Lab 5 - Multispectral Classification
In this lab you will experiment with different classification algorithms with Landsat TM imagery from the state of Amazonas in Brazil.
First, open the BZ92_276. sub file in the /2002/lab7 folder in the class_lab folder on the desktop.
The first step is to select Regions Of Interest (ROI's) to represent the different land cover classes that you want to differentiate using the image data. Remember that the classes must be spectrally distinct for the classification algorithm to distinguish them.
Before picking the ROIs, look at a few different false color representations of the image data to get some idea of what you will be classifying. In general, time spent examining your data is time well spent. If nothing else, it will minimize the low grade embarassment of having casual observers ask you about features in the image that you failed to notice because you didn't examine it in detail.
Compare RGB: 3/2/1, 5/4/3, 6/4/1 side by side in 3 different image windows.
Q 1. Why is the 3/2/1 image so difficult to interpret?
Q 2.How would you enhance this image to improve interpretability?
Link the images (Functions -> Link -> Link Displays) and use the dynamic overlay tool (mouse) to compare specific features.
Choose your favorite of the 3 RGB images, blow away the other two and proceed selecting ROI's (Tools -> Regions of Interest -> ROI Tool). The ROI tool is described in the ENVI User's Guide and in the Tutorial as well as in the online Help.
You might pan around and look at 2D scatter plots for (say) the NIR and visible red bands to look at the spectral signatures of land cover types present in the image.
Select a single ROI for each of the following landcover classes:
Remember to select "New Region" to add a new ROI class or you will keep adding to the first class and you will have to begin again.
If you do this, just hit "Delete" and start the class over.
Save the ROIs to a file (remember to "select all" before saving) using your initials as the first 3 letters in the filename (e.g. CSSexample.roi). Make sure you save it to the Class folder or your desktop.
Q 3. What tool would you use now to assess the spectral separability of the classes qualitatively?
Try it. Are they spectrally distinct? If not, you might want to reselect your training areas.
ENVI provides two statistical measures of the spectral separability of the classes in the ROI tool. If you have time, run it and see if your ROIs are spectrally distinct.
Q. 4. Which of the 2 measures provides a more conservative estimate of class separability?
First, from the Classification -> Supervised menu. run the Parallelopiped classification.
In all classifications, Output Result to Memory and Do Not output Rule Images.
Display the classified image (which will appear in your Available Bands list) in a new window as a gray scale image. Nice gray scale, eh?
Link the classification window with the RGB image containing your ROIs and compare the results w/ the dynamic overlay.
Q 5. What are all the black areas?
Now, from the Classification -> Supervised menu, do a Maximum Likelihood classification and display the result in a new image window.
Q 6. What happened to the black areas?
Now rerun the MaxLike classification with a threshold.
Q 7. What threshold did you choose?
Q 8. What didn't get classified?
Now select additional ROI's for each class and add two more classes (and save to your file).
Q 9. What classes did you add to improve your classification?
Run the Maximum Likelihood, Parallelopiped and Minimum Distance classifications again using the new classes.
Summarize the results.
Proceed to the "Post Classification Processing" section of the Classification menu.
Calculate the Confusion Matrix (for the ROI method only) for both of your Maximum Likelihood Classifications.
Q 10. Why are they different?
Q 12. Explain the "off diagonal" numbers.
Summarize your impression of this exercise in one sentence.
Q 13. What did you learn?
SlideShare utilise les cookies pour améliorer les fonctionnalités et les performances, et également pour vous montrer des publicités pertinentes. Si vous continuez à naviguer sur ce site, vous acceptez l’utilisation de cookies. Consultez nos Conditions d’utilisation et notre Politique de confidentialité.
SlideShare utilise les cookies pour améliorer les fonctionnalités et les performances, et également pour vous montrer des publicités pertinentes. Si vous continuez à naviguer sur ce site, vous acceptez l’utilisation de cookies. Consultez notre Politique de confidentialité et nos Conditions d’utilisation pour en savoir plus.
Explorez tous vos thèmes favoris dans l’ application SlideShare. Obtenez l’application SlideShare afin d’ enregistrer pour plus tard. même hors-ligne.
