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

• URL: http://arxiv.org/abs/2609.10806v1
• Date: Wed, 09 Sep 2026 20:17:32 GMT
• Title: TrajFusionNet+: Transformer-Based Prediction of Pedestrian Crossing Intention via Fusion of Trajectory Representations and Scene Graphs
• Abstract summary: The pedestrian crossing intention task involves predicting whether pedestrians are likely to cross the road from the point of view of an autonomous vehicle.<n>We introduce TrajFusionNet+, a novel transformer-based model for pedestrian crossing intention prediction.<n>TrajFusionNet+ combines sequential and visual representations of pedestrian trajectory with a graph-based representation of the scene context.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• TrajFusionNet: Pedestrian Crossing Intention Prediction via Fusion of Sequential and Visual Trajectory Representations [0.0]
  TrajFusionNet is a transformer-based model for predicting pedestrian crossing intention.<n>It learns from a sequential representation of the observed and predicted pedestrian trajectory and vehicle speed.<n>It achieves state-of-the-art results across the three most commonly used datasets for pedestrian crossing intention prediction.
  arXiv  Detail & Related papers  (2025-08-27T13:29:15Z)
• GC-GAT: Multimodal Vehicular Trajectory Prediction using Graph Goal Conditioning and Cross-context Attention [0.0]
  We present a lane graph-based motion prediction model that first predicts graph-based goal proposals and later fuses them with cross attention over multiple contextual elements.<n>We evaluate our work on nuScenes motion prediction dataset, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2025-04-15T12:53:07Z)
• PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning [10.812772606528172]
  We propose a novel framework that relies on different data modalities to predict future trajectories and crossing actions of pedestrians from an ego-centric perspective. We show that our model improves state-of-the-art in trajectory and action prediction by up to 22% and 13% respectively on various metrics.
  arXiv  Detail & Related papers  (2022-10-14T15:12:00Z)
• DR.VIC: Decomposition and Reasoning for Video Individual Counting [93.12166351940242]
  We propose to conduct pedestrian counting from a new perspective - Video Individual Counting (VIC) Instead of relying on the Multiple Object Tracking (MOT) techniques, we propose to solve the problem by decomposing all pedestrians into the initial pedestrians who existed in the first frame and the new pedestrians with separate identities in each following frame. An end-to-end Decomposition and Reasoning Network (DRNet) is designed to predict the initial pedestrian count with the density estimation method and reason the new pedestrian's count of each frame with the differentiable optimal transport.
  arXiv  Detail & Related papers  (2022-03-23T11:24:44Z)
• Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion [87.77727495366702]
  We introduce the new task of pedestrian stop and go forecasting. Considering the lack of suitable existing datasets for it, we release TRANS, a benchmark for explicitly studying the stop and go behaviors of pedestrians in urban traffic. We build it from several existing datasets annotated with pedestrians' walking motions, in order to have various scenarios and behaviors.
  arXiv  Detail & Related papers  (2022-03-04T18:39:31Z)
• SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction [64.16212996247943]
  We present a Sparse Graph Convolution Network(SGCN) for pedestrian trajectory prediction. Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians. visualizations indicate that our method can capture adaptive interactions between pedestrians and their effective motion tendencies.
  arXiv  Detail & Related papers  (2021-04-04T03:17:42Z)
• Vehicle Trajectory Prediction in Crowded Highway Scenarios Using Bird Eye View Representations and CNNs [0.0]
  This paper describes a novel approach to perform vehicle trajectory predictions employing graphic representations. The problem is faced as an image to image regression problem training the network to learn the underlying relations between the traffic participants. The model has been tested in highway scenarios with more than 30 vehicles simultaneously in two opposite traffic flow streams.
  arXiv  Detail & Related papers  (2020-08-26T11:15:49Z)
• Implicit Latent Variable Model for Scene-Consistent Motion Forecasting [78.74510891099395]
  In this paper, we aim to learn scene-consistent motion forecasts of complex urban traffic directly from sensor data. We model the scene as an interaction graph and employ powerful graph neural networks to learn a distributed latent representation of the scene.
  arXiv  Detail & Related papers  (2020-07-23T14:31:25Z)
• VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation [74.56282712099274]
  This paper introduces VectorNet, a hierarchical graph neural network that exploits the spatial locality of individual road components represented by vectors. By operating on the vectorized high definition (HD) maps and agent trajectories, we avoid lossy rendering and computationally intensive ConvNet encoding steps. We evaluate VectorNet on our in-house behavior prediction benchmark and the recently released Argoverse forecasting dataset.
  arXiv  Detail & Related papers  (2020-05-08T19:07:03Z)
• Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction [57.56466850377598]
  Reasoning over visual data is a desirable capability for robotics and vision-based applications. In this paper, we present a framework on graph to uncover relationships in different objects in the scene for reasoning about pedestrian intent. Pedestrian intent, defined as the future action of crossing or not-crossing the street, is a very crucial piece of information for autonomous vehicles.
  arXiv  Detail & Related papers  (2020-02-20T18:50:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.