Metraipolis › archive › dc_cc57cfa17025

TrajFusionNet+: Transformer-Based Prediction of Pedestrian Crossing Intention via Fusion of Trajectory Representations and Scene Graphs — arXiv:2609.10806

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10806
License (as archived)
CC0-1.0
Archived
2026-10-16T06:28:53.718Z
SHA-256 of the archived text
63acd359c727744d3b6ce7b170a99303b88e9875d189e748e85e37bdf87ac908
Stable URL of this page
https://metraipolis.com/documento/dc_cc57cfa17025

How to cite

TrajFusionNet+: Transformer-Based Prediction of Pedestrian Crossing Intention via Fusion of Trajectory Representations and Scene Graphs — arXiv:2609.10806 — arXiv (en), https://arxiv.org/abs/2609.10806 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc57cfa17025 (Metraipolis archive dc_cc57cfa17025, sha256 63acd359c727744d3b6ce7b170a99303b88e9875d189e748e85e37bdf87ac908)
BibTeX
@misc{dccc57cfa17025,
  title = {TrajFusionNet+: Transformer-Based Prediction of Pedestrian Crossing Intention via Fusion of Trajectory Representations and Scene Graphs — arXiv:2609.10806},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10806},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc57cfa17025; sha256 63acd359c727744d3b6ce7b170a99303b88e9875d189e748e85e37bdf87ac908},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10806. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The pedestrian crossing intention task involves predicting whether pedestrians are likely to cross the road from the point of view of an autonomous vehicle. We introduce TrajFusionNet+, a novel transformer-based model for pedestrian crossing intention prediction. TrajFusionNet+ combines sequential and visual representations of pedestrian trajectory with a graph-based representation of the scene context in order to predict pedestrian crossing intention. The proposed architecture builds upon our previous model, TrajFusionNet, and comprises three branches: a Sequence Attention Module (SAM), which processes a sequential representation of past and predicted pedestrian trajectories; a Visual Attention Module (VAM), which utilizes a visual representation of the pedestrian trajectories by overlaying observed and predicted bounding boxes onto scene images; and a Graph Attention Module (GAM), which extracts pedestrian-centric graphs from segmented scene images and captures the relational dependencies between pedestrians and traffic elements. TrajFusionNet+ achieves improved state-of-the-art performance on the two most widely used pedestrian crossing intention datasets, PIE and JAAD. Furthermore, we introduce a new evaluation protocol in which models are trained jointly on the PIE and JAAD datasets but evaluated separately on each. Under this setting, TrajFusionNet+ demonstrates superior generalization compared to existing approaches.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.10806 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T06:06:28.744Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).