Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.08016 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916649482846208 |
|---|---|
| author | Ghiya, Akshat AlShami, Ali K. Kalita, Jugal |
| author_facet | Ghiya, Akshat AlShami, Ali K. Kalita, Jugal |
| contents | Predicting pedestrian trajectories is essential for autonomous driving systems, as it significantly enhances safety and supports informed decision-making. Accurate predictions enable the prevention of collisions, anticipation of crossing intent, and improved overall system efficiency. In this study, we present SGNetPose+, an enhancement of the SGNet architecture designed to integrate skeleton information or body segment angles with bounding boxes to predict pedestrian trajectories from video data to avoid hazards in autonomous driving. Skeleton information was extracted using a pose estimation model, and joint angles were computed based on the extracted joint data. We also apply temporal data augmentation by horizontally flipping video frames to increase the dataset size and improve performance. Our approach achieves state-of-the-art results on the JAAD and PIE datasets using pose data with the bounding boxes, outperforming the SGNet model. Code is available on Github: SGNetPose+. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08016 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SGNetPose+: Stepwise Goal-Driven Networks with Pose Information for Trajectory Prediction in Autonomous Driving Ghiya, Akshat AlShami, Ali K. Kalita, Jugal Computer Vision and Pattern Recognition Predicting pedestrian trajectories is essential for autonomous driving systems, as it significantly enhances safety and supports informed decision-making. Accurate predictions enable the prevention of collisions, anticipation of crossing intent, and improved overall system efficiency. In this study, we present SGNetPose+, an enhancement of the SGNet architecture designed to integrate skeleton information or body segment angles with bounding boxes to predict pedestrian trajectories from video data to avoid hazards in autonomous driving. Skeleton information was extracted using a pose estimation model, and joint angles were computed based on the extracted joint data. We also apply temporal data augmentation by horizontally flipping video frames to increase the dataset size and improve performance. Our approach achieves state-of-the-art results on the JAAD and PIE datasets using pose data with the bounding boxes, outperforming the SGNet model. Code is available on Github: SGNetPose+. |
| title | SGNetPose+: Stepwise Goal-Driven Networks with Pose Information for Trajectory Prediction in Autonomous Driving |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.08016 |