Excluding blobs / petri dish borders

[piotrvidal]

Hi :)

Great software. Is there any way to prevent the sides of the petri dish from being identified as blobs? Or to click on them an "exclude" them somehow?

I've tried:

• increasing threshold (this works but also decreases the detection of the animals on the plate)
• modifying the video beforehand by adding a circular mask to get rid of the petri dish borders (this also works but it'd be very time consuming when using many plates)
• using the categorize feature to train a model by telling the network which blobs are animals and which are just borders, but for some reason it keeps showing me plate borders identified as "isopod" in the "category/skip" tile selector

EDIT: I'm sure this is a user thing. I'm going over the documentation again and again but I'm unable to find a way out so that's why I decided to drop a message.

[piotrvidal]

I just realized that I could simply exclude those undesired blobs from the .csv for my data representations. It would still be a cool feature being able to select a specific blob and tell TRex to ignore it.

[mooch443]

Hey! There is a function that could help you with that. While you're in tracking view (like in your screenshots) simply CTRL/CMD+lef-click any (empty) point in the image. If you chain those clicks, you'll get a (convex) polygon that you can exclude from tracking. Be aware though that convex is currently the constraint here. You will need to add multiple boxes for a round shape! An alternative that I haven't used in a while is to use -cam_circle_mask during conversion. Let me know if that still works... You'll need to use -crop_window before conversion to crop the video so that it cuts off exactly at the borders. Only works for one petri dish though. If you need the same values multiple times, then you can copy the values from the terminal to -crop_offsets for the next program start.

Good point though. I'll add this to documentation and include a part about this topic there. Thanks!