[Juicyy]

very easily. here is the lecture from my robotics course. Amazing professor. Dr. Sodemann was the best I had in my lifetime. https://robogrok.com/1-2-3_Cameras_and_Color.php

Its actually easier than you would expect! you can use a process in image processing called "thresholding" where you basically filter the RGB or color values. Its very common and a little "hack" on compute. Computers "look" at images or video by converting the camera data into large matrices. Red would be 1 matrix, blue another, green another. Instead of this, you typically convert it to black and white but you can do any color you want, depending what youre looking for. This reduces your compute from 3 matrixes to 1 and makes your functions exponentially faster. Someone can help me on O(n) notation lol.

[IshKebab]

You're talking about different things.

Computer vision to detect red and green blocks in a controlled environment is completely trivial.

Driving a robot with human hands to pick up and manipulate blocks is still advanced research.

[refulgentis]

Fascinating...my most recent deep work was around color so this really tickled me, ty!