Clustering approaches to feature change detectionMS3

Identifying meaningful changes between two multi-temporal images is a problem with application in many types of sensing modalities and visual monitoring. This presentation examines the usage of k-means clustering in color space to detect changes to an image collected by synthetic aperture sonar system in the form of new objects added to the scene. For simple images with a limited number of colors, new objects can be detected by examining the change between the optimal number of clusters for the original and modified images.

This presentation is part of Minisymposium “MS3 - Applications of Imaging Modalities beyond the Visible Spectrum (2 parts)
organized by: Max Gunzburger (Florida State University) , G-Michael Tesfaye (Naval Surface Warfare Center, Panama City) , Janet Peterson (Florida State University) .

G-Michael Tesfaye (Naval Surface Warfare Center, Panama City)
Max Gunzburger (Florida State University)
Janet Peterson (Florida State University)
change detection, image registration, image segmentation