HOME: Heatmap Output for future Motion Estimation - Mines Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

HOME: Heatmap Output for future Motion Estimation

Résumé

In this paper, we propose HOME, a framework tackling the motion forecasting problem with an image output representing the probability distribution of the agent's future location. This method allows for a simple architecture with classic convolution networks coupled with attention mechanism for agent interactions, and outputs an unconstrained 2D topview representation of the agent's possible future. Based on this output, we design two methods to sample a finite set of agent's future locations. These methods allow us to control the optimization trade-off between miss rate and final displacement error for multiple modalities without having to retrain any part of the model. We apply our method to the Argoverse Motion Forecasting Benchmark and achieve 1 st place on the online leaderboard.
Fichier principal
Vignette du fichier
2105.10968.pdf (2.74 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03356794 , version 1 (28-09-2021)

Identifiants

  • HAL Id : hal-03356794 , version 1

Citer

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou, Bogdan Stanciulescu, Fabien Moutarde. HOME: Heatmap Output for future Motion Estimation. 2021 IEEE International Intelligent Transportation Systems Conference (ITSC'2021), Sep 2021, Indianapolis, United States. ⟨hal-03356794⟩
64 Consultations
182 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More