Assessment of multi-hypothesis tracking performance for low signal-to-noise ratio targets

Madeleine Gabrielle Sabordo, Samuel Jarrod Davey


The Multi-Hypothesis Tracker (MHT) is generally considered to be the best performing conventional tracker. It assesses the feasible association of sequences of measurements, calculates the probabilities of the association hypotheses and has track initiation capability. Whilst conventional tracking systems use a detection algorithm to extract measurements from the sensor data, Track-Before-Detect techniques remove the detection algorithm and supply all information received from the signal processing system as measurements to be associated and filtered by the tracker. We compare the performance of the MHT with that of a grid-based Hidden Markov Model Track-Before-Detect algorithm for low signal-to-noise ratio targets. The performances of the MHT and grid Hidden Markov Model algorithms are quantified using six measures: root-mean-square position error, overall detection probability, instantaneous detection probability, false track count, false track length, and computation resource. The grid Hidden Markov Model algorithm is found to have better detection and significantly better false track performance at the cost of computation resource.

  • S. S. Blackman and R. Popoli. Design and Analysis of Modern Tracking Systems. Artech House, 1999.
  • B. Ristic, S. Arulampalam, and N. Gordon. Beyond the Kalman Filter: Particle Filters for Tracking Applications. Artech House, 2004.
  • R. M. Burczewski and N. C. Mohanty. Detection of Moving Optical Objects. In Proceedings of International Telemetering Conference, pages 325--330, 1978.
  • S. J. Davey, M. G. Rutten, and B. Cheung. Comparison of Detection Performance for Several Track-Before-Detect Algorithms. EURASIP Journal on Advances in Signal Processing, 2008.
  • C. A. Barlow and S. S. Blackman. New Bayesian Track-Before-Detect Design and Performance Study. In Proceedings of SPIE 3373, 1998.
  • L. D. Stone, C. A. Barlow, and T. L. Corwin. Bayesian Multiple Target Tracking. Artech House, 1999.
  • S. B. Colegrove, S. J. Davey, and B. Cheung. Clutter Rejection Using Peak Curvature. IEEE Trans AES, 42:1492--1496, 2006.
  • D. B. Reid. An Algorithm for Tracking Multiple Targets. IEEE Transactions on Automatic Control, AC-24:843--854, December 1979.
  • B. Ristic and N. Gordon. Lecture notes in Multisensor and Data Fusion. Adelaide University, 2007.
  • S. J. Davey, B. Cheung, and M. G. Rutten. Track-Before-Detect for Sensors with Complex Measurements. In Fusion Conference, 2009.
  • S. J. Davey and M. G. Rutten. A Comparison of Three Algorithms for Tracking Dim Targets. In IDC Conference, 2007.


MHT, multi-hypothesis tracker, tracking, detection, track-before-detect, TBD, TkBD, HMM, hidden-Markov model

Full Text:



Remember, for most actions you have to record/upload into this online system
and then inform the editor/author via clicking on an email icon or Completion button.
ANZIAM Journal, ISSN 1446-8735, copyright Australian Mathematical Society.