Tango in a dark setting -

For the ATAP team:

My Yellowstone device has an IR filter on the fish-eye Camera lens . I have watched Tango in a deep room by filling the water with the IR light. Color exposes camera room (as grayscale), and fishes does not show anything (just a black image). Tango service does not work in this setting.

How important is the eyes of fish for the visual odomi? I am thinking that the fish will be able to give the correct position / orientation reading to the Tango service by removing the IR filter from the eye lens. But this is my expensive operation to Tango, so I wanted to ask the question before doing it.

FII, Tango service in this setting gives status messages such as "FishIndex underpaced" and perhaps the Tango service has stopped trying to make Visual Odomi in this situation (even if the RGB-IR camera room Can see as grayscale). So to take out the Tango service, I had a small pencil and amp; Raised in this fish-eye camera. It has got rid of the underexposure situation, but this is the correct orientation & amp; Event. Tango was still quite lost. As much as I can tell, no visual odometry is done with the RGB-IR camera (i.e. Fishey does all this) ... or the camera frames burned by the IR are not acceptable for odomime (probably color natural Is necessary for the facility recognition ???).

How can Tango team IR light alone provide information about how a visual odometer can be done in a dark room? Or is it even possible?