Support Website Contact Support Blog

Image Mask / Annotation and Affect on Processing

Hi, I’m new to Pix4D and I’m looking to discard/disregard some pixels from my video capture images. I saw on the forums that you can apply a mask via the annotation tool to remove affected portions of the point cloud. 

What is more important to me is having this also remove the pixels from consideration in the photogrammetry algorithm? I’m assuming that some very complicated things happen in determining the flight path. Could occluding objects, especially ones that are attached to the drone (rotors, drone components, protective cages), affect the result? 

I’m hoping the mask will completely discard portions of the image and allow the flight path calculation to perform as though they didn’t exist. And furthermore, allow the point cloud to generate without these pixels being included.

Thanks.

Hi Deam,

We are happy to have you on boarding with us!

The annotation tool (learn more) allows you to discard pixels from images that will not be used to generate 3D points. Anything that is captured in the images potentially impacts the reconstruction of the model. In the scenario you describe, the global mask is suitable for a consistent obstacle on all the images, e.g. the foot of the drone.

Also for more specific articles, you can have a look at:

That’s good news, thanks. However, is it just a single global image? Or can it change from frame to frame. I’m looking to occlude something that may change from frame to frame.

Thanks

Hello Dean,

There are 3 types of Annotation tool:

  • mask : this tool can be used to remove from the point cloud an obstacle that appears in few images, like a scaffold. All the images in which the object appear should be masked and step 2 should be rerun after masking.
  • carve : each annotated pixel has an impact on the point cloud. The effect of the annotation is immediately visible in the 3D View of the rayCloud and it is easy to notice if some pixels were erroneously annotated so as to be corrected immediately.
  • global mask : can be used to remove an obstacle that covers the same pixels in all images, like the foot of a drone. Only one image should be annotated and the annotation is propagated in the same pixels of all the images. If you have multiple objects to remove you can do it by annotating different images, one per object. However, in case that the objects appear in different locations on the images (different image coordinates), it is recommended not to use this tool as it will remove also other important information. In such cases, the mask tool is a better and safer option, even if it is more time-consuming.

Please note that you should be very careful when using this tool so that you make sure that there is no error in the pixel annotation. 

Regards,