Source code derived from: [Duan's Repository]
Requirements: The following packages were imported in a Linux Environment:
- PyTorch >= 1.0. Installation instructions can be found at https://pytorch.org/get-started/locally/
- opencv-python
- Pycocotools -> pycocotools
- tqdm
- Clone my repository
- Download the pre-trained network weights, which is trained on COCO, MW-R and HABBOF, and place it under the RAPiD/weights folder. If running in Virtualbox Machine in Ubuntu:
- Refer to OpenCV Installation to install openCV on Ubuntu.
- Run
workon -openCV setup name-in terminal. - Directly run
python main.pyorpython3 main.pyin terminal.
Z. Duan, M.O. Tezcan, H. Nakamura, P. Ishwar and J. Konrad,
“RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images”,
in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
Omnidirectional Computer Vision in Research and Industry (OmniCV) Workshop, June 2020.