Incremental Learning of Statistical Motion Patterns with Growing Hidden Markov Models

Dizan Alejandro Vasquez Govea 1 Thierry Fraichard 2, * Christian Laugier 2
* Corresponding author
2 E-MOTION - Geometry and Probability for Motion and Action
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : Modeling and predicting human and vehicle motion is an active research domain. Due to the difficulty of modeling the various factors that determine motion (eg internal state, perception, etc.) this is often tackled by applying machine learning techniques to build a statistical model, using as input a collection of trajectories gathered through a sensor (eg camera, laser scanner), and then using that model to predict further motion. Unfortunately, most current techniques use off-line learning algorithms, meaning that they are not able to learn new motion patterns once the learning stage has finished. In this paper, we present an approach which is able to learn new motion patterns incrementally, and in parallel with prediction. Our work is based on a novel extension to Hidden Markov Models called Growing Hidden Markov models.
Document type :
Book sections
Complete list of metadatas

https://hal.inria.fr/inria-00584320
Contributor : Thierry Fraichard <>
Submitted on : Friday, April 8, 2011 - 10:50:43 AM
Last modification on : Monday, August 19, 2019 - 4:42:03 PM

Links full text

Identifiers

Collections

Citation

Dizan Alejandro Vasquez Govea, Thierry Fraichard, Christian Laugier. Incremental Learning of Statistical Motion Patterns with Growing Hidden Markov Models. Makoto Kaneko and Yoshihiko Nakamura. Robotics Research, 66, Springer Berlin, pp.75-86, 2011, Springer Tracts in Advanced Robotics, 978-3-642-14742-5. ⟨10.1007/978-3-642-14743-2_7⟩. ⟨inria-00584320⟩

Share

Metrics

Record views

261