Fall Detection through Video Surveillance using CNN

Computer Engineering

There has been an exponential increase in the number of elderly people living alone. This is mainly due to the increasing number of nuclear families that have been abandoning their parents. This has forced them to take care of themselves, which is a herculean task when a person is very old. Added to this epidemic, old people are highly susceptible to balance issues due to weak musculature. It is a very deadly combination that can lead to some seriously fatal falls. The elderly people are also more prone to get severely affected by these falls and some can also be fatal. Therefore, an innovative system is proposed, that utilizes image processing for the purpose of detection of falls and provides a constant vigilance on the subject. This novel approach is made possible due to the integration of Convolutional Neural Networks and the region of interest to evaluate each frame efficiently to ascertain the fall. As soon as the fall is detected, the neighbors, relatives and the emergency services that can provide much-needed lifesavingassistance.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.