I am working with Drone air images. These are geotiff images and clearly portray trees and buildings. I need to first classify the image according to land cover distribution, then need to remove the trees, grasses and buildings to get the original terrain model. I have another image of same area with elevation values and I need to reduce the elevation of objects over the surface.

Aerial Foto collected from Drone

I used ArcGIS 10.2 Spatial Analyst>Image Classification. I selected the Training Areas against my classification requirement and the generate signature file using automated toolset. I used this signature file for supervised classification and used Maximum likelihood for my classification.

The result of classification was awful. I found the big trees are classified as both grass land and trees as well as crops field also classified as big trees.

The image is RGB and it shows similar reflectance of big trees, crop fields and grass land. So, it is difficult for me to classify different classes separately to extract actual surface reducing tree height or crop height.

I am wondering if anybody has any suggestions regarding this issue.

  • Would you be able to edit your question to include the precise procedure you used and an accurate description of what in the result was not as you expected from the documentation, please? – PolyGeo Aug 5 '14 at 9:49
  • I'm having hard time to understand this: "to extract actual surface reducing tree height or crop height." How do you actually "remove the trees"? – reima Aug 5 '14 at 11:54
  • @reima: Thanks for saying that. May be I am not too good in describing my Problems. Actually I need a better classification and then I can use conditional Tools to reduce the Elevation of object to get only surface elevation.:-) – Shiuli Pervin Aug 5 '14 at 12:59
  • 1
    @Alesinar Please consider adding your comment as an answer. I also believe that spectral resolution is the issue here. – Aaron Aug 5 '14 at 13:09
  • @Shiuli Pervin How many spectral bands are you working with? – Aaron Aug 5 '14 at 13:10

I wanted to write a comment, but i don´t have points enough. I think that what you need is to do a classification by texture. Last week i was on a seminar where the aim was to classify images of high resolution with texture and variograms (geostatistics).

you can read this:

i hope this helps you!

  • I found this article very important for my problem but I do not have Access to full document..Thanks:-) – Shiuli Pervin Aug 5 '14 at 13:03
  • +1 Texture is a good idea if spectral resolution is lacking. Texture can and should be included with the spectral bands in the classification. – Aaron Aug 5 '14 at 13:12
  • the second one: google.cl/… – Pau Aug 5 '14 at 13:14

Do you have access to the point cloud from the imagery? In mosaicing the images from the drone, depending on software, you can export a 3D point cloud. You then can use LASTools to classify the ground points and then convert to a DEM.

  • Thanks:-). actually we use pix4Dmapper(pix4d.com/products) for Drone Image and it has 3D Point cloud. Our Company capture their own Images. But, still we do not have lasTools. We can think about it.:-) – Shiuli Pervin Aug 5 '14 at 13:31
  • +1 however this will also be hard to achieve as in densly vegetated areas there will be only a few ground points or even none. – Alešinar Aug 5 '14 at 16:56

Three band images are generally not sufficient for high quality land cover classifications. Usually at least near infrared band is required. When I was classifying one image that had four bands (r,g,b,nir) I also calculated NDVI and included it in classification. As you probably don't have nir band you could add more information for the classification using other indexes that require two of three bands that you have at your disposal. In this article there is a list of some that you might use.

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.