You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
after doing a number of tests, i found out that 3d pose estimation doesnot provide an accurate estimation of the location of the detected object. Now i want to use find-2d-object only for object detection, and use a 3d lidar for distance estimation. in this case, how can i implement 3d pose estimation? would you please guide me?
Thanks
The text was updated successfully, but these errors were encountered:
Hi @Delbina, this comment may be a bit late and hopefully you may have moved on
I would recommend using other deep learning object detection methods, but if you would want to still use find-2d-object, you could extract the XY coordinates from find object, set up your transforms properly, try to find the same XY point on the 3d lidar then by triangulation or otherwise find your distance
It is a very roundabout way of doing things and depending on where the lidar is mounted it might not even make sense to do things this way.
Hi Matlabbe,
after doing a number of tests, i found out that 3d pose estimation doesnot provide an accurate estimation of the location of the detected object. Now i want to use find-2d-object only for object detection, and use a 3d lidar for distance estimation. in this case, how can i implement 3d pose estimation? would you please guide me?
Thanks
The text was updated successfully, but these errors were encountered: