Attention : l'accès aux ressources peut être restreint, soit pour des raisons juridiques, soit par la volonté de l'auteur.
10 résultats
section 1 sur 1
résultats 1 à 10
Canal-u.fr
5.1. Introduction  Droits d'accès : non autorisé
Description : In this part of the course we are going to go deeper into situation awareness and in particular we are going to study how to model and learn human behavior which is a crucial task for social-aware navigation.
Date : 01-06-2015
 Description complète
5.1. Introduction
Accéder aux documents
Canal-u.fr
5.2. Expectation-Maximization Clustering  Droits d'accès : non autorisé
Description : In this video, we are going to start working towards building a motion model.
Date : 01-06-2015
 Description complète
5.2. Expectation-Maximization Clustering
Accéder aux documents
Canal-u.fr
5.3a. Learning typical trajectories 1/2  Droits d'accès : non autorisé
Description : In video 5.2 we showed how to apply the expectation maximization clustering algorithm to two-dimensional data. In this video we will learn how to apply it to trajectory data. And then we will be able to detect typical trajectories in data.
Date : 01-06-2015
 Description complète
5.3a. Learning typical trajectories 1/2
Accéder aux documents
Canal-u.fr
5.3b. Learning typical trajectories 2/2  Droits d'accès : non autorisé
Description : In this video we are aiming to improve on the results we obtained in video 5.3a, in particular with respect to the greyed-out trajectories that are badly represented.
Date : 01-06-2015
 Description complète
5.3b. Learning typical trajectories 2/2
Accéder aux documents
Canal-u.fr
5.4. Bayesian filter inference  Droits d'accès : non autorisé
Description : In this video we will review the base filter and we will study a particular instance of the Bayesian filter called Hidden Markov models which is a discrete version of a Bayesian filter.
Date : 01-06-2015
 Description complète
5.4. Bayesian filter inference
Accéder aux documents
Canal-u.fr
5.5. From trajectories to discrete time-state models  Droits d'accès : non autorisé
Description : In this video we are going to apply the concepts we have reviewed in the video 5.4 into real trajectories.
Date : 01-06-2015
 Description complète
5.5. From trajectories to discrete time-state models
Accéder aux documents
Canal-u.fr
5.6. Predicting Human Motion  Droits d'accès : non autorisé
Description : In video 5.5 we have defined an HMM in Python. In this video we are going to learn how to use it to estimate and predict motion.
Date : 01-06-2015
 Description complète
5.6. Predicting Human Motion
Accéder aux documents
Canal-u.fr
5.7. Typical Trajectories: drawbacks  Droits d'accès : non autorisé
Description : In previous videos we have discussed how to implement the typical trajectories and motion patterns approach. In this video we are going to discuss what are the drawbacks of such an approach, because there are many of them.
Date : 01-06-2015
 Description complète
5.7. Typical Trajectories: drawbacks
Accéder aux documents
Canal-u.fr
5.8. Other approaches: Social Forces  Droits d'accès : non autorisé
Description : In this video we will review one of the alternatives we are proposing to the use of Hidden Markov models and typical trajectories: the Social Force model.
Date : 01-06-2015
 Description complète
5.8. Other approaches: Social Forces
Accéder aux documents
Canal-u.fr
5.9. Other approaches: Planning-based approaches  Droits d'accès : non autorisé
Description : In this video we are going to study a second, and probably the most promising alternative for motion prediction: planning-based algorithms.
Date : 01-06-2015
 Description complète
5.9. Other approaches: Planning-based approaches
Accéder aux documents