RGBDSLAM using custom data [closed]

asked 2014-03-26 09:42:36 -0500

msalasg gravatar image

updated 2016-10-24 08:36:37 -0500

ngrennan gravatar image

I want to use RGBDSlam on a dataset which is made out of RGB (uint8) and depth (uint16) images from a Kinect. I haven't record the dataset, so I have no access to the rosbags.

I wrote a code that read the images from my disk and publish them on the corresponding topics:

  • camera/rgb_image publish a color image CV_8U3C
  • camera/depth_image publish a grey image CV_16U1C
  • camera/pointcloud publish a PointCloud2 made out of the pre-aligned RGB and depth image.

So far, I've not been able to build a map. Is there any other topic i should publish in order to make it work?


edit retag flag offensive reopen merge delete

Closed for the following reason question is not relevant or outdated by tfoote
close date 2015-10-28 18:16:22.646679