search

imatge-upc / rvos

RVOS: End-to-End Recurrent Network for Video Object Segmentation (CVPR 2019)
https://imatge-upc.github.io/rvos/
Other
277 stars 54 forks source link

Handling new objects entering the video #26

Open dl002 opened 4 years ago

dl002 commented 4 years ago

Thank you for sharing your code. The code is working if you have masks for all objects provided for the first frame. If some objects are appearing halfway through the video, how do I give the mask for that? I know I can give the mask for the first frame with -mask_path, how do I give the mask for new object entering at, say, 20th frame.

carlesventura commented 4 years ago

The code is not ready for this scenario. However, you could process all frames until say the 20th frame (no new objects entering), save the predictions at 20th frame, and then run again RVOS from 20th frame as starting point using the mask of the new entering object and the prediction masks for the other objects in the video already processed.