Child Presence Detection for Child Safety with Deep Neural Networks

Abstrak

Accidents and injuries to children often occur due to lack of supervision. This research develops a child presence detection system using Computer Vision technology and the Age Estimation method to improve child safety in dangerous areas. The system was tested with a Canon EOS M50 camera at various distances, camera heights, and light intensity. The analysis using anova obtained a data confidence level of 95% for light intensity, and the age estimation method showed performance with a success of 84.72%. This research can be applied to supervise and improve safety in children, especially outdoors.