Marker Detection - Image Scale

[FabianN]

Hi Alexey,

I sometimes have problems in detecting coded markers when they are too small in an image. However, when I upsample the images (f.e. by a factor of 2), the detection works well an accurately (visually).
Is it an option for you to implement a user-parameter for internal up- or downsampling of the images prior to marker detection? This would allow to handle coded targets with a larger size difference than what is currently possible.

Or is there another way of dealing with this?

Thank you,
Fabian

[3DWinter]

This is a cool revelation. I wonder if the automatic detection is sensitive to a specific geometry size/ resolution!?

[howcanoewang]

Any progress on this point? I met the same problem, the markers in original image are too small to detect, but by using a python script to up-sample images (from 5472x3648 to 10944x7296 ), all the markers can be detected perfectly.

It seems the marker detection are closely related to the absolute pixel-numbers rather than its relative sizes in the image.

It would be really helpful if giving an upsample factor in the marker detection tool, for solving such cases.

@Alexey

[Alexey Pasumansky]

Hello howcanoewang,

Can you share a few examples of images, where upscaling helps, to support@agisoft.com, so that we could test possible solutions?

[howcanoewang]

Hello howcanoewang,

Can you share a few examples of images, where upscaling helps, to support@agisoft.com, so that we could test possible solutions?

Thanks for getting in touch, I have just send the email with data shared by Google drive to you

[FabianN]

Hi Alexey,

Is there any progress on this? It would also be great to have this option for uncoded targets.