Dene33 / Video_to_bvh
Convert human motion from video to .bvh
Stars: ✭ 222
Labels
Projects that are alternatives of or similar to Video to bvh
Data Augmentation For Wearable Sensor Data
A sample code of data augmentation methods for wearable sensor data (time-series data)
Stars: ✭ 222 (+0%)
Mutual labels: jupyter-notebook
Navigan
Navigating the GAN Parameter Space for Semantic Image Editing
Stars: ✭ 221 (-0.45%)
Mutual labels: jupyter-notebook
Scikit Geometry
Scientific Python Geometric Algorithms Library
Stars: ✭ 220 (-0.9%)
Mutual labels: jupyter-notebook
Melusine
Melusine is a high-level library for emails classification and feature extraction "dédiée aux courriels français".
Stars: ✭ 222 (+0%)
Mutual labels: jupyter-notebook
Vqa demo
Visual Question Answering Demo on pretrained model
Stars: ✭ 222 (+0%)
Mutual labels: jupyter-notebook
Paperboy
A web frontend for scheduling Jupyter notebook reports
Stars: ✭ 221 (-0.45%)
Mutual labels: jupyter-notebook
Ai Platform Samples
Official Repo for Google Cloud AI Platform
Stars: ✭ 222 (+0%)
Mutual labels: jupyter-notebook
Natural Language Processing With Tensorflow
Natural Language Processing with TensorFlow, published by Packt
Stars: ✭ 222 (+0%)
Mutual labels: jupyter-notebook
Deep Vector Quantization
VQVAEs, GumbelSoftmaxes and friends
Stars: ✭ 222 (+0%)
Mutual labels: jupyter-notebook
Htmresearch
Experimental algorithms. Unsupported.
Stars: ✭ 221 (-0.45%)
Mutual labels: jupyter-notebook
Ownphotos
Self hosted alternative to Google Photos
Stars: ✭ 2,587 (+1065.32%)
Mutual labels: jupyter-notebook
Neural Style Painting
Implementing of the "A Neural Algorithm of Artistic Style"
Stars: ✭ 219 (-1.35%)
Mutual labels: jupyter-notebook
Triplet Attention
Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]
Stars: ✭ 222 (+0%)
Mutual labels: jupyter-notebook
Dl For Chatbot
Deep Learning / NLP tutorial for Chatbot Developers
Stars: ✭ 221 (-0.45%)
Mutual labels: jupyter-notebook
Sec
Seed, Expand, Constrain: Three Principles for Weakly-Supervised Image Segmentation
Stars: ✭ 221 (-0.45%)
Mutual labels: jupyter-notebook
Lfortran
Official mirror of https://gitlab.com/lfortran/lfortran. Please submit pull requests (PR) there. Any PR sent here will be closed automatically.
Stars: ✭ 220 (-0.9%)
Mutual labels: jupyter-notebook
Covid 19
Ciência de Dados aplicada à pandemia do novo coronavírus.
Stars: ✭ 223 (+0.45%)
Mutual labels: jupyter-notebook
Ipython Notebooks
A collection of IPython notebooks covering various topics.
Stars: ✭ 2,543 (+1045.5%)
Mutual labels: jupyter-notebook
video_to_bvh
Convert human motion from video to .bvh with Google Colab
Usage
1. Open video_to_bvh.ipynb in Google Colab
- Go to https://colab.research.google.com
-
File
>Upload notebook...
>GitHub
>Paste this link:
https://github.com/Dene33/video_to_bvh/blob/master/video_to_bvh.ipynb - Ensure that
Runtime
>Change runtime type
isPython 3
withGPU
2. Initial imports, install, initializations
Second step is to install all the required dependencies. Select the first code cell and push shift+enter
. You'll see running lines of executing code. Wait until it's done (1-2 minutes).
3. Upload video
- Select the code cell and push
shift+enter
- Push
select files
button - Select the video you want to process (it should contain only one person, all body parts in frame, long videos will take a lot of time to process)
4. Process the video
- Specify desired
fps
rate at which you want to convert video to images. Lower fps = faster processing - Select the code cell and push
shift+enter
This step does all the job:
- Convertion of video to images (images are required for pose estimation to work)
- 2d pose estimation. For each image creates corresponding .json file with 2djoints with format similar to output .json format of original openpose. Fork of keras_Realtime_Multi-Person_Pose_Estimation is used.
- 3d pose estimation. Creates .csv file of all the frames of video with 3d joints coordinates. Fork of End-to-end Recovery of Human Shape and Pose
- Convertion of estimated .csv files to .bvh with help of custom script with .blend file.
5. Download .bvh
- Select the code cell and push
shift+enter
.bvh will be saved to your PC. - If you want preview it, run Blender on your PC.
File
>Import
>Motion Capture (.bvh)
>alt+a
6. Clear all the generated data if you want to process new video
- Select the code cell and push
shift+enter
.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].