Target Tracking Using Factor Graphs and Multi-Camera Systems

被引:7
作者
Castaldo, Francesco [1 ]
Palmieri, Francesco A. N. [1 ]
机构
[1] Seconda Univ Napoli, I-81031 Aversa, CE, Italy
关键词
Ports and harbors - Target tracking - Clutter (information theory);
D O I
10.1109/TAES.2015.140087
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
This paper presents a multi-camera target tracking system based on factor graphs, designed to estimate the state of moving targets using a message propagation framework. Inexpensive cameras deployed in the area of interest are the main sensory modality. We discuss the transformation geometry between world points and camera pixels and how the uncertainties in the homographies affect the estimation. The framework has been tested on real data coming from a harbor to track moving vessels.
引用
收藏
页码:1950 / 1960
页数:11
相关论文
共 20 条
[1]  
[Anonymous], 2012, Bayesian Reasoning and Machine Learning
[2]  
[Anonymous], 2004, IEEE INT C SYST MAN
[3]  
[Anonymous], 2011, Tracking and Data Fusion
[4]  
Bar-Shalom Y., 2002, ESTIMATIONWITH APPL
[5]  
Bier A., 2009, COMPUTER VISION COMP
[6]   Object Tracking in the Presence of Occlusions Using Multiple Cameras: A Sensor Network Approach [J].
Ercan, Ali O. ;
El Gamal, Abbas ;
Guibas, Leonidas J. .
ACM TRANSACTIONS ON SENSOR NETWORKS, 2013, 9 (02)
[7]   Codes on graphs: Normal realizations [J].
Forney, GD .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2001, 47 (02) :520-548
[8]   SINGULAR VALUE DECOMPOSITION AND LEAST SQUARES SOLUTIONS [J].
GOLUB, GH ;
REINSCH, C .
NUMERISCHE MATHEMATIK, 1970, 14 (05) :403-&
[9]  
Hartley R., 2003, Multiple view geometry in computer vision
[10]  
Koller N.F. Daphne., 2009, Probabilistic Graphical Models: Principles and Techniques