Ask Your Question
0

Object detection using a 3D-TOF camera

asked 2016-09-14 09:14:59 -0500

Jack16 gravatar image

updated 2016-09-14 09:18:00 -0500

Hello everyone,

I am trying to connect a 3D TOF camera using opencv on Visual Studio. This camera generates four output streams as mentioned below.

  • Intensity
  • Confidence
  • Range/Depth data
  • 3D PCL

1) How I could verify if this camera is supported on opencv ? I tried to connect using the default but it didnt work. VideoCapture cap(0); // open the default camera

2) Which one of the stream is suitable for the detection of an object as given on the link below. http://www.logistik-xtra.de/klt-rahme...

3) Which object detection technique available on opencv plateform is suitable for the detection of object mentioned in the link above.

helping comments would be highly appreciated

Thanks in advance.

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted
1

answered 2016-09-14 09:39:41 -0500

kbarni gravatar image

OpenCV can open only 3D cameras supporting the OpenNI library.

To open the camera, use:

VideoCapture cap(CV_CAP_OPENNI);

Then grab the images:

cap.grab();
cap.retrieve( depthMap, CV_CAP_OPENNI_DEPTH_MAP );

More information here: http://docs.opencv.org/2.4/doc/user_g...

Otherwise use the default library to grab the images from the camera to a memory buffer, then convert it to Mat object. It should like something like:

ushort *buffer;
camera.grab(buffer);
Mat depthMap(camera.height,camera.width,CV_16U,buffer);

For object identification, you'll need to see how the images look like first, than try to find a solution for yourself first. Check this page for ideas: https://www.intorobotics.com/how-to-d...

If you are looking for object identification from 3D point clouds, you can check the PCL library too.

edit flag offensive delete link more
Login/Signup to Answer

Question Tools

1 follower

Stats

Asked: 2016-09-14 09:14:59 -0500

Seen: 1,290 times

Last updated: Sep 14 '16