Fall Detection and Daily Living Activity Recognition in Python

There is an ever-increasing need for automated monitoring systems to enable independent living in today's elderly population. Human fall detection is widely researched within the field of assistive technologies. However, fall detection systems based on wearable sensors is often incapacitated by inadvertent neglect to wear the sensors. Computer vision based approaches to detect a human fall in video holds promise. It has been noted that an informative yet compact representation schema can significantly improve the performance of video understanding. For human activity recognition, Extended CORE9 has been used for obtaining a qualitative spatial description of the video activity. The spatial description of an activity obtained using Extended CORE9 along with the temporal information can be encoded within a graph structure. Extended CORE9 has been applied for human-human and human-object interactions. In this paper, we show how Extended CORE9 can be applied for single-person activities. We evaluate our approach for detecting fall in an assisted living environment. Experiments performed on the UR Fall Detection dataset shows promising results.