Pedestrian trajectory prediction in multiple scenarios is of immense importance in autonomous driving and disentanglement of human behavior but is limited in catching human intention and initiative. Most previous works tend to predict the trajectory using only 2D coordinates, which generally cause two common problems: a) Overlooking the subjective initiative, including sudden swerve and erratic movement; b) A potential challenge called abnormal collision caused by unlabeled pedestrians on dataset is not being identified and resolved, which would ruin the model prediction. To break those limitations, we introduce visual localization and orientation as Visual Intention Knowledge to help the trajectory prediction, which is learned directly from visual scenarios. It benefits to comprehend human intention and formulates decision-making processes. Moreover, by learning from the visual information and decision-making policy, we construct the Visual Intention Knowledge associated spatio-temporal Transformer (VIKT) to predict human trajectory by combining the intention knowledge with the novel Transformer. Extensive experimental results demonstrate that our VIKT model could achieve competitive performance by the Visual Intention Knowledge through optimizing the model prediction compared with state-of-the-art methods in terms of prediction accuracy on ETH/UCY and SDD benchmarks.
Visual Exposes You: Pedestrian Trajectory Prediction Meets Visual Intention
IEEE Transactions on Intelligent Transportation Systems ; 24 , 9 ; 9390-9400
2023-09-01
2314867 byte
Article (Journal)
Electronic Resource
English
Pedestrian intention estimation and trajectory prediction based on data and knowledge‐driven method
Wiley | 2024
|Pedestrian intention estimation and trajectory prediction based on data and knowledge‐driven method
DOAJ | 2024
|Driver intention prediction and intention trajectory updating method
European Patent Office | 2023
|