I want to classify various rabi crops (Wheat, mustard, pea etc.) in Sahibganj District, Jharkhand (India) using Landsat OLI, I have some GPS point also for different- different crops. Please suggest me any easiest and reliable method for this.
If I correctly understand what you want to do, you just need to proceed with a supervised classification method using one of the different remote sensing softwares like ERDAS, ENVI....
For Landsat 7 a good combinatios is 742 = 753 in OLI 753
This combination provides a "natural-like" rendition, while also penetrating atmospheric particles and smoke. Healthy vegetation will be a bright green and can saturate in seasons of heavy growth, grasslands will appear green, pink areas represent barren soil, oranges and browns represent sparsely vegetated areas. Dry vegetation will be orange and water will be blue. Sands, soils and minerals are highlighted in a multitude of colours.
Depends of the water content, you could also use another bands combination, but sometime ago i read an article that use the different harvesting periods of the crops to perfectly classified them.
If you need a better resolution you can merge your image with the pancromatic band or use Sentinel 2.
Good luck
Thanks, Ivan. I would like to ask one more question....i have some GPS points, can it will useful to make a signature profile for various crops.
Sure, you can select the pixel of your GPS points as true value in the supervised classification. In this way you will get the variation inside the same element (wheat) but be cautious because with similar plant species introducing to high variability of the pixel values could be risky.
One advise, order the corrected images to the USG and compare in which time of the year the differences between the different crops are greater. This simply action can save you a lot of time.
- Badges
- Science topic
- Similar topics
- Agricultural Science
- Agronomy