0

I have an assignment about working with pictures that depth cameras take.

First thing first, this is how one of these pictures looks like.

depth 4

The way the camera works is that it represents objects in different tones of color depending on how far they are from the camera lens. The closer something is the brighter the color gets. Farther = darker of course.

My assignment is that I basically need to make a people counter for a depth camera that is located in an elevator.

What my idea is that I would basically like to convert the image to a 2D matrix of numbers and then apply a local maximum finder algorithm in order to find those heads sticking out towards the camera so I can count the people in that way.

So, my questions are - Is this an okay approach for someone who is not very experienced? What tools should I use for the conversion? Can I do all of this in C or should I use something more advanced?

I haven't had much experience outside of C but I'm open to trying maybe C# if it provides more advanced and better tools for the job.

All advice appreciated!

m69's been on strike for years
  • 11,835
  • 3
  • 34
  • 57
Machi
  • 43
  • 1
  • 7
  • Maybe you could provide a second, marked up image showing the heads because I can't see any! Python might be an easy-to-use language, btw. – Mark Setchell Aug 22 '18 at 19:30
  • depends on the fileformat of the image you will get as input... what will it be? png,bmp,mat,raw,ASCII ? The approach might be enough but I woul drather crate a ROI mask for pixels above certain height and count the number of blobs by subsequential flood filling (labeling) of any non background pixel. People are using OpenCV for tasks like this I prefer my own C++ code ... – Spektre Aug 23 '18 at 05:42
  • @MarkSetchell Right now that's the only sample I got cause that's what my professor gave me. I asked him to give me some more but that will probably take some time. I worked in Python and compared to C the syntax was beautiful and simple :) – Machi Aug 23 '18 at 13:28
  • @Spektre It will be something like I posted in my question - png. I talked with my professor and he did mention OpenCV was quite useful, so maybe I should go with that? That is just try and research into it. – Machi Aug 23 '18 at 13:31
  • can I know what depth camera it is? Is it a kinect? – Srini Aug 23 '18 at 17:45
  • @Srini We have multiple types but kinect is one of types we are using – Machi Aug 23 '18 at 23:57
  • 1
    The reason I ask is because what APIs and frameworks will be suitable depends a lot on the type of camera – Srini Aug 24 '18 at 17:29

0 Answers0