Hello every one, I am new here.
I am using Pytorch for depth prediction through the paper ‘Deeper depth prediction by Lanina et al.’, I have to take video from AR Drone 2.0 and convert that to frames/images and then do the depth prediction on each image taken from the video. Afterwards depth map which is the output of neural network will be fed to RGBD SLAM along with its corresponding RGB image.
Can some one help me with that.
Regards.
If you want to Convert the Video into frames/images then you might try Online tools for this purpose. There are several tools that can solve your problem. But according to my opinion you should try YTB Converter Free for this purpose. As, it can easily convert the video into frames and images so you can go into the depth of each image. It contains many tools which might help you.
Here is a link to it: https://ytbconverterfree.com/youtube-downloader-online-free