For　irregular　extended　object　and　group　target　tracking　(IEOT　and　IGTT),　using　a　random　matrix　to　simplify　the　extension　as　an　ellipsoid,　although　efficient,　may　not　be　accurate　without　losing　useful　information　in　shape　and　orientation.　In　view　of　this,　we　consider　modeling　an　irregular　extended　object　or　target　group　as　a　combination　of　multiple　regular　sub-objects.　Each　sub-object　can　be　described　adequately　by　an　ellipsoid　represented　by　a　random　matrix.　Different　regular　sub-objects　are　distinguished　by　different　dynamic　models.　Based　on　such　models,　a　Bayesian　approach　is　then　proposed　to　estimate　the　kinematic　states　and　the　extensions　of　the　sub-objects.　For　maneuvering　IEOT　and　IGTT,　a　multiple-model　approach　is　proposed.　Overall　maneuver　models　are　combined　with　the　sub-object　models　to　describe　the　common　and　the　individual　motions　of　the　sub-objects.　Two　scenarios　for　maneuvering　and　non-maneuvering　IEOT　and　IGTT　are　simulated.　The　results　demonstrate　the　effectiveness　of　the　proposed　modeling　and　estimation　approach.　©　2012　ISIF　(Intl　Society　of　Information　Fusi).