Jump to content

Tutorial A to Z - how to make a landuse classification using LANDSAT images


Arhanghelul

Recommended Posts

Hello GIS forum !

Where can I find a complet tutorial about Land Use/Land Cover classification using LANDSAT images ? A tutorial for begginers, for newbies, non-experts in remote sensing ? :)

I would like to find a tutorial that presents step-by-step, from A to Z, all the aspects of using LANDSAT images to obtain a land cover map.

Content of the tutorial:

  1. Where to obtain and how to select satelite images of LANDSAT data collection ? (this I allready know: Glovis, EarthExplorer, and 0% clound cover, different seasons for vegetation status, etc)
  2. The pre-processing steps of the satellite images ? How to make an atmosferic calibration, remove any disturbances, etc ? What software to use better : ENVI or ERDAS ? What modules of these software to use for pre-processing ?
  3. Classification methods: un-supervised classification/ supervised classification ? (advantages/dis-advantages of these metods?) How to make a supervised classification (selecting the classes according to spectral values, selecting samples/ training areas, spectral mixture, spectral analysis, spectral plots/diagrams, etc) What is the best software to use for this step (ENVI or ERDAS) and what modules to use ?
  4. Post-classification methods ? How to make a post-classification of a Land use /Land cover image ? (in ENVI or ERDAS) Tips and tricks ? ( is it better to change the classification method, the samples, or the satelite image ?) What is an error matrix of the classification and how to make it ? How to asses the quality of the classification method ?
  5. Are there any methods to obtain good results in classification of LANDSAT images ?

So this is what I am searching, a tutorial about using LANDSAT images to create a Land use/Land cover map !

( video tutorial or document tutorial with a package of images and examples, explained step-by-step, special for begginers or "idiots" ;) )

Please give me a tutorial !!!!

Thank you all, my friends !

:D:blink:

  • Like 1
Link to comment
Share on other sites

Remote Sensing is an advanced thing, so there is a good possibility that you'll never find anything 'complete'. It's not just software, you'll need to learn the theory as well. Riccardo Klinger has a good set of tutorial video you can try.

http://www.youtube.com/playlist?list=PLCEBF53A31190DABE&feature=viewall

Speaking about Erdas and ENVI, both works fine in lots of aspect. Sometimes ENVI runs smoother than Erdas, runs in linux too.

The quality of result relies on the methodology and data you follow.

From my pov, try object-based classification rather than pixel-based. Object based image analysis (OBIA) is one of the most powerful technique to use most from your image and give far better result than pixel based analysis. In OBIA you are working with color, texture, pixel statistics, nature,and band values all at once. Pixel based classification only rely on one thing-DN, so error is inevitable. It has an automated workflow, so no raster filling and reckoning fuzzy-class.

Throwing my two cent. :)

  • Like 1
Link to comment
Share on other sites

I am having trouble about use landsat image to make a landuse classification. I want devide to: Forest rich, Forest medium, Forest lowest, Land rice, Land fruit, Land industry, water.... I used Landsat Image ETM 30M. I am having trouble about combination band, i dont know used these band to difference between land. 5-4-3, 3-2-1..... ??? Every body can show me how combination band and choose band to classfication? Thank you very much.

Link to comment
Share on other sites

To classification land use very difficulty. I am having trouble about classification forest rich and forest medium. two land use have color in image landsat similar. Anybody can show me how classification forest rich and forest medium...... Thank you very much. :huh: :huh: :huh:

Edited by HaNoi
Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...

Important Information

By using this site, you agree to our Terms of Use.

Disable-Adblock.png

 

If you enjoy our contents, support us by Disable ads Blocker or add GIS-area to your ads blocker whitelist