Best Image Recognition Algorithm - Advice Please [closed]

asked 2017-05-04 21:43:26 -0600

VincentSerpico gravatar image

I am working on a "UPS Package Detection" program. The app takes photos of my porch every 1 minute from a Raspberry Pi. I then run a the image through a Feature Matching against a "cube" to detect cubes (packages are cubes, right??)

I referenced the examples here: https://opencv-python-tutroals.readth...

I decide if a package has been delivered if there are 3 or more observations (see the two images below). I find my algorithm crude, and I know I can do better. Can someone please recommend and advise a better way for me to detect if a package has been delivered.

(I am using Python)

image description image description

edit retag flag offensive reopen merge delete

Closed for the following reason the question is answered, right answer was accepted by sturkmen
close date 2020-10-10 03:31:39.202234

Comments

1

comparing a textureless synthetic box to a real one (of different shape) seems a bad idea already

berak gravatar imageberak ( 2017-05-04 23:12:48 -0600 )edit
1

A background subtraction like algorithm could do the trick?

  • use default images when there is nothing (maybe some issue with illumination change?)
  • there is a box when the current images differ to the reference images in a certain region in the image
  • the current /reference images are different and there is no movement
Eduardo gravatar imageEduardo ( 2017-05-05 03:18:28 -0600 )edit
add a comment