pytorch-openpose-master
所属分类：人工智能/神经网络/深度学习
开发工具：Python
文件大小：3053KB
下载次数：9
上传日期：2020-03-17 16:50:28
上 传 者：
linmi
说明： 本例程是我研究生阶段做的一个小项目，该项目用pytorch的深度学习框架来进行人体姿态识别，能够实现头部和身体的骨架识别！图像处理方面加入了OpenCV包进行相关的处理，希望能帮助大家！
(175/5000
This routine is a small project that I did in the graduate stage. The project uses pytorch's deep learning framework to recognize human body posture, and can realize skeleton recognition of head and body! In the aspect of image processing, OpenCV package has been added for relevant processing, hoping to help everyone!)
文件列表:
.idea (0, 2020-03-08)
.idea\dataSources (0, 2019-11-27)
.idea\misc.xml (320, 2020-01-13)
.idea\modules.xml (305, 2019-11-25)
iml (556, 2020-01-13)
.idea\workspace.xml (15715, 2020-03-08)
demo.py (1534, 2019-10-14)
demo_camera.py (1429, 2019-12-01)
example.py (491, 2019-12-01)
images (0, 2020-01-13)
images\body_preview.jpg (1076132, 2019-10-14)
images\body_preview_estimation.jpg (159628, 2019-10-14)
images\body_preview_keypoints.jpg (140649, 2019-10-14)
images\dance.jpg (31276, 2019-11-27)
images\demo.jpg (16334, 2019-10-14)
images\demo_preview.png (153723, 2019-10-14)
images\detect_hand_preview.jpg (60693, 2019-10-14)
images\hand.jpg (8717, 2019-10-14)
images\hand_preview.png (75507, 2019-10-14)
images\hand_preview_estimation.png (56644, 2019-10-14)
images\keypoints_hand.png (185529, 2019-10-14)
images\keypoints_pose_18.png (11153, 2019-10-14)
images\skeleton.jpg (159442, 2019-10-14)
images\ski.jpg (305923, 2019-10-14)
notebooks (0, 2020-01-13)
notebooks\detectHand.ipynb (158167, 2019-10-14)
notebooks\hand.ipynb (696400, 2019-10-14)
notebooks\network_graph.ipynb (76187, 2019-10-14)
output1.avi (7734, 2019-12-01)
python (0, 2020-01-13)
python\__pycache__ (0, 2020-01-13)
python\__pycache__\body.cpython-37.pyc (7219, 2019-12-01)
python\__pycache__\hand.cpython-37.pyc (2979, 2019-12-01)
python\__pycache__\model.cpython-37.pyc (5860, 2019-11-29)
python\__pycache__\util.cpython-37.pyc (6219, 2019-11-27)
python\body.py (10955, 2019-11-29)
python\dance.jpg (31276, 2019-11-27)
python\hand.py (3403, 2019-10-14)
python\hand_model_output_size.json (13902, 2019-10-14)
... ...
## pytorch-openpose
pytorch implementation of [openpose](https://github.com/CMU-Perceptual-Computing-Lab/openpose) including **Body and Hand Pose Estimation**, and the pytorch model is directly converted from [openpose](https://github.com/CMU-Perceptual-Computing-Lab/openpose) caffemodel by [caffemodel2pytorch](https://github.com/vadimkantorov/caffemodel2pytorch). You could implement face keypoint detection in the same way if you are interested in. Pay attention to that the face keypoint detector was trained using the procedure described in [Simon et al. 2017] for hands.
openpose detects hand by the result of body pose estimation, please refer to the code of [handDetector.cpp](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/src/openpose/hand/handDetector.cpp).
In the paper, it states as:
```
This is an important detail: to use the keypoint detector in any practical situation,
we need a way to generate this bounding box.
We directly use the body pose estimation models from [29] and [4],
and use the wrist and elbow position to approximate the hand location,
assuming the hand extends 0.15 times the length of the forearm in the same direction.
```
If anybody wants a pure python wrapper, please refer to my [pytorch implementation](https://github.com/Hzzone/pytorch-openpose) of openpose, maybe it helps you to implement a standalone hand keypoint detector.
Don't be mean to star this repo if it helps your research.
### Model Download
* [dropbox](https://www.dropbox.com/sh/7xbup2qsn7vvjxo/AABWFksdlgOMXR_r5v3RwKRYa?dl=0)
`*.pth` files are pytorch model, you could also download caffemodel file if you want to use caffe as backend.
### Todo list
- [x] convert caffemodel to pytorch.
- [x] Body Pose Estimation.
- [x] Hand Pose Estimation.
- [ ] Performance test.
- [ ] Speed up.
### Demo
#### Skeleton
#### Body Pose Estimation
#### Hand Pose Estimation
#### Body + Hand
### Citation
Please cite these papers in your publications if it helps your research (the face keypoint detector was trained using the procedure described in [Simon et al. 2017] for hands):
```
@inproceedings{cao2017realtime,
author = {Zhe Cao and Tomas Simon and Shih-En Wei and Yaser Sheikh},
booktitle = {CVPR},
title = {Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields},
year = {2017}
}
@inproceedings{simon2017hand,
author = {Tomas Simon and Hanbyul Joo and Iain Matthews and Yaser Sheikh},
booktitle = {CVPR},
title = {Hand Keypoint Detection in Single Images using Multiview Bootstrapping},
year = {2017}
}
@inproceedings{wei2016cpm,
author = {Shih-En Wei and Varun Ramakrishna and Takeo Kanade and Yaser Sheikh},
booktitle = {CVPR},
title = {Convolutional pose machines},
year = {2016}
}
```
近期下载者：
相关文件：
收藏者：