Fast Trajectory End-Point Prediction with Event Cameras for Reactive Robot Control

If you use any of this data, please cite the following publication:

@inproceedings{monforte2023fast,  title={Fast Trajectory End-Point Prediction with Event Cameras for Reactive Robot Control},  author={Monforte, Marco and Gava, Luna and Iacono, Massimiliano and Glover, Arren and Bartolozzi, Chiara},  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},  pages={4035--4043},  year={2023}}

Event-based datasets of synthetic and real trajectories of a bouncing ball.

The synthetic trajectories were obtained converting frames taken using Unreal Engine to events. The ground truth is provided along with objects and camera settings.

The real trajectories wer dumped from a real event camera located in front of the robot workspace.

To import .log files containing events, we suggest bimvee Python library.

Specifically use the functions to import .log files:

data = importIitYarpBinaryDataLog(filePathOrName=input_path)