alejocb / dpptam

DPPTAM: Dense Piecewise Planar Tracking and Mapping from a Monocular Sequence
GNU General Public License v3.0
219 stars 82 forks source link

question about usage #3

Open amiltonwong opened 8 years ago

amiltonwong commented 8 years ago

Dear @alejocb ,

I have questions about the usage, I couldn't see any output in RViz. The following are my steps:

$ cd ~/catkin_ws $ roscore & $ rosrun dpptam main

Open an other terminal, $ rosbag play ~/dpptam-dataset/lab_unizar.bag Open an other terminal, $ rosrun rviz rviz

But I couldn't see any output in RViz, and it shows the following error: Fixed Frame No tf data. Actual error: Fixed Frame [map] does not exist

https://goo.gl/dTjjys

Any idea or suggestion to fix it?

Thanks in advance~ Milton

amiltonwong commented 8 years ago

[Update]

I modify the file "/root/catkin_ws/src/dpptam/src/data.yml", and replace required info as follows:

camera_path:"/camera/rgb/image_color" cameraMatrix: !!opencv-matrix rows: 3 cols: 3 dt: das listed data: [ 520.908620, 0., 325.141442, 0., 521.007327 , 249.701764, 0., 0., 1. ] distCoeffs: !!opencv-matrix rows: 5 cols: 1 dt: d data: [ 0.231222, -0.784899, -0.003257, -0.000105, 0.917205 ]

Now, I could see some output in the window where I issue command "rosrun dpptam main" See: https://goo.gl/0zy4eJ

But I still couldn't see any output in RViz, and just the following error ( https://goo.gl/OL2AlJ ):

Fixed Frame Fixed Frame [map] does not exist

It seems the RViz couldn't find the topics for map.

Any idea or suggestion to fix it?

Thanks in advance~ Milton

alejocb commented 8 years ago

Hi Milton,

Many thanks for all the feedback :)

Check this screenshot for a correct visualization in rviz: https://www.dropbox.com/s/pymufqi2i2aixys/visualization_rviz.png?oref=e&n=314995776

Download again the code, since I modified a couple of things for the visualization and please let me know if you obtain good results in the example sequence.

Notice that you have to use this command to visualize the reprojection of the map in the camera frame: rosrun image_view image_view image:=/dpptam/camera/image

You can always visualize the results in meshlab, the map is saved as '.ply' files in src/map_and_poses.

Best,

Alejo.

amiltonwong commented 8 years ago

Hi, @alejocb , Thank you so much for your reply and updated version. I had tested the two dataset and obtain very impressive results :) For lab_unizar.bag: https://goo.gl/na1DnG For lab_upenn.bag: https://goo.gl/ujVW1M

BTW, currently it doesn't support live camera, right?

alejocb commented 8 years ago

Glad to hear that Milton :) Yes, you can use a live camera, just change the camera_path and calibration matrix in the file 'src/data.yml' with the path and calibration parameters of your camera-> 'camera_path', 'cameraMatrix' and 'distCoeffs'

DigitalGabriele commented 5 years ago

Hello @alejocb ,

I am having the same issue as the other user. I followed your instructions and downloaded the lab_unizar.bag. However, I do not see anything in rviz. I tried selecting all the possible parameters but to no avail.

Your links in this thread to show the appropriate rviz configurations also do not work.