Object detection, 3D detection, and pose estimation using center point detection:
Objects as Points,
Xingyi Zhou, Dequan Wang, Philipp Krähenbühl,
arXiv technical report (arXiv 1904.07850)
This project is based on original CenterNet - Objects as Points from https://github.com/xingyizhou/CenterNet. I added some customizations to train CenterNet on BDD100k dataset for my advanced driver-assistance system project. The detailed training result can be found at this blog post.
Notice that this repository was modified using this instruction and should only be used for converting models to ONNX format. Pay attention to use right version of PyTorch for this repository (v1.0 or v1.1 instead of v0.4.1 like in training environment).
Please use original repository or this repository to train models.
CenterNet itself is released under the MIT License (refer to the LICENSE file for details). Portions of the code are borrowed from human-pose-estimation.pytorch (image transform, resnet), CornerNet (hourglassnet, loss functions), dla (DLA network), DCNv2(deformable convolutions), tf-faster-rcnn(Pascal VOC evaluation) and kitti_eval (KITTI dataset evaluation). Please refer to the original License of these projects (See NOTICE).
If you find this project useful for your research, please use the following BibTeX entry.
@inproceedings{zhou2019objects,
title={Objects as Points},
author={Zhou, Xingyi and Wang, Dequan and Kr{\"a}henb{\"u}hl, Philipp},
booktitle={arXiv preprint arXiv:1904.07850},
year={2019}
}