Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications. A key component of this task is represented by the inherently multi-modal nature of human paths which makes socially acceptable multiple futures when human interactions are involved. To this end, we propose a generative architecture for multi-future trajectory predictions based on Conditional Variational Recurrent Neural Networks (C-VRNNs). Conditioning mainly relies on prior belief maps, representing most likely moving directions and forcing the model to consider past observed dynamics in generating future positions. Human interactions are modelled with a graph-based attention mechanism enabling an online attentive hidden state refinement of the recurrent estimation. To corroborate our model, we perform extensive experiments on publicly-available datasets (e.g., ETH/UCY, Stanford Drone Dataset, STATS SportVU NBA, Intersection Drone Dataset and TrajNet++) and demonstrate its effectiveness in crowded scenes compared to several state-of-the-art methods.
AC-VRNN: Attentive Conditional-VRNN for multi-future trajectory prediction / Bertugli, A.; Calderara, S.; Coscia, P.; Ballan, L.; Cucchiara, R.. - In: COMPUTER VISION AND IMAGE UNDERSTANDING. - ISSN 1077-3142. - 210:(2021), pp. 103245-103257. [10.1016/j.cviu.2021.103245]
AC-VRNN: Attentive Conditional-VRNN for multi-future trajectory prediction
Bertugli A.;Calderara S.;Cucchiara R.
2021
Abstract
Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications. A key component of this task is represented by the inherently multi-modal nature of human paths which makes socially acceptable multiple futures when human interactions are involved. To this end, we propose a generative architecture for multi-future trajectory predictions based on Conditional Variational Recurrent Neural Networks (C-VRNNs). Conditioning mainly relies on prior belief maps, representing most likely moving directions and forcing the model to consider past observed dynamics in generating future positions. Human interactions are modelled with a graph-based attention mechanism enabling an online attentive hidden state refinement of the recurrent estimation. To corroborate our model, we perform extensive experiments on publicly-available datasets (e.g., ETH/UCY, Stanford Drone Dataset, STATS SportVU NBA, Intersection Drone Dataset and TrajNet++) and demonstrate its effectiveness in crowded scenes compared to several state-of-the-art methods.File | Dimensione | Formato | |
---|---|---|---|
2005.08307.pdf
Open access
Tipologia:
Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
12.62 MB
Formato
Adobe PDF
|
12.62 MB | Adobe PDF | Visualizza/Apri |
1-s2.0-S1077314221000898-main.pdf
Open access
Tipologia:
Versione pubblicata dall'editore
Dimensione
2.23 MB
Formato
Adobe PDF
|
2.23 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris