Performance evaluation of a multispectral classificator that employs high-performance computing techniques

The classification procedure to identify remote sensing signatures from a particular geographical region can be achieved using an accurate image classification approach which is based on multispectral sets and uses pixel statistics for the class description, and it is referred to as the Multispectra...

Full description

Saved in:
Bibliographic Details
Main Author: Villalon-Turrubiates, Ivan E.
Format: Conference Proceeding
Language:English
Subjects:
Image classification
image processing
Image segmentation
multispectral
Probes
Real-time systems
Remote sensing
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The classification procedure to identify remote sensing signatures from a particular geographical region can be achieved using an accurate image classification approach which is based on multispectral sets and uses pixel statistics for the class description, and it is referred to as the Multispectral Pixel Classification method. This paper presents a study of the performance that this approach provides for supervised segmentation and classification of sensed signatures for land use analysis and using high-performance computing techniques compared with traditional programming methodologies. The results obtained with this study uses real multispectral scenes obtained with remote sensing techniques (high-resolution optical images) to probe the efficiency of the classification technique.
ISSN:2153-7003
DOI:10.1109/IGARSS.2016.7729995