qvio malfunctioning



  • Hi, I'm currently experimenting the voxl's qvio ability. I followed the technical docs and calibrated the camera(I'm using the hires camera, I updated the code and it seems to work just fine), the imu and the extrinsic (to the m500 flight deck I printed in a 3d printer), but when I'm running the voxl-qvio-server, the values of the xyz are not accurate, the quality is low and it is just keeps crashing and sending me the following error - "not_stationary". I'm guessing if I'll solve the error it will solve the other problems. Ty in advance.



  • This post is deleted!


  • This post is deleted!

  • Dev Team

    Hi,

    We've never tested QVIO on the hires cam, it's been extensively tuned for the fisheye tracking camera and benefits heavily from having a wide field of view. I suspect that this is where you issue originates, have you tried your mount with the tracking camera?



  • This post is deleted!


  • @Alex-Gardner Hi, Unfortunately I don't have the tracking camera so I'm trying to perform a working SLAM with the hires camera. I'm using the m500 flight deck and currently mounted the hires where is suppose to be. Does it matter if I'm using the hires camera or the tracking camera if I mount the hires on the same location where the tracking camera should be while using a fitting extrinsic? should I try it?


  • Dev Team

    Hi,

    You can definitely try it but the QVIO algorithm benefits A LOT from having a wide field of view on the camera and the hires cam has a fairly narrow field of view, especially when compared to the fisheye tracking camera. There are no hard restrictions to trying this but know that performance will almost certainly be worse.


Log in to reply