Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    Autonomous Virtual Agents for Performance Evaluation of Tracking Algorithms

    This paper describes a framework which exploits the use of computer animation to evaluate the performance of tracking algorithms. This can be achieved in two different, complementary strategies. On the one han...

    Pau Baiget, Xavier Roca, Jordi Gonzàlez in Articulated Motion and Deformable Objects (2008)

  2. No Access

    Chapter and Conference Paper

    Semantic Annotation of Complex Human Scenes for Multimedia Surveillance

    A Multimedia Surveillance System (MSS) is considered for automatically retrieving semantic content from complex outdoor scenes, involving both human behavior and traffic domains. To characterize the dynamic in...

    Carles Fernández, Pau Baiget, Xavier Roca in AI*IA 2007: Artificial Intelligence and Hu… (2007)

  3. No Access

    Chapter and Conference Paper

    Automatic Learning of Conceptual Knowledge in Image Sequences for Human Behavior Interpretation

    This work describes an approach for the interpretation and explanation of human behavior in image sequences, within the context of a Cognitive Vision System. The information source is the geometrical data obtaine...

    Pau Baiget, Carles Fernández, Xavier Roca in Pattern Recognition and Image Analysis (2007)

  4. No Access

    Chapter and Conference Paper

    Natural Language Descriptions of Human Behavior from Video Sequences

    This contribution addresses the generation of textual descriptions in several natural languages for evaluation of human behavior in video sequences. The problem is tackled by converting geometrical information...

    Carles Fernández Tena, Pau Baiget in KI 2007: Advances in Artificial Intelligen… (2007)

  5. No Access

    Chapter and Conference Paper

    3D Human Motion Sequences Synchronization Using Dense Matching Algorithm

    This work solves the problem of synchronizing pre-recorded human motion sequences, which show different speeds and accelerations, by using a novel dense matching algorithm. The approach is based on the dynamic...

    Mikhail Mozerov, Ignasi Rius, Xavier Roca, Jordi González in Pattern Recognition (2006)

  6. No Access

    Chapter and Conference Paper

    Posture Constraints for Bayesian Human Motion Tracking

    One of the most used techniques for full-body human tracking consists of estimating the probability of the parameters of a human body model over time by means of a particle filter. However, given the high-dime...

    Ignasi Rius, Javier Varona, Xavier Roca in Articulated Motion and Deformable Objects (2006)

  7. No Access

    Chapter and Conference Paper

    A 3D Dynamic Model of Human Actions for Probabilistic Image Tracking

    In this paper we present a method suitable to be used for human tracking as a temporal prior in a particle filtering framework such as CONDENSATION [5]. This method is for predicting feasible human postures given...

    Ignasi Rius, Daniel Rowe, Jordi Gonzàlez in Pattern Recognition and Image Analysis (2005)

  8. No Access

    Chapter and Conference Paper

    Probabilistic Image-Based Tracking: Improving Particle Filtering

    Condensation is a widely-used tracking algorithm based on particle filters. Although some results have been achieved, it has several unpleasant behaviours. In this paper, we highlight the...

    Daniel Rowe, Ignasi Rius, Jordi Gonzàlez in Pattern Recognition and Image Analysis (2005)

  9. No Access

    Chapter and Conference Paper

    Multiple Model Approach to Deformable Shape Tracking

    This paper describes a new proposal for tracking deformable objects in video sequences using multiple shape models of heterogeneous dimensionality. This models are generated unsupervisedly from a training sequ...

    Daniel Ponsa, Xavier Roca in Pattern Recognition and Image Analysis (2003)

  10. No Access

    Chapter and Conference Paper

    Unsupervised Parameterisation of Gaussian Mixture Models

    In this paper we explain a new practical methodology to fully parameterise Gaussian Mixture Models (GMM) to describe data set distributions. Our approach analyses hierarchically a data set distribution to be m...

    Daniel Ponsa, Xavier Roca in Topics in Artificial Intelligence (2002)