2020-04-26 02:36:25 -0600 | received badge | ● Popular Question (source) |
2016-04-05 03:57:46 -0600 | commented answer | solvePnP large (~100) pixel re-projection error I now think the points from the laser are probably wrong, when detecting the ball arch it might have caught part of my leg, as a consequence the arch seems bigger than it actually is and the laser position is higher than it actually is. I'm going to do some tests soon and report back. |
2016-04-05 03:56:07 -0600 | commented answer | solvePnP large (~100) pixel re-projection error
|
2016-04-05 03:31:13 -0600 | received badge | ● Enthusiast |
2016-04-04 17:14:44 -0600 | commented answer | solvePnP large (~100) pixel re-projection error Don't think it's possible unless I get a bigger ball, which is pretty hard since the one I'm using is already 95 cm in diameter. The other alternatives would be a non-flat ground which would mess with the rest of the program or moving the equipment which is also not possible. I can redo the calibration with that sample code, however the current matrix was obtained with a very similar code to what that link shows and returned an RMS of ~0.5 pixel. |
2016-04-04 04:45:17 -0600 | received badge | ● Student (source) |
2016-04-04 03:47:17 -0600 | commented answer | solvePnP large (~100) pixel re-projection error Looking at the picture the orientation looks right, but the coordinate system should be lower. I'm going to add an image to my post, it's basically the same result that you got, but with both coordinate systems and in 3D. About increasing the span...unfortunately it's not possible. Camera and laser position are static. |
2016-04-02 19:44:03 -0600 | commented answer | solvePnP large (~100) pixel re-projection error It gives me X and Y (error is 30 mm). Z is calculated based on the arch that the laser scanner "sees". IE: If Z is 0.3 it means that the centroid is 0.3 meters above the laser scanner |
2016-04-02 19:19:56 -0600 | commented answer | solvePnP large (~100) pixel re-projection error With a laser range scanner. |
2016-04-02 13:53:36 -0600 | commented answer | solvePnP large (~100) pixel re-projection error It's not an actual shape. It's the centroid of a sphere in 25 images. The camera is always going to be at the same position, so I was hoping to take 25 images with a ball in different positions and calculate the transformation from my reference frame to the camera using solvePnP. No need to apologize, I'm grateful for your help. |
2016-04-01 03:50:34 -0600 | commented answer | solvePnP large (~100) pixel re-projection error I don't have the exact truth, although the resulting transformation matrix from solvePnP is: and it's inverse: I know that the rotation part of T^-1 is close to reality, so is X and Y translation, however the Z translation is off by about 0.5 meters. Yes, points are in the same order. |
2016-03-31 11:31:43 -0600 | received badge | ● Editor (source) |
2016-03-31 11:28:07 -0600 | asked a question | solvePnP large (~100) pixel re-projection error Hi, I have been trying to find a camera pose in relation to an object frame, however I'm getting unstable results and large re-projection errors (100 pixels or more in total). I know that object points and image points are correct. Intrinsic parameters and distortion coefficients were obtained with OpenCV's calibrateCamera with minimal re-projection error (0.5 pixel). I have tried CV_EPNP and solvePnPRansac, all of them return about the same results, or worse. The code: Object points file and image points file (dropbox links). In these conditions I get a re-projection error of 94.43. The image bellow shows original image points (green) and re-projected image points (red). I'm also not sure how I should use the distortion coefficients, since image points are already obtained from an undistorted image I opted to not use them on solvePnP and projectPoints, is this correct? Although I don't think this is where the large re-projection error comes from, since the error doesn't really change much by using them or not. I can't seem to find an explanation for such a large error... If you need any more details feel free to ask. Thanks in advance. EDIT: An image to help visualize the problem. See comments bellow. Green is the Z camera axis, orange with the frame overlapped is my reference frame ... (more) |