2012-09-16 00:18:13 -0600 | received badge | ● Supporter (source) |
2012-09-16 00:17:25 -0600 | answered a question | 3D scale is poor. Oh... I had missed that description. As you say, if the coordinates of the point could 16 times, you seem to be the correct scale. So, Z coordinate was almost the same as reality, and X-Y coodinates. I appreciate your comments very much! |
2012-09-16 00:01:59 -0600 | received badge | ● Scholar (source) |
2012-09-14 11:20:30 -0600 | asked a question | 3D scale is poor. I got 3D point cloud by using stereo camera and sample stereo_calib.cpp and stereo_match.cpp. And, when viewed in the point cloud gnuplot, scale is very small compared with the reality. I used 9x6 checkerboard of square size 3.45cm. Of course, squareSize of source code, I've assigned a 3.45. As a result, RMS error=0.221828 and reprojection error=0.261209, and rectified images was good. Then, place the object to the location of the shooting distance of 100cm from the stereo camera, I got a 3D point cloud using stereo SGBM. However, average Z value of that object was 6. Why not? |