Calibrating ZED X One on 2m Baseline

[ben-danial]

Hi!

I am trying to calibrate a stereo pair of ZED X One on a 2m baseline and I am really struggling to get full coverage on in the calibration software.

I have tested using an A0 board with a 13x9 90mm grid. I struggle since when I get close, I can get coverage on one side but then I am out of frame on the other camera. If I increase the FOV, getting the top corners say of the frame becomes very difficult.

How were these cameras calibrated by stereolabs when testing a 2m baseline?

Any advice would be greatly appreciated.

[auc7us]

Hey, can you share how you are calibrating it? I hope you aren’t trying to cover the entire FOV in one go. Link to calibration demo

@ben-danial

when I get close, I can get coverage on one side but then I am out of frame on the other camera. If I increase the FOV, getting the top corners say of the frame becomes very difficult.

Also when you say “increase the FOV” do you mean increase the distance between the calibration board and the camera pair?

[ben-danial]

Not trying to get the entire board in the FOV in one go and I am following the demo. To increase FOV, I mean taking it outside instead of being restrained to a room.

[Myzhar]

@ben-danial unfortunately, it’s hard to understand how you are trying to calibrate your rig.
Can you please record a video to show the behaviors of the calibration software?

[auc7us]

Hi Ben,

I just finished calibrating the camera pair on a 1.5m baseline. I used a 1000mm x 800mm board with 16*12 boxes with a 50mm box width.

The furthest I had to be from the camera rig was 3.5-4m and I got pretty solid calibration with a very accurate baseline and complete coverage.

At times I had to come as close as 1.5 m to the camera rig to get complete coverage(green screen) during calibration . Not sure if this helps.

[ben-danial]

Hi auc7us,

This does help, is there a way we can get in touch to discuss further?

I would be interested to see how your results were using the depth viewer after calibrating.

[auc7us]

Sent you a dm. We can continue the conversation there.

[Blake-James]

Hi @ben-danial and @auc7us I’m very interested in keeping up to date with your findings and collaborating on this.
I’ve also been battling with a ZED X One setup as you can see here:

ZED X One Stereo Accuracy

I have been testing ZED X One stereo pairs along side the ZED 2i, and I am struggling to get good accurate & stable depth data from the X One’s. I have these two cameras both mounted together onto a larger PTZ camera, which allows me to move the X One pair in a nice controlled way during calibration. In this configuration, the X One pair has a baseline of 218mm, almost twice as much as the 120mm baseline of the ZED 2i, so I am expecting the X One pair to give better quality depth info then the …

Next week I’ll be trying some very narrow lenses (30deg fov) on my 4k X One pair, trying to test the limits of how much accuracy I can get at longer ranges.

[ben-danial]

Hi Blake,

Would love to talk!

I am also finding the long distance measurements to be poor.

I will send you a dm

[NivC]

Hey Blake, how was going you experiment? i am wondering if buying these cameras set will fit to my needs. If you don’t mind, i would like to talk to you private to get more details.

[Blake-James]

We eventually stopped using the ZED X and have since switched to a more custom stereo solution with two standard cameras, so I don’t have any recent updates unfortunately.

The experiment with the narrow 30deg lenses on the 4K ZED X’s did show some promising signs. I was able to get the pair calibrated and the pixel size at long distances was great. The stereo depth quality seemed similar to what we were getting with a ZED 2i with narrow lens.