Authors: LASYA VENIGALLA*, University of Texas at Dallas
Topics: Remote Sensing, Land Use
Keywords: Neuro-Fuzzy Classifier, Remote Sensing, Object-based Classification
Session Type: Virtual Paper
Start / End Time: 4:40 PM / 5:55 PM
Room: Virtual 13
Presentation File: No File Uploaded
The increased capabilities of a remote sensing sensor resulted in a wide range of high-spatial-resolution images. The increase in spatial resolution makes it possible to view the minute details on the earth’s surface. However, while identifying the features pixel-by-pixel, only spatial properties of the image are considered, and textural properties are not considered. Therefore, object-based classification techniques that take both spatial as well as textural properties into consideration are used to extract features from a high-resolution image. However, rule-based methods that are used for object-based classification consider a single summary statistic value to represent the entire object and do not consider the within object spectral variability. There are curve-based matching methods that utilize all the pixels inside an object, but matching is done on each sample, lacking generalizing ability. The concepts that are under-discussed by the present scholars are within object spectral heterogeneity and generalizing ability together in image analysis. In this paper, both these concepts are together addressed by treating histograms of the objects as spectral curves and performing neuro-fuzzy classification using Gaussian-Fuzzy Learning Vector Quantization (GFLVQ) algorithm. A case study was performed on the World-View2 image for the Dallas Forth-worth area.