Normally, babies are pretty unsubtle about being hungry, and loudly announce their needs to the world. But it turns out that crying is a lagging indicator of hunger, and that there are a host of face, head, and hand cues that precede the wailing. [Caleb] based his system on Google’s MediaPipe library, using his baby monitor’s camera to track such behaviours as lip-smacking, pacifier rejection, fist mouthing, and rooting, all signs that someone’s tummy needs filling. By putting together a system to recognize these cues and assign a weight to them, Caleb now gets a text before the baby gets to the screaming phase, to the benefit of not only the little nipper but to his sleep-deprived servants as well.
From Caleb: “I wanted to put this out and see if the idea had legs before spending any more time on it. Makes sense to open source it if ultimately I don’t want to pursue the idea further”. So it appears it is not going out as open source, unfortunately.
See https://hackaday.com/2022/07/23/machine-learning-baby-monitor-prevents-the-hunger-games/
#technology #machinelearning #babies