Pedestrian trajectory prediction with convolutional neural networks

作者：

Highlights：

• New convolutional model achieves state-of-the-art results on ETH and TrajNet datasets.

• Random rotations and Gaussian noise are the best data augmentation techniques.

• Coordinates with the origin in the last observation point better represent trajectory.

摘要

•New convolutional model achieves state-of-the-art results on ETH and TrajNet datasets.•Random rotations and Gaussian noise are the best data augmentation techniques.•Coordinates with the origin in the last observation point better represent trajectory.

论文关键词：Trajectory prediction,Pedestrian prediction,Convolutional neural networks

论文评审过程：Received 8 October 2020, Revised 3 August 2021, Accepted 11 August 2021, Available online 13 August 2021, Version of Record 19 August 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108252