Are there any programming libraries or neural network design patterns designed for the task of finding persons in a photo/video and extracting their silhouettes (i.e. not only the rectangle containing the person but a bitmap marking which pixels are part of the person and which are background)?
Asked
Active
Viewed 761 times
-1
-
1You're looking for image or instance segmentation. – nbro Apr 27 '22 at 13:46
1 Answers
1
Check out pytorch/pyvision. This is wonderful in that it has many great models that are pretrained that you can use to train your model on and then go further and use what is trained to train further. It has bounding boxes, silhouettes, segmentation, etc.
https://medium.com/@ashishgupta_65016/semantic-segmentation-for-silhouette-extraction-e52c7d319295
https://pytorch.org/vision/main/auto_examples/plot_visualization_utils.html
I am sure there are many more options out there. This is just one that I am familiar with. Good luck!!
Jennifer Crosby
- 26
- 7