search

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

Problems initializing tracking with proper calibration #17

Open Loeing opened 8 years ago

Loeing commented 8 years ago

Hi,

I've calibrated my camera based off of the OpenCV asymmetrical points calibration but DPPTAM fails to initialize, despite my use of heavily textured areas or very sparse areas. I've managed to initialize dpptam on my input only once. Can anyone help me? I've attached my camera's calibration, it's worked for other projects.

cameraMatrix: !!opencv-matrix rows: 3 cols: 3 dt: d data: [ 1066.218200176972, 0., 639.5, 0., 1066.218200176972, 359.5, 0., 0., 1. ] distCoeffs: !!opencv-matrix rows: 5 cols: 1 dt: d data: [ 0.1710096450750865, -0.2813834964230731, 0., 0., 0.]

Loeing commented 8 years ago

I fixed the camera path, but it was crashing when the last part of the distortion matrix was 0.

Loeing commented 8 years ago

Hi @alejocb,

I'm getting this error message during calibration. Could you help me figure out what is causing it?

OpenCV Error: Assertion failed (m.dims >= 2) in Mat, file /build/buildd/opencv-2.4.8+dfsg1/modules/core/src/matrix.cpp, line 269 terminate called after throwing an instance of 'cv::Exception' what(): /build/buildd/opencv-2.4.8+dfsg1/modules/core/src/matrix.cpp:269: error: (-215) m.dims >= 2 in function Mat

alejocb commented 8 years ago

I am sorry, I am not familiar with openCV calibration toolbox..

Loeing commented 8 years ago

That's ok, I've analysed the core dump and it looks like it's being caused on line 760, by this line color.rowRange(0,color.rows).colRange(0,1).copyTo(color); of the get_color function which is being called in initialized_sd