About this document
PIP-Net Pedestrian Intention Prediction in The Wild by refaat.fathy2020 is a document available to read on EtoBox.
The document presents PIP-Net, a novel framework for predicting pedestrian crossing intentions in real-world urban scenarios using Autonomous Vehicles (AVs). It leverages kinematic data and spatial features, employing a recurrent and temporal attention-based model that outperforms existing methods. Additionally, the study introduces the Urban-PIP dataset, which includes multi-camera annotations, enhancing the model
- Author
- refaat.fathy2020
- Language
- EN