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 top-view 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 1st place on the online leaderboard.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    HOME: Heatmap Output for future Motion Estimation


    Beteiligte:


    Erscheinungsdatum :

    2021-09-19


    Format / Umfang :

    3025568 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Reconfigurable avionics systems heatmap

    WONG JASON L | Europäisches Patentamt | 2022

    Freier Zugriff

    Vehicle Detection based on Deep Learning Heatmap Estimation

    Theodosc, Ruddy / Denis, Dieumet / Blanc, Christophe et al. | IEEE | 2019


    Automated Motion Heatmap Generation for Bridge Navigation Watch Monitoring System

    Gokcek, Veysel / Kocak, Gazi / Genc, Yakup | Online Contents | 2022


    Reconfigurable Avionics Systems Heatmap

    WONG JASON L | Europäisches Patentamt | 2021

    Freier Zugriff

    Automated Motion Heatmap Generation for Bridge Navigation Watch Monitoring System

    Gokcek Veysel / Kocak Gazi / Genc Yakup | DOAJ | 2022

    Freier Zugriff