Deep Learning Baby Monitor Keeps an Eye on Your Crib

[HardOCP News]

Studies have shown that the risk of SIDS increases in infants who sleep on their stomachs, but it’s not always possible for parents to monitor their infant’s sleep. As an engineer in search of a solution, Lui’s instinct was to turn to technology. Using NVIDIA DIGITS, the Caffe deep learning framework and NVIDIA Tesla GPUs, Lui started building BabbyCam, a baby monitor based in deep learning. Initially, Lui trained the machine to determine if a baby was present in its crib, developing its recognition ability by feeding it thousands of downloaded images. He then trained it to distinguish whether the baby was on its stomach, and from there created the activity labels of “no baby,” “baby asleep,” “baby awake,” “baby crying” and “face covered.” Parents can enable email and text alerts for any of the latter four.

 

[Twisted Kidney]

Having five kids I can honestly say that "baby awake" never once required a text message.

 

[ChefJeff789]

Having five kids I can honestly say that "baby awake" never once required a text message.

Can corroborate this. It's also definitely not necessary to indicate baby crying or baby asleep.

 

[Pieter3dnow]

Now only if it only could raise your child using proper manners that would be something parents would pay for

 

[Uvaman2]

SIDS, can't imagine that beyond-horror situation.. I am not sure anyone really knows BS about what causes it, stomach or no stomach.
My second one, nothing you would do will get her out of the sleeping in the stomach, she will flip right over as soon as she got a bit of strength.

 

[Galvin]

Every 10 years it changes to what was good is now bad, and vice versa.