Joint Detection and Estimation of Multiple Objects From Image Observations

The problem of jointly detecting multiple objects and estimating their states from image observations is formulated in a Bayesian framework by modeling the collection of states as a random finite set. Analytic characterizations of the posterior distribution of this random finite set are derived for various prior distributions under the assumption that the regions of the observation influenced by individual objects do not overlap. These results provide tractable means to jointly estimate the number of states and their values from image observations. As an application, we develop a multi-object filter suitable for image observations with low signal-to-noise ratio (SNR). A particle implementation of the multi-object filter is proposed and demonstrated via simulations.

[1]  David Suter,et al.  Multi-object filtering from image sequence without detection , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Samuel J. Davey,et al.  A Comparison of Detection Performance for Several Track-before-Detect Algorithms , 2008, 2008 11th International Conference on Information Fusion.

[3]  Ba-Ngu Vo,et al.  On performance evaluation of multi-object filters , 2008, 2008 11th International Conference on Information Fusion.

[4]  Ba-Ngu Vo,et al.  A Consistent Metric for Performance Evaluation of Multi-Object Filters , 2008, IEEE Transactions on Signal Processing.

[5]  Ronald Mahler,et al.  Multitarget-moment filters for nonstandard measurement models , 2008, SPIE Defense + Commercial Sensing.

[6]  David Suter,et al.  Bayesian multi-object estimation from image observations , 2009, 2009 12th International Conference on Information Fusion.

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

[8]  Andrew W. Moore,et al.  'N-Body' Problems in Statistical Learning , 2000, NIPS.

[9]  Jens B. Lund,et al.  Perfect simulation and inference for point processes given noisy observations , 2004, Comput. Stat..

[10]  Roy L. Streit,et al.  Multitarget Tracking of Distributed Targets Using Histogram-PMHT , 2002, Digit. Signal Process..

[11]  R. Waagepetersen,et al.  Modern Statistics for Spatial Point Processes * , 2007 .

[12]  D. J. Salmond,et al.  A particle filter for track-before-detect , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[13]  Sim Heng Ong,et al.  Tracking multiple speakers using CPHD filter , 2007, ACM Multimedia.

[14]  Ba-Ngu Vo,et al.  Analytic Implementations of the Cardinalized Probability Hypothesis Density Filter , 2007, IEEE Transactions on Signal Processing.

[15]  J. Vermaak,et al.  A unifying framework for multi-target tracking and existence , 2005, 2005 7th International Conference on Information Fusion.

[16]  Branko Ristic,et al.  Beyond the Kalman Filter: Particle Filters for Tracking Applications , 2004 .

[17]  Sim Heng Ong,et al.  Tracking Multiple Objects using Probability Hypothesis Density Filter and Color Measurements , 2007, 2007 IEEE International Conference on Multimedia and Expo.

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

[20]  Samuel S. Blackman,et al.  Multiple-Target Tracking with Radar Applications , 1986 .

[21]  Robin J. Evans,et al.  Linear joint integrated probabilistic data association - LJIPDA , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[22]  R. Mahler,et al.  PHD filters of higher order in target number , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[23]  Ronald P. S. Mahler,et al.  Statistical Multisource-Multitarget Information Fusion , 2007 .

[24]  Ba-Ngu Vo,et al.  The Cardinality Balanced Multi-Target Multi-Bernoulli Filter and Its Implementations , 2009, IEEE Transactions on Signal Processing.

[25]  Ba-Ngu Vo,et al.  The Gaussian Mixture Probability Hypothesis Density Filter , 2006, IEEE Transactions on Signal Processing.

[26]  Patrick Pérez,et al.  Sequential Monte Carlo methods for multiple target tracking and data fusion , 2002, IEEE Trans. Signal Process..

[27]  A. Doucet,et al.  Sequential Monte Carlo methods for multitarget filtering with random finite sets , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[28]  R. Nevanlinna Models for Point Processes Observed with Noise , 1998 .