Continuer vers le site mobile »
Toucher deux fois pour dézoomerClassification methods envi
1 document mis en ligne
Partager ce SlideShare
LinkedIn Corporation © 2017
Image providers such as DigitalGlobe strongly recommend orthorectifying satellite images to guarantee geo-accuracy. Orthorectification is the process of correcting an acquired image using an elevation model so that georeferenced pixels in the image roughly correspond to what one would see if one were flying directly over that geolocation. In this tutorial, you will learn how to orthorectify an image using a geospatial analysis software package called ENVI.Requirements¶ Walkthrough¶ Locate satellite images¶
First locate your images. Below are the typical contents of satellite data acquired from the QuickBird satellite.
Make sure that you have Ortho Ready Standard Imagery by checking the IMD files for the following attribute.
The 005613412020_01_P001_MUL folder contains the multispectral images and the 005613412020_01_P001_PAN folder contains the corresponding panchromatic images. Here we have rearranged the files into pairs.Locate digital elevation model¶
Orthorectification requires a digital elevation model, which are measurements of elevation at each geolocation. Results from the latest Shuttle Radar Topography Mission are provided free at the CGIAR-CSI SRTM 90m DEM Digital Elevation Database .
Download your localized SRTM data as a GeoTiff image.Perform orthorectification¶
Start ENVI and choose Map > Orthorectification > QuickBird > Orthorectify QuickBird. Open the satellite image you want to orthorectify and click OK.
The Orthorectification Parameters dialog appears.
The ENVI documentation recommends using Nearest Neighbor resampling to preserve pixel values.
Select elevation model.
The orthorectification process can take anywhere from ten minutes to an hour, depending on the size of the image. Note that you should activate the Geoid option if you are orthorectifying with an SRTM in ArcGIS.
The best way i can recommend is to use "Radiometric Calibration" tool of ENVI. In this, no manual calculation is required.
Step 1: Open the MTL file from ENVI (File-> Open). When Landsat 8 images are downloaded, they provide with .MTL text file (eg. LC81920252013135LGN01_MTL)
Step 2: Search in Toolbox for "Radiometric Calibration".As you select the tool,it will provide you with three band option: Multispectral, Thermal and Panchromatic. Select the thermal as shown in figure below. Click on "OK".
Step 3: Select the option of "Brightness Temperature" from drop-down menu, as shown in figure below. Save the output data to your computer. (If image to be atmospherically corrected for fog, click FLAASH for default correction)
answered May 18 '15 at 17:05
The paper utilized Landsat 5 TM and Landsat 8 OLI for analyzing land use/land cover change and its impact on land surface temperature in Sundarban Biosphere Reserve, India. Split window algorithm and spectral radiance model were used for determining land surface temperature from Landsat 8 OLI and Landsat 5 TM, respectively. The land use land cover change analysis revealed phenomenal increase in the waterlogged areas followed by settlement and paddy and a decrease in open forest followed by deposition and water body. The distribution of average change in land surface temperature shows that water recorded highest increase in temperature followed by deposition, open forest and settlement. Overlay of the transect profiles drawn on land use/land cover change map over land surface temperature map revealed that the land surface temperature has increased in those areas which were transformed from open forest to paddy, open forest to settlement, paddy to settlement and deposition to settlement. The study demonstrated that increase in non-evaporating surfaces and decrease in vegetation have increased the surface temperature and modified the temperature of the study area.
answered Nov 29 '16 at 6:25Your Answer
2017 Stack Exchange, Inc
ENVI products create the premier geospatial software foundation to process and analyze all types of imagery and data such as multispectral, hyperspectral, LiDAR, and SAR. They are designed to be used by everyone from GIS professionals to image analysts and image scientists, regardless of prior experience with imagery. All ENVI products integrate with ArcGIS® from Esri, are easily customized to meet your unique needs, and are backed by a robust community of users that crosses disciplines.
IDL is the trusted scientific programming language used across disciplines to extract meaningful visualizations out of complex numerical data.
This software is available to Harvard Affiliates only. Please follow the installation instruction below to download, install, and activate your license. To directly download the software, you will need to login with your HUID/HarvardKey here: Software Access page (click) to get credentials for downloading it from the Download Link section below.
ENVI License Servers
After installation, download the following two license files in the Download Link section by right-click to save link as ***.dat into C:\Program Files\Exelis\License\ folder.
Share this webpage with
The Center for Geographic Analysis, a member of the Institute for Quantitative Social Science (IQSS). 1737 Cambridge Street, Cambridge MA 02138 (map ) 617-495-3213 © President & Fellows Harvard University. All Rights Reserved.