Train on my own dataset without superpixels

[ron-weiner]

First of all, great work! I assume that in order to use it I have to train the weights on a dataset with superpixels annotations, or at least some boundry boxes. Am I right? What do you suggest me to do if now I have lots of clean videos which I want to make segmentation on some features that are moving in the video? Should I start with simple boundary boxes classification and only than proceed? or that there is any shortcut for that?

Thanks

[warmspringwinds]

Hi @ron-weiner

You can try this software to create training data: https://github.com/wkentaro/labelme

and then train using our library

Let me know if you have any further questions :)

[ron-weiner]

Thank you @warmspringwinds , it is a great tool! Unfortunately I need to do it on a huge amount of data and the only option that I see is to get bunch of people to label it all. If i wish make segmentation on moving objects in a video? Do you have another lead besides that? I started using "https://www.learnopencv.com/object-tracking-using-opencv-cpp-python/" but I wish to have a great segmentation such as yours

[warmspringwinds]

@ron-weiner I will have a look if such tool exists :)

Or if you find something better by that time, I would also be interested in the way you approached your problem.

Thank you.

[ron-weiner]

For sure, I will let you know! Thank you!