Human tracking using 3D surface colour distributions

TY - JOUR

T1 - Human tracking using 3D surface colour distributions

AU - Roberts, Timothy J.

AU - McKenna, Stephen J.

AU - Ricketts, Ian W.

N1 - dc.publisher: Elsevier

PY - 2006/12

Y1 - 2006/12

N2 - A likelihood formulation for detailed human tracking in real-world scenes is presented. In this formulation, the appearance, modelled using feature distributions defined over regions on the surface of an articulated 3D model, is estimated and propagated as part of the state. The benefit of such a formulation over currently used techniques is that it provides a dense, highly discriminatory object-based cue that applies in real world scenes. Multi-dimensional histograms are used to represent the feature distributions and an on-line clustering algorithm, driven by prior knowledge of clothing structure, is derived that enhances appearance estimation and computational efficiency. An investigation of the likelihood model shows its profile to be smooth and broad while region grouping is shown to improve localisation and discrimination. These properties of the likelihood model ease pose estimation by allowing coarse, hierarchical sampling and local optimisation.

AB - A likelihood formulation for detailed human tracking in real-world scenes is presented. In this formulation, the appearance, modelled using feature distributions defined over regions on the surface of an articulated 3D model, is estimated and propagated as part of the state. The benefit of such a formulation over currently used techniques is that it provides a dense, highly discriminatory object-based cue that applies in real world scenes. Multi-dimensional histograms are used to represent the feature distributions and an on-line clustering algorithm, driven by prior knowledge of clothing structure, is derived that enhances appearance estimation and computational efficiency. An investigation of the likelihood model shows its profile to be smooth and broad while region grouping is shown to improve localisation and discrimination. These properties of the likelihood model ease pose estimation by allowing coarse, hierarchical sampling and local optimisation.

KW - Human tracking

KW - Articulated models

KW - Sequential estimation

KW - Human computer interfaces

UR - https://www.scopus.com/pages/publications/33749552246

U2 - 10.1016/j.imavis.2006.04.011

DO - 10.1016/j.imavis.2006.04.011

M3 - Article

SN - 0262-8856

VL - 24

SP - 1332

EP - 1342

JO - Image and Vision Computing

JF - Image and Vision Computing

IS - 12

ER -