525
[10]   MEAN SHIFT, MODE SEEKING, AND CLUSTERING [J].
CHENG, YZ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (08) :790-799