Bayesian multiple target tracking in forward scan sonar images using the PHD filter

A multiple target tracking algorithm for forward-looking sonar images is presented. The algorithm will track a variable number of targets estimating both the number of targets and their locations. Targets are tracked from range and bearing measurements by estimating the first-order statistical moment of the multitarget probability distribution called the probability hypothesis density (PHD). The recursive estimation of the PHD is much less computationally expensive than estimating the joint multitarget probability distribution. Results are presented showing a variable number of targets being tracked with targets entering and leaving the field of view. An initial implementation is shown to work on a simulated sonar trajectory and an example is shown working on real data with clutter.

[1]  Yvan Petillot,et al.  AUV Navigation Using a Forward Looking Sonar , 2000 .

[2]  Michael Isard,et al.  BraMBLe: a Bayesian multiple-blob tracker , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[3]  Y. Petillot,et al.  Concurrent mapping and localization using sidescan sonar , 2004, IEEE Journal of Oceanic Engineering.

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

[5]  Timothy J. Robinson,et al.  Sequential Monte Carlo Methods in Practice , 2003 .

[6]  R. Mahler.  Multitarget Bayes filtering via first-order multitarget moments , 2003 .

[7]  Emanuele Trucco,et al.  Feature Tracking in Video and Sonar Subsea Sequences with Applications , 2000, Comput. Vis. Image Underst..

[8]  A.D. Lanterman,et al.  A probability hypothesis density-based multitarget tracker using multiple bistatic range and velocity measurements , 2004, Thirty-Sixth Southeastern Symposium on System Theory, 2004. Proceedings of the.

[9]  David M. Lane,et al.  A comparison of inter-frame feature measures for robust object classification in sector scan sonar image sequences , 1999 .

[10]  Neil J. Gordon,et al.  Bayesian State Estimation for Tracking and Guidance Using the Bootstrap Filter , 1993 .

[11]  Sumeetpal S. Singh,et al.  Sequential monte carlo implementation of the phd filter for multi-target tracking , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[12]  Wolfram Burgard,et al.  People Tracking with Mobile Robots Using Sample-Based Joint Probabilistic Data Association Filters , 2003, Int. J. Robotics Res..

[13]  Y. Wang,et al.  Underwater vehicle path planning using a multi-beam forward looking sonar , 1998, IEEE Oceanic Engineering Society. OCEANS'98. Conference Proceedings (Cat. No.98CH36259).

[14]  P. Pérez,et al.  Tracking multiple objects with particle filtering , 2002 .

[15]  Ronald P. S. Mahler,et al.  Particle-systems implementation of the PHD multitarget-tracking filter , 2003, SPIE Defense + Commercial Sensing.

[16]  Yvan Petillot,et al.  Concurrent Mapping and Localisation using Side-scan sonar for autonomous navigation , 2003 .

[17]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[18]  Alfred O. Hero,et al.  A Bayesian method for integrated multitarget tracking and sensor management , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[19]  Editors , 1986, Brain Research Bulletin.

[20]  James Llinas,et al.  Handbook of Multisensor Data Fusion , 2001 .

[21]  Hedvig Sidenbladh,et al.  Multi-target particle filtering for the probability hypothesis density , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[22]  Fredrik Gustafsson,et al.  Monte Carlo data association for multiple target tracking , 2001 .