EUVIMEDEUVIMED entdecken
Crossref

Towards Trajectory Forecasting From Detection

Pu Zhang, Lei Bai, Yuning Wang, Jianwu Fang, Jianru Xue, Nanning Zheng, Wanli Ouyang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-10 · 45 (10) · 12550-12561

DOI: 10.1109/tpami.2023.3274686 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-10. Verfasst von Pu Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, STI 2030 Major Project, National Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Trajectory forecasting for traffic participants (e.g., vehicles) is critical for autonomous platforms to make safe plans. Currently, most trajectory forecasting methods assume that object trajectories have been extracted and directly develop trajectory predictors based on the ground truth trajectories. However, this assumption does not hold in practical situations. Trajectories obtained from object detection and tracking are inevitably noisy, which could cause serious forecasting errors to predictors built on ground truth trajectories. In this paper, we propose to predict trajectories directly based on detection results without relying on explicitly formed trajectories. Different from traditional methods which encode the motion cues of an agent based on its clearly defined trajectory, we extract the motion information only based on the affinity cues among detection results, in which an affinity-aware state update mechanism is designed to manage the state information. In addition, considering that there could be multiple plausible matching candidates, we aggregate the states of them. These designs take the uncertainty of association into account which relax the undesirable effect of noisy trajectory obtained from data association and improve the robustness of the predictor. Extensive experiments validate the effectiveness of our method and its generalization ability to different detectors or forecasting schemes.

Förderung

  • National Natural Science Foundation of China
  • STI 2030 Major Project
  • National Key R&D Program of China
  • Shanghai Committee of Science and Technology

Zitieren

APA

Zhang, P., Bai, L., Wang, Y., Fang, J., Xue, J., Zheng, N., & Ouyang, W. (2023). Towards Trajectory Forecasting From Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10), 12550-12561. https://doi.org/10.1109/tpami.2023.3274686

Vancouver

Zhang P, Bai L, Wang Y, Fang J, Xue J, Zheng N, et al. Towards Trajectory Forecasting From Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(10):12550-12561. doi:10.1109/tpami.2023.3274686

BibTeX
@article{Zhang2023,
  author = {Zhang, Pu and Bai, Lei and Wang, Yuning and Fang, Jianwu and Xue, Jianru and Zheng, Nanning and Ouyang, Wanli},
  title = {Towards Trajectory Forecasting From Detection},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {10},
  pages = {12550--12561},
  doi = {10.1109/tpami.2023.3274686}
}
Kostenlos starten →