OSMDigitize with previously orthorectified images?

We’re currently evaluating options for an automated drone image classification workflow, and ODM/WebODM looks amazing.

We’re currently using Pix4D for orthorectification, but I’m keen to explore ODM as an alternative. In addition, the OSMDigitize feature in WebODM looks very attractive. Based on the examples, this seems to allow drawing and annotating of polygons etc. directly on the images - is that correct? If so, it would be very useful for us, since we’re using machine learning for the image classification and having an integrated user interface for the digitisation step would massively streamline the process of creating a training dataset for the ML algorithm.

I have a couple of questions and would be grateful if someone could point me in the right direction, please:

  • Is this a sensible use case for the OSMDigitize plugin? Ideally, we would like to have multiple users drawing polygons defining features/land classes of interest on top of our images. We would then export these polygons as georeferenced vector datasets (e.g. as GeoJSON) that we can use to build training datasets

  • Is there any way I can try the OSMDigitize plugin without uploading raw images and re-running the orthorectification procedure? I already have an orthorectified mosiac to work with and my main interest right now is to explore options for digitising and annotation. Eventually we might implement the whole workflow with ODM, but right now I’d like to skip the orthorectification part and load my existing mosaic for digitisation. Is this possible?

Thanks in advance for any tips or advice! :slight_smile:

1 Like

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.