30 April 2018 Scene analysis using semi-supervised clustering
Author Affiliations +
Abstract
This work performs scene analysis in order to represent and understand the elements contained in a defined area under the ground. Elements of interest are the ground layer, sub-surface layers, explosive hazards, and non-explosive (clutter) objects. The scene is composed of data collected by hand-held and vehicular-mounted ground penetrating radar (GPR) devices. In previous work, we segmented scenes into super-voxels and used a Markov Random Field (MRF) to combine super-voxels into layer regions. Here, we provide users with a training tool to annotate exemplar regions in sample data. Annotations associate must-link and cannot-link regions. Semi-supervised clustering is used to implement the Probability-Based Training Realignment (PBTR) algorithm. PBTR influences region labeling and increases the accuracy of scene representation.
Conference Presentation
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Peter J. Dobbins, Peter J. Dobbins, Joseph N. Wilson, Joseph N. Wilson, } "Scene analysis using semi-supervised clustering", Proc. SPIE 10628, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIII, 106280A (30 April 2018); doi: 10.1117/12.2304302; https://doi.org/10.1117/12.2304302
PROCEEDINGS
12 PAGES + PRESENTATION

SHARE
Back to Top