ekfmonoslam icon indicating copy to clipboard operation
ekfmonoslam copied to clipboard

Published 20 hours ago • verified publisher icon JzHuai0108

camera model

Open pangfumin opened this issue 8 years ago • 5 comments

Hi Huai， Thank you for sharing your code . Nowadays I am trying to modify the ekfslam to run my own dataset.But I get confused by the Civera's classic model as in Civera, 2008 . I don't what the relationship between k1 k2 in Civera's classic model to the general opencv radial distortion. Can you give a answer? Thank you.

pangfumin avatar Aug 04 '16 16:08 pangfumin

Please check (1) the appendix of Javier Civera's paper inverse depth parameterization for monocular slam, (2) OpenCV calibration model http://docs.opencv.org/2.4/doc/tutorials/calib3d/camera_calibration/camera_calibration.html, (3) Javier's explaination about these camera models at http://webdiis.unizar.es/~jcivera/code/1p-ransac-ekf-monoslam.html.

JzHuai0108 avatar Aug 04 '16 18:08 JzHuai0108

Hi Huai,the data you uesed is your collection from sesors or the KITTI dataset? I don't understand this problem after reading your code description. Thank you!

wk199 avatar Dec 21 '16 15:12 wk199

@w1019220367 https://www.youtube.com/watch?v=xOzqoA8QzJ0&t=16s

pangfumin avatar Dec 21 '16 15:12 pangfumin

Are you referring to the linked video? The data used for the algorithm shown in the video is collected by cameras mounted on our GPS car.

JzHuai0108 avatar Dec 22 '16 22:12 JzHuai0108

Hi Huai, the comment beneath the video that u think leveraging filter and BA may work best, do you mean that to use both of them for one dataset ,and make a choice according to different data status?

huanhexiao avatar Sep 04 '18 07:09 huanhexiao