2022.1 Introduces a critical fix and an essential feature for teams experimenting with ball tracking.
Bugfixes
-
We acquired information from one of our suppliers about an issue (and a fix!) that affects roughly 1/75 of the CPUs specifically used in Limelight 2 (it may be related to a specific batch). It makes sense, and it was one of the only remaining boot differences between the 2022 image and the 2020 image.
-
Fix the upload buttons for GRIP inputs and SolvePNP Models
Features
Hue rainbow and inversion
- The new hue rainbow makes it easier to configure the hue threshold. Here’s an example of filtering for blue pixels:
- The new hue inversion feature is a critical feature if you want to track red objects, as red is at both the beginning and the end of the hue range:
- If you’re trying to track balls, the aspect ratio filter (set a tight range around “1”) and the fullness filter (you want above 70%) should work quite well. Explicit “circle” filtering is relatively slow and wont work as well as people assume. Gifs of ball tracking will be posted later today.
New Python libraries
- We’ve added scipy, scikit-image, pywavelets, pillow, and pyserial to our python sandbox. I wonder what everyone’s planning given the recent feature requests
