0
$\begingroup$

I'm looking for any recommended approaches to be able to digitally process a room full people, like an auditorium or a movie theater and output the following information:

Goals:

  1. How many people are in the room
  2. Locate unoccupied and available seating
  3. Display the available seating to ushers, or people attending late, on an iPad or TV outside the auditorium. Similar to viewing airplane seat occupancy online.

Sensors I'm considering:

  • LiDar Scanning
  • Many ceiling (IR) cameras looking straight down (or perpendicular to the seating if the seating is inclined)

Challenges: Be able to take accurate enough measurements when:

  • The lights are on
  • The lights are off or in low light
  • People are standing
  • People are sitting
  • Seating is a long bench, not a chair

Constraints:

  • Individual sensors for each seat isn't ideal, as we need to count people when they are standing as well.

Thoughts on LiDar:

I like the thought of scanning the room with LiDar to develop a 3D Map from which I can determine the number of prominent heads to count, and distance/location of each head to identify a seat that is taken or open.

Are there any affordable (under $10,000) LiDar scanners that make this easy?

Thoughts on Top Down Infrared (IR) Cameras :

The auditorium seats 700 people and has a balcony. If the cameras are positioned in a top-down perspective, we would need to install about 22 cameras. It would be nice to have less of an installation overhead.

Also, I'd like to respect the audience and not look down shirts.

Thoughts on 1 or 2 Infrared (IR) Cameras Viewing the Crowd from the stage:

This could work for counting faces (using OpenCV or other Computer Vision library) but would make it difficult to tell what seats are open and available, especially when people are standing.


Images of the Auditorium:

enter image description here enter image description here enter image description here

$\endgroup$
  • $\begingroup$ Looks like a church. You have pews. Try counting the number of people entering and leaving the pew at both ends. A simple “break the light beam” sensor might work, but bored children will probably investigate. People tend to be creatures of habit, so you can probably set a rough prior probability on how many people typically occupy a pew. $\endgroup$ – Stanley Pawlukiewicz Apr 12 '18 at 1:39
  • $\begingroup$ @StanleyPawlukiewicz That's a great suggestion and provides a new way to think about the problem/solution. Thanks Stanley. $\endgroup$ – aero Apr 12 '18 at 1:49
  • $\begingroup$ Another issue if you go with multiple cameras, is their field of view will overlap, so you can automate counting the number of people in each view, there will be double counts that you need to deconflict. To be honest, I wouldn’t count people, I would look for empty seats. People move, empty space doesn’t $\endgroup$ – Stanley Pawlukiewicz Apr 12 '18 at 2:16
  • $\begingroup$ You should also be aware that clothing is not opaque in some IR bands $\endgroup$ – Stanley Pawlukiewicz Apr 12 '18 at 2:39
  • $\begingroup$ @StanleyPawlukiewicz Overlapping counts is a good consideration. I was hoping to stitch the images together before counting... but overcounting could still occur. As for non-opaque clothing with IR... definitely something we would want to avoid! Thanks for pointing that out! $\endgroup$ – aero Apr 12 '18 at 16:21

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.