Hello, I'm currently trying to perform a supervised classification of land cover for remote sensing images. In order to do that, I must create a training imput where I classify a fraction of the pixels of an image and asign to each one a land cover category. In this case, if I perform a simple random sampling some categories may be under represented in the sample because of the prevalent land cover for each study area, thereby, an stratified samplig should be better.
However for this case, the only thing that I have for the sample size determination is the population number (total pixels in the image). How can I determinate the number of pixels per category that I should classify for that training imput?
Dear Researcher
To determine or calculate the sample size go through the followings:
1. https://www.who.int/ncds/surveillance/steps/resources/sampling/en/
2. Article Sample size calculation
3. https://apps.who.int/iris/handle/10665/40062
Please go through the attached file on sample size and you will calculate the sample size online by using the following link:
1. https://www.surveysystem.com/sscalc.htm
2. https://www.calculator.net/sample-size-calculator.html
you may use these above calculators as you find the suitable for your research.
Hope you find all the information useful in the way to determine sample size.
Happy researching...
- Badges
- Science topic
- Similar topics
- Computer Science
- Images