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

• Main Author: Sruthi Inbavanan
• Other Authors: Cham Tat Jen
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
• Online Access: http://hdl.handle.net/10356/59904
• Institution: Nanyang Technological University

In today’s fast-paced world, adults are having less and less time to stay home and take care of their children throughout a day. Child care is increasingly becoming a challenging task. Lack of the caretaker’s attention, can lead to high risks of accidents when caring for a child. This project aims to create a system to alleviate this problem and help assist the person taking care of the child and allow him/her to focus on other tasks. Using the home surveillance system input sequences, this project targets at developing an interactive and semi-automated system to help track the child. A vision-based tracking capability is implemented to help track and monitor the child’s movements. Additionally, the user will be notified if the child enters restricted areas and hence the child minder will be able to act immediately and move the child away from danger. Various image processing and computer vision techniques available have been analysed. The efficiency and performance rates have been compared and conclusive decisions have been drawn based on the observations to improve the efficiency of the system.