Did you read the paper?
https://arxiv.org/pdf/2208.11215.pdf
Sorry, but lines like:
Figures 7 and 8 show the image and color charts of the phantom object. The object is present in
only one frame, which allows us to determine its speed of at least 52 degrees per second, taking into
account the angular dimensions of the frame.
don't inspire a lot of confidence...
And the whole claim that they can get distance from the color spectrum seems - to put it mildly- questionable...