Landmine detection using IR image segmentation by means of fractal dimension analysis

This work is concerned with buried landmines detection by long wave infrared images obtained during the heating or cooling of the soil and a segmentation process of the images. The segmentation process is performed by means of a local fractal dimension analysis (LFD) as a feature descriptor. We use...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Abbate, H.A., Gambini, J., Delrieux, C., Castro, E.H.
Formato: CONF
Materias:
Classification
Fractal dimension
Infrared imagery
Segmentation
Box-counting dimension
Buried landmines
Computational costs
Feature descriptors
Fractal dimension analysis
IR images
K-means method
Land mine detection
Local fractal dimension
Long wave infrared
Segmentation process
Segmentation techniques
Bombs (ordnance)
Explosives
Image segmentation
Infrared imaging
Mining
Partial discharges
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_0277786X_v7303_n_p_Abbate
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
Descripción
Sumario:This work is concerned with buried landmines detection by long wave infrared images obtained during the heating or cooling of the soil and a segmentation process of the images. The segmentation process is performed by means of a local fractal dimension analysis (LFD) as a feature descriptor. We use two different LFD estimators, box-counting dimension (BC), and differential box counting dimension (DBC). These features are computed in a per pixel basis, and the set of features is clusterized by means of the K-means method. This segmentation technique produces outstanding results, with low computational cost. © 2009 SPIE.

Ejemplares similares