Algorithm to measure sleep hours of a patient

asked 2015-05-30 02:14:46 -0500

Katrina_V gravatar image

Hi, I am a doctor and recently learnt basics of opencv. I wanted to use opencv ( by analysing the video feed from a camera attached in the room) to measure the sleeping hours of a patient in my hospital - time for which the patient is awake, roaming around and time for which he sleeping on bed. There is a nurse as well moving around in the room sometimes. Can you please tell me the way in which I can solve the problem. I tried using the Zdenek Kalal's predator algorithm but its computationally heavy and I have some other analytics also running sideways. Please help me.

edit retag flag offensive close merge delete

Comments

Not an easy problem in my opinion. Even if you want to measure only the sleeping time, it is hard to measure the time when the patient sleeps over the time when the patient just lies in the bed.

Depends also if you can use other type of sensors or if you can only use a camera. By the way, if the room is completly dark, a camera will not work (you have to use an infrared camera).

In my opinion, if you can restrict your problem to time during the patient is on the bed vs time during the patient is not on the bed:

  • I would use a Kinect sensor placed directly above the bed, calibrated with the depth when there is nobody to detect if there is something on the bed
  • a pressure sensor under the bed, a smart wristband to record patient activity, a smartphone in ...
(more)
Eduardo gravatar imageEduardo ( 2015-05-30 10:05:44 -0500 )edit
1

The Kinect sensor seems the easiest solution in my opinion. It embeds a depth sensor and an RGB camera and it works in the dark. Located in the ceiling, the depth data could tell you / detect the posture of the patient. The RGB data could be used to detect motion, or for visual monitoring.

You can also check the litterature on this subject on google scholar, or in specific medicine journals or ask your colleagues.

For Kinect:

Eduardo gravatar imageEduardo ( 2015-05-30 10:31:20 -0500 )edit

Thanks Eduardo, links seem to be quite useful, I will take a look at it :)

Katrina_V gravatar imageKatrina_V ( 2015-06-03 04:41:17 -0500 )edit