Python + OpenCv
Fall detector with an overhead webcam - part 2 (work in progress)

Check out the first part here

This is the second version of a fall detector, for a course called Linux project at Haaga-Helia UAS. In this version there are a few new features.
Current detection time period is 50 frames (~10 seconds):

The program detects if the person is not moving for a time period. This is probably a better way to detect if a person needs help than detecting when the person fall. In a real situation the time period would be set around 2 minutes if the person is on the floor. For the sofa there could be a limit of two hours and for the bed there could be a limit of 12 hours. There are currently not different detection times for the sofa or a bed.

On the detection area there are different values. First is the person id, second frames since person last moved and on the bottom detection area size.

Detecting two persons at the same time (+smelly feet):

Demonstrating loggin the alerts to a webservice (on the feed the person gets id 7):

Further updates will be available at ResearchGate.

Kim Salmi