scaelles / OSVOS-TensorFlow

One-Shot Video Object Segmentation
http://vision.ee.ethz.ch/~cvlsegmentation/osvos/
GNU General Public License v3.0
438 stars 132 forks source link

For video #22

Closed Raj7kumar7 closed 6 years ago

Raj7kumar7 commented 6 years ago

Hello Nice work.If we need to do segmentation for a video what should i do? Kindly help.

scaelles commented 6 years ago

Hello, Once you have a video sequence, you have to extract its frames. Then, you have to annotate manually the segmentation mask of the object that you want to segment in the first frame of the video. After that, you can use our method to perform the segmentation in all the other frames of the video. In order to extract the frames and then to create a video again with the segmentation results, I would recommend you using ffmpeg. Let us know if you have any further question.