Inference on a video/webcam

una-dinosauria / human-motion-prediction

Simple baselines and RNNs for predicting human motion in tensorflow. Presented at CVPR 17.

MIT License

406 stars 140 forks source link

Inference on a video/webcam #50

Open babdulhakim2 opened 5 years ago

babdulhakim2 commented 5 years ago

Is it possible to parse video from file or IP camera using OpenCV and then get a prediction of the motion. I want to be able to classify an action in a video. Sorry, i'm new to computer vision. Thank you

una-dinosauria commented 5 years ago

Hi @babdulhakim2,

I am not sure what you mean by parsing in this context. Our code works with mocap data currently -- it could be extended to handle an online mocap system, but I don't think that would be trivial.

I recommend you go to http://openaccess.thecvf.com/ECCV2018.py and search for papers on action recognition/classification for pointers on your problem.

Cheers,

babdulhakim2 commented 5 years ago

Thank you for the feedback. will sure read more