Repository files navigation

Convert human motion from video to .bvh with Google Colab

1. Go tohttps://colab.research.google.com
2. File >Upload notebook... >GitHub >Paste this link:https://github.com/Dene33/video_to_bvh/blob/master/video_to_bvh.ipynb
3. Ensure thatRuntime >Change runtime type isPython 3 withGPU

Second step is to install all the required dependencies. Select the first code cell and pushshift+enter. You'll see running lines of executing code. Wait until it's done (1-2 minutes).

1. Select the code cell and pushshift+enter
2. Pushselect files button
3. 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)

1. Specify desiredfps rate at which you want to convert video to images. Lower fps = faster processing
2. Select the code cell and pushshift+enter

This step does all the job:

1. Convertion of video to images (images are required for pose estimation to work)
2. 2d pose estimation. For each image creates corresponding .json file with 2djoints with format similar to output .json format of originalopenpose.Fork ofkeras_Realtime_Multi-Person_Pose_Estimation is used.
3. 3d pose estimation. Creates .csv file of all the frames of video with 3d joints coordinates.Fork ofEnd-to-end Recovery of Human Shape and Pose
4. Convertion of estimated .csv files to .bvh with help ofcustom script with.blend file.

1. Select the code cell and pushshift+enter .bvh will be saved to your PC.
2. If you want preview it, runBlender on your PC.File >Import >Motion Capture (.bvh) >alt+a

1. Select the code cell and pushshift+enter.