VIT-Ped: Visionary Intention Transformer for Pedestrian Behavior Analysis
By: Aly R. Elkammar, Karim M. Gamaleldin, Catherine M. Elias
Potential Business Impact:
Helps self-driving cars predict where people will walk.
Pedestrian Intention prediction is one of the key technologies in the transition from level 3 to level 4 autonomous driving. To understand pedestrian crossing behaviour, several elements and features should be taken into consideration to make the roads of tomorrow safer for everybody. We introduce a transformer / video vision transformer based algorithm of different sizes which uses different data modalities .We evaluated our algorithms on popular pedestrian behaviour dataset, JAAD, and have reached SOTA performance and passed the SOTA in metrics like Accuracy, AUC and F1-score. The advantages brought by different model design choices are investigated via extensive ablation studies.
Similar Papers
TrajFusionNet: Pedestrian Crossing Intention Prediction via Fusion of Sequential and Visual Trajectory Representations
CV and Pattern Recognition
Helps self-driving cars guess if people will cross.
Intention-Aware Diffusion Model for Pedestrian Trajectory Prediction
CV and Pattern Recognition
Helps self-driving cars guess where people will walk.
Pedestrian Intention Prediction via Vision-Language Foundation Models
CV and Pattern Recognition
Helps self-driving cars guess when people will cross.