Android image processing and obstacle detection [closed]

asked 2013-03-27 01:17:48 -0500

Madz gravatar image

Hi, I'm new to OpenCV and image processing. My objective is to detect obstacles via an android phone, the user carries the phone with him.
I have used canny edge detection(which worked) and tried background subtraction(which didn't work) and am at a loss on what to do next. I need to detect an incoming object. What should I do next to detect an obstacle?
Any help would be much appreciated.

edit retag flag offensive reopen merge delete

Closed for the following reason question is not relevant or outdated by sturkmen
close date 2020-10-01 12:34:40.598821


Detecting random objects, of any color, size or texture on a mobile phone is a task that haven't been solved yet. Focus on a much, much smaller scale: Define some objects to be avoided (let's say red or blue squares) and start from there. When you are ready with them, try to generalize a bit, and so on.

sammy gravatar imagesammy ( 2013-03-27 08:06:45 -0500 )edit

If you are ready to use multiple frames, you could use Optical flow to detect if any object is coming towards the user.

jayrambhia gravatar imagejayrambhia ( 2013-03-27 18:22:08 -0500 )edit

@jayrambhia Can you elaborate on how to achieve this with optical flow please?

Madz gravatar imageMadz ( 2013-03-28 08:57:20 -0500 )edit