Acronym TMO
Name Tracking of Moving Objects with Trained Multi-Models
Funding Reference FCT - PRAXIS/P/EEI/12050/1998
Dates 1999|2003
Summary

This project aims at developing robust tracking algorithms for dealing with complex motion and shape dynamics. Current methods achieve good tracking performance in the presence of non-cluttered background and smooth motion and deformation regimes but they typically loose track if one of these conditions fails. This project studies the use of multiple deformable models with switching/mixing algorithms as a way to enlarge the tracking capabilities. This raises several interesting questions: how to combine multiple models or switch between them? Can tracking be improved if the parameters lie on manifold contained in Rn? What methods can be used to estimate the manifold and the parameter trajectory? Other topics that will be addressed in this project are multi-model learning and robust trajectory estimation methods to reduce the influence of outliers. The proposed algorithms will be tested in selected applications.

Research Groups Signal and Image Processing Group (SIPG)
Project Partners IST, ISEL
ISR/IST Responsible
Jorge Salvador Marques
[1] Jacinto Nascimento, Robust Shape Estimation and Tracking in the Presence of Clutter, Ph.D. Thesis, Instituto Superior Tecnico, Lisbon, Portugal, 2003
[2] Jacinto Nascimento, Arnaldo J. Abrantes, Jorge Salvador Marques, Using middle level features for robust shape tracking, Pattern Recognition Letters, Vol. 24, 295-307, 2003
[3] Jacinto Nascimento, Arnaldo J. Abrantes, Jorge Salvador Marques, The Role of Middle level features for robust shape tracking, 12th Portuguese Conference on Pattern Recognition, Aveiro, 2002 - PDF
[4] Joao M. Lemos, Rui N. Silva, Jorge Salvador Marques, Adaptive Control of the Ball and Beam Plant in the Presence of Sensor Measurement Outliers, Proc. of ACC2002 - American Control Conference, Anchorage, Alaska, USA, 2002
[5] Rui M. Jesus, Arnaldo J. Abrantes, Jorge Salvador Marques, Tracking of Human Body using Multiple Predictors, Second International Workshop on Articulated Motion and Deformable Models, Maiorca, 2002 - PDF
[6] João Sanches, Jorge Salvador Marques, 3D Reconstruction from Log-Compressed Rayleigh Images, Proc. of ICIP2001 - IEEE International Conference on Image Processing, pp. 345-348, Thessaloniki, 2001 - PDF
[7] Jorge Salvador Marques, Arnaldo J. Abrantes, A Constrained Clustering Algorithm for Shape Analysis with Multiple Features, Proc. of ICPR2000 - International Conference on Pattern Recognition, Barcelona, Spain, Vol.1, pp. 916-919, 2000
[8] Jorge Salvador Marques, J. M. Lemos, Jorge Silva, Tracking Diffusions on Manifolds: A Hidden Markov Model Approach, Proc. of the 5th Ibero American Symposium on Pattern Recognition, Lisbon, Portugal, pp. 255-266, 2000
[9] J. M. Lemos, L. M. Rato, Jorge Salvador Marques, Minimum variance control of time varying systems based on hidden Markov models, Controlo' 2000, Guimaraes, Portugal, 2000
[10] Jorge Silva, Jorge Salvador Marques, J. M. Lemos, Robust motion tracking on one-dimensional manifolds, Controlo'2000, Guimaraes, Portugal, 2000
[11] Jorge Salvador Marques, Joao M. Lemos, Shape Tracking with Switched Multiple Models, Proc. 11th Portuguese Conference on Pattern Recognition, Porto, 213-218, 2000
[12] Jorge Salvador Marques, Joao M. Lemos, Arnaldo J. Abrantes, Estimation of Random Trajectories on Manifolds: Application to Object Tracking, Proc. of ICIP1999 - IEEE International Conference on Image Processing, Kobe, Japan, pp. 103-107, 1999
[13] Jorge Salvador Marques, Joao M. Lemos, Shape Tracking Based on Switching Dynamical Models, Proc. of ICIP1999 - IEEE International Conference on Image Processing, Kobe, Japan, pp. 954-958, 1999
[14] Jacinto Nascimento, Arnaldo J. Abrantes, Jorge Salvador Marques, An Algorithm for Centroid Based Tracking of Moving Objects, Proc. of ICASSPP1999 - IEEE International Conference on Acoustics, Speech and Signal Processing, Phoenix, USA, pp. 3305-3308, 1999
[15] Jacinto Nascimento, Jorge Salvador Marques, Robust Shape Tracking in the Presence of Cluttered Background, IEEE International Conference on Image Processing, vol.3, 82-85, Vancouver, Canada, 2000
[16] Jorge Salvador Marques, Joao M. Lemos, Tracking of Moving Objects with Multiple Models Using Gaussian Mixtures, Proc. of ICASSP1999 - IEEE International Conference on Acoustics, Speech and Signal Processing, Phoenix, USA, pp. 3317-3320, 1999
[17] A. J. Abrantes, Jorge Salvador Marques, Seguimento de Objectos com Modelo de Observacoes Baseado em Centroides, Jornadas de Engenharia de Telecomunicacoes e Computadores, VI, pp. 15-20, 1999
[18] Jorge Salvador Marques, Joao M. Lemos, Optimal and Suboptimal Shape Tracking Based on Multiple Switched Dynamic Models, Image and Vision Computing, 539-550, 2001 - PDF
[19] Jacinto Nascimento, Jorge Salvador Marques, An Adaptive Potential for Robust Shape Estimation, British Machine Vision Conference, 343-352, Manchester, 2001
[20] Pedro Jorge, Arnaldo J. Abrantes, Jorge Salvador Marques, Automatic Tracking of Multiple Pedestrians with Group Formation and Occlusions, IASTED International Conference on Visualization, Imaging and Image Processing, 613-618, Marbella, Spain, 2001 - PDF
[21] Jacinto Nascimento, Jorge Salvador Marques, Improving the Robustness of Parametric Shape Tracking with Switched Multiple Models, Pattern Recognition in Information Systems, A. Fred, A. Jain, eds, 50-58, Setubal, 2001 - PDF
[22] Arnaldo J. Abrantes, Jorge Salvador Marques, Shape Tracking Using Centroid Based Methods, Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, Sophia-Antipolis, France, pp. 576-591, 2001
[23] Jorge Salvador Marques, Joao M. Lemos, Arnaldo Abrantes, A HMM Approach to the Estimation of Random Trajectories on Manifolds, Signal Processing, Vol. 82, 1205-1214, 2002 - PDF
[24] Jacinto Nascimento, Jorge Salvador Marques, Robust Multi-Model Filter for Shape Tracking in the Presence of Outliers, Pattern Recognition, Vol. 35, 2711-2718, 2002 - PDF