Assisted child-minding based on visual activity monitoring in a home camera surveillance system

• Main Author: Lee, Leonard Kok Yong.
• Other Authors: Cham Tat Jen
• Format: Final Year Project
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
• Online Access: http://hdl.handle.net/10356/52088
• Institution: Nanyang Technological University

Constant attention and supervision are required when you have a baby or a toddler at home. Still fresh and unknown to their environment, these kids have high curiosity and energy to explore their surroundings and the stuffs around them. Careful parents would try their best to child‐proof or baby‐proof their house by removing their glass table or vase so as to not let any accident happen to their beloved kids. But even without dangerous items around the house, unintentional injuries still occurs (E.g. hitting head on the crib). Parents or child minders can’t possibly watch the kids 24/7. There will be times where the call of nature has to be answered, where dinner has to be cooked, and the toddler has to be left on his or her own for a while. The objective of this project was to explore the possibilities of creating a camera surveillance with the help of the OpenCV Libraries. By exploring a couple of functionalities the OpenCV library has, the camera surveillance will be equipped with tracking functionalities and will be able to notify the parents or child minder if the child is near any dangerous part of the room or even the house (based on the position of the camera and the number of cameras) by sounding out an alarm.