False detections at night / 1-channel greyscale issue?

I get lots of false detections from spider webs and moths etc at night in infrared.

[This](
https://medium.com/@anuj_shah/object-detection-in-infrared-3f247dc3708) article suggests that images from an infrared camera are single channel, while most models are trained on 3 channel RGB Images.

There is also [this](https://github.com/tensorflow/models/issues/3369) on tensorflow github with some more info if needed.

Solution as per the links appears to be to stack the single channel 3 times to form a 3-channel input.

Hopeful this is possible and not too much work :)


The issue names no files, tests, or entry points. Start by reviewing the linked infrared article and TensorFlow issue, then trace how camera frames reach the object-detection model. Done means evaluating whether single-channel infrared input can be handled without the reported false detections, with coverage for the supported input path.

Written by the indexing model from the issue text.