Lab 5: classification Accuracy Assessment

Goal

The goal of this lab is to understand how to evaluate the accuracy of classification results. Accuracy assessments are mandatory after performing an image classification, this is a portion of the post-processing stage of remotely sensed data.

Methods

An accuracy assessment is performed on a supervised and an unsupervised classification from labs 3 and 4. This is done by utilizing the accuracy assessment tool in Erdas. A high resolution reference image of the same study area is used to perform the assessment. This is done by generating  random points on the reference image, 125 random points in this lab,  and classifying those points based on the high resolution image utilizing the same classification codes for water, forest, agriculture, etc. (Table 1). By identifying these points, a comparison report is then produced (Figure 1). This allows for an error matrix to be created from the results of comparing the random points to the classified images.
Table 1: Values assigned to specific land cover land use classes.

Figure 1: This shows the accuracy report that is produced, this image shows it being edited in notepad to allow for it to be read easier.

Results


The results from both accuracy reports were then transferred into error matrix (Table 2 and 3), where statistics on the accuracy of the classification could be performed. These tables shows how many accurate classifications compered to the actual number gathered from the randomly generated points. By calculating the percent of correctly identified features, we can come up with an overall accuracy percentage, and an overall Kappa Statistics value, which is providing a measurement for the accuracy of the comparison based on comparing the agreement between the images.
Table 2: This error matrix shows the final accuracy assessment of the unsupervised classification scheme.
 Producer’s accuracy (Omission Error)
Water=92.31%
Forest=56.25%
Agriculture= 50%
Urban/built up= 75%
Soil=36.36%
User’s accuracy (Commission error)
Water=80%
Forest= 84.38%
Agriculture= 50%
Urban/built up= 20%
Soil= 32%
Table 3: This error matrix shows the final accuracy assessment of the supervised classification scheme. 
Producer’s accuracy (Omission Error)
Water=100%
Forest=70.21%
Agriculture= 35.556%
Urban/built up= 50%
Soil= 53.85%
User’s accuracy (Commission error)
Water=100%
Forest= 100%
Agriculture=  51.61%
Urban/built up= 18.51%

Soil= 29.167%

 Each of the error matrix above show producer's accuracy (Omission Error) , and user's accuracy (Commission Error), these provide percentages for the individual classes. Omission error simply provides a percentage of how many pixels are classified correctly,  where commission error provides a percentage for how many pixels on the classified image are what they say they are. Based on overall accuracy, my supervised classification is better than my unsupervised classification. However both of these classification methods are very bad due to them not being over 75 percent.

Sources

[Landsat 7 ETM]. (2000, June 9). Retrieved from https://eros.usgs.gov/usa

[NAIP High Resolution Imagery]. (2005, June). Retrieved from https://www.fsa.usda.gov/index

Comments

Post a Comment

Popular posts from this blog

Lab 6: Digital Change Detection

Image
Background The goal of this lab is to develop an image that shows change detection of land surface features over time. First a means of performing a qualitative change detection will be performed, then we will quantify post-classification change detection, and a model will be developed that will map detailed change of land use land cover images over time. Methods Part 1: Change detection using Write Function Memory Insertion The first part of the lab, a Write Function Memory Insertion is utilized. This processes utilizes near infrared bands, when the two images are brought into the Write Function, an output image is produced, and the image has areas highlighted in pinkish red, these are areas that have experienced change. Specifically in this lab, ec_envs1991.img and ec_envs_2011.img were used to perform this change detection. Part 2: Post-classification comparison change detection   In this part of the lab a From-to change detection using classified images of the Milw...
Read more

Lab 10: Radar Remote Sensing

Image
Goal The goal of this lab is to understand how to perform basic preprocessing and processing of radar images. Specifically noise reduction through speckle filtering, spectral and spatial enhancement, multi-sensor fusion, texture analysis, polarimetric processing, and slant-range to ground-range conversion. When this lab is completed, the basic knowledge of processing on any type of synthetic aperture radar image will be gained. Methods Speckle Supression In this lab radar imagery is analyzed and processed through Erdas Imagine, and ENVI. Noise reduction methods for preprocessing of radar imagery was performed through speckle filtering, edge enhancement and image enhancement. To perform speckle filtering, Radar speckle suppression tool is used. this removes common salt and pepper effect. this is done by utilizing a calculated coefficient of variation (Figure 1). Figure 1: coefficient of variation is 0.274552. This variable is then used to run the Speckle Suppression Functio...
Read more