Performance Evaluation of a Decentralized Multitarget-Tracking Algorithm Using a LIDAR Sensor Network With Stationary Beams

A LIght Detection And Ranging (LIDAR) sensor network to track walking persons inside a surveillance area is investigated. A small number of sensor nodes with spatially stationary and partially overlapping narrow LIDAR beams are chosen in order to keep the costs to a minimum. As a consequence of this network topology, the area of surveillance is not fully covered with LIDAR beams, and thus, accurate tracking of persons walking inside the area of surveillance is challenging, particularly in a multitarget situation. To tackle this problem, multitarget tracking based on a sophisticated decentralized track-to-track fusion architecture is developed and evaluated in this paper: Dynamic multihypothesis tracking (MHT) by independent local trackers is carried out in all sensor nodes; then, local track favorites are sent to a fusion center, where global track candidates are derived and fed back to the local trackers in order to improve local tracking. With this architecture, a track association success rate of (98.8 <formula formulatype="inline"><tex Notation="TeX">$\pm$</tex></formula> 0.3)% and a mean square position error of <formula formulatype="inline"><tex Notation="TeX">$\Delta p = 6.7\ \hbox{cm}$</tex></formula> were derived from 1000 random pairs of intersecting trajectories of two persons walking (mean velocity 1.5 m/s) across a rectangular surveillance area of size 20 m <formula formulatype="inline"><tex Notation="TeX">$\times$</tex></formula> 10 m. The tracking performances as functions of target velocity <formula formulatype="inline"><tex Notation="TeX">$v$</tex></formula> and target radius <formula formulatype="inline"><tex Notation="TeX">$r$</tex></formula> were quantified. Furthermore, the tracking performances as functions of the distance measurement error <formula formulatype="inline"><tex Notation="TeX">$\Delta L$</tex></formula> and beamwidth <formula formulatype="inline"><tex Notation="TeX">$2\beta$</tex></formula> as the most important parameters were obtained. The performance of the proposed algorithm was also experimentally evaluated.

[1]  Aubrey B. Poore,et al.  Multiple Hypothesis Correlation in Track-to-Track Fusion Management , 2006 .

[2]  José Luis Lázaro,et al.  Embedded Vision Modules for Tracking and Counting People , 2009, IEEE Transactions on Instrumentation and Measurement.

[3]  Robert W. Sittler,et al.  An Optimal Data Association Problem in Surveillance Theory , 1964, IEEE Transactions on Military Electronics.

[4]  T. Kirubarajan,et al.  Performance Limits of Track-to-Track Fusion vs . Centralized Estimation : Theory and Application , 2001 .

[5]  Y. Bar-Shalom.  Tracking and data association , 1988 .

[6]  Ryosuke Shibasaki,et al.  A novel system for tracking pedestrians using multiple single-row laser-range scanners , 2005, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[7]  M. J. O'Driscoll,et al.  Multifunction array lidar network for intruder detection, tracking, and identification , 2010, 2010 Sixth International Conference on Intelligent Sensors, Sensor Networks and Information Processing.

[8]  Heinrich Ruser,et al.  Multiple hypothesis tracking of two persons using a network of lidar sensors with stationary and directional beams , 2010, Defense + Commercial Sensing.

[9]  Erwin Prassler,et al.  Fast and robust tracking of multiple moving objects with a laser range finder , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[10]  Heinrich Ruser,et al.  Configuration of a sparse network of LIDAR sensors to identify security-relevant behavior of people , 2009, Security + Defence.

[11]  Thiagalingam Kirubarajan,et al.  Performance limits of track-to-track fusion versus centralized estimation: theory and application [sensor fusion] , 2003 .

[12]  Antonios Tsourdos,et al.  Robust Covariance Estimation for Data Fusion From Multiple Sensors , 2011, IEEE Transactions on Instrumentation and Measurement.

[13]  H. Ruser,et al.  Decentralized multi-target-tracking using a LIDAR sensor network , 2012, 2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[14]  D. Kazakos,et al.  Sequential distributed detection for multisensor data , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[15]  Panganamala Ramana Kumar,et al.  Tracking Objects with Networked Scattered Directional Sensors , 2008, EURASIP J. Adv. Signal Process..

[16]  Kazuhiko Takahashi,et al.  Laser-based tracking of randomly moving people in crowded environments , 2010, 2010 IEEE International Conference on Automation and Logistics.

[17]  Xin Tian,et al.  Exact algorithms for four track-to-track fusion configurations: All you wanted to know but were afraid to ask , 2009, 2009 12th International Conference on Information Fusion.

[18]  Yakov Bar-Shalom,et al.  Multitarget-Multisensor Tracking: Principles and Techniques , 1995 .