F2DNet
2021-12-29 18:23:11
A two stage anchor free pedestrian detection model, based on HRNet backbone and feature pyramid network, center and scale head followed by fast suppression head.
| Method description: | A two stage anchor free pedestrian detection model, based on HRNet backbone and feature pyramid network, center and scale head followed by fast suppression head. |
| Computation Environment: | Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz, GTX1080Ti |
| Computation Time: | 4949.52 |
| Publication: | F2DNet: Fast Focal Detection Network for Pedestrian Detection |
| Authors: | Abdul Hannan Khan, Mohsin Munir, Ludger van Elst, Andreas Dengel |
| Publication Venue: | ICPR 2022 |
| Publication Link: | https://www.computer.org/csdl/proceedings-article/icpr/2022/09956732/1IHoOhBF9Li |
| Publication Code (Link): | https://github.com/AbdulHannanKhan/F2DNet |