1

I have some photos of 1X1 meter plots that were taken with a NIR digital camera. They have been georeferenced, corrected, etc.

I am interested in performing an image classification for the vegetation, however, I have only ever done this on a landscape scale with Landsat, MODIS, or on the scale of a small city-sized area.

I know the vegetation types, I just have a lot of photos and from multiple years and need to train the model to automate the process. I will most likely be utilizing the NDVI, which I am familiar with.

Does anyone know of any journal articles, tutorials, other resources, other feeds where this has been addressed etc. where others have done image classifications/change analyses on as small a scale as a meter squared plot?

-1

Check out this one: http://www.samplepoint.org/

I have not used it but it sounds like exactly what you are looking for. Here is a link to the tutorial document: http://www.samplepoint.org/SamplePointTutorial.pdf

I guess this solution only works if you are interested in using different software than you have used for large scale projects.

We're looking for long answers that provide some explanation and context. Don't just give a one-line answer; explain why your answer is right, ideally with citations. Answers that don't include explanations may be removed.

  • 1
    also there are lots of papers referenced on the main page that you may be able to make use of. – gomapping Mar 14 '16 at 19:08
-1

https://www.harrisgeospatial.com/docs/RegionOfInterestTool.html

https://www.harrisgeospatial.com/docs/Classification.html

using ENVI software your objective might be achieved.

We're looking for long answers that provide some explanation and context. Don't just give a one-line answer; explain why your answer is right, ideally with citations. Answers that don't include explanations may be removed.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.