UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914904143822848 |
|---|---|
| author | Feng, Lan Bahari, Mohammadhossein Amor, Kaouther Messaoud Ben Zablocki, Éloi Cord, Matthieu Alahi, Alexandre |
| author_facet | Feng, Lan Bahari, Mohammadhossein Amor, Kaouther Messaoud Ben Zablocki, Éloi Cord, Matthieu Alahi, Alexandre |
| contents | Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored. While these questions can be studied by employing multiple datasets, it is challenging due to several discrepancies, e.g., in data formats, map resolution, and semantic annotation types. To address these challenges, we introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria, presenting new opportunities for the vehicle trajectory prediction field. In particular, using UniTraj, we conduct extensive experiments and find that model performance significantly drops when transferred to other datasets. However, enlarging data size and diversity can substantially improve performance, leading to a new state-of-the-art result for the nuScenes dataset. We provide insights into dataset characteristics to explain these findings. The code can be found here: https://github.com/vita-epfl/UniTraj |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15098 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction Feng, Lan Bahari, Mohammadhossein Amor, Kaouther Messaoud Ben Zablocki, Éloi Cord, Matthieu Alahi, Alexandre Computer Vision and Pattern Recognition Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored. While these questions can be studied by employing multiple datasets, it is challenging due to several discrepancies, e.g., in data formats, map resolution, and semantic annotation types. To address these challenges, we introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria, presenting new opportunities for the vehicle trajectory prediction field. In particular, using UniTraj, we conduct extensive experiments and find that model performance significantly drops when transferred to other datasets. However, enlarging data size and diversity can substantially improve performance, leading to a new state-of-the-art result for the nuScenes dataset. We provide insights into dataset characteristics to explain these findings. The code can be found here: https://github.com/vita-epfl/UniTraj |
| title | UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.15098 |