Détail de l'auteur
Auteur Zhenhua Cui |
Documents disponibles écrits par cet auteur (1)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
![Tris disponibles](./images/orderby_az.gif)
Modeling human–human interaction with attention-based high-order GCN for trajectory prediction / Yanyan Fang in The Visual Computer, vol 38 n° 7 (July 2022)
![]()
[article]
Titre : Modeling human–human interaction with attention-based high-order GCN for trajectory prediction Type de document : Article/Communication Auteurs : Yanyan Fang, Auteur ; Zhiyu Jin, Auteur ; Zhenhua Cui, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 2257 - 2269 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] attention (apprentissage automatique)
[Termes IGN] détection de cible
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] interaction spatiale
[Termes IGN] modèle de simulation
[Termes IGN] objet mobile
[Termes IGN] piéton
[Termes IGN] réseau neuronal de graphes
[Termes IGN] trajet (mobilité)Résumé : (auteur) This paper presents a novel high-order graph convolutional network (GCN) for pedestrian trajectory prediction. Specifically, the walking state of a target pedestrian depends on both its historical trajectory, which encodes its speed, walking direction and acceleration information, as well as the movement of its neighbors. Thus we propose to leverage GCNs to aggregate the trajectory features of the target pedestrian and its neighbors to predict the movement of the target pedestrian. Considering that the movement of the neighbors’ neighbors affects the movement of the target pedestrian’s neighbors, thus indirectly affecting the movement of the target pedestrian, we propose to use a high-order GCN for human–human interaction modelling. Such a high-order GCN considers the target pedestrian’s neighbors as well as its neighbors’ neighbors. Further, a pedestrian avoids collision with others by estimating its locations and its neighbors’ upcoming locations, and it slows down or changes direction if it believes a collision may occur, especially in very crowded scenes. In light of this, we propose to model such anticipation-based decision making behavior as attention and combine it with our high-order GCN. Thus we first roughly estimate the future trajectories of all pedestrians with a simple method. By using the coarse predicted future trajectory and GCN outputs, we calculate the attention in our attention-based high-order GCN and predict future trajectory. Extensive experiments validate the effectiveness of our approach. In addition, our model shows a higher data efficiency. On the ETH&UCY dataset, using only 5% of the training data for each training epoch, our model outperforms the state of the art. Numéro de notice : A2022-507 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-021-02109-2 Date de publication en ligne : 01/07/2021 En ligne : https://doi.org/10.1007/s00371-021-02109-2 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101040
in The Visual Computer > vol 38 n° 7 (July 2022) . - pp 2257 - 2269[article]