Share Email Print
cover

Proceedings Paper

Multiple-instance learning-based sonar image classification
Author(s): J. Tory Cobb; Xiaoxiao Du; Alina Zare; Matthew Emigh
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

An approach to image labeling by seabed context based on multiple-instance learning via embedded instance selection (MILES) is presented. Sonar images are first segmented into superpixels with associated intensity and texture feature distributions. These superpixels are defined as the "instances" and the sonar images are defined as the "bags" within the MILES classification framework. The intensity feature distributions are discrete while the texture feature distributions are continuous, thus the Cauchy-Schwarz divergence metric is used to embed the instances in a higher-dimensional discriminatory space. Results are given for labeled synthetic aperture sonar (SAS) image database containing images with a variety of seabed textures.

Paper Details

Date Published: 3 May 2017
PDF: 8 pages
Proc. SPIE 10182, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXII, 101820H (3 May 2017); doi: 10.1117/12.2262530
Show Author Affiliations
J. Tory Cobb, Naval Surface Warfare Ctr. Panama City Div. (United States)
Xiaoxiao Du, Univ. of Missouri (United States)
Alina Zare, Univ. of Florida (United States)
Matthew Emigh, Naval Surface Warfare Ctr. Panama City Div. (United States)


Published in SPIE Proceedings Vol. 10182:
Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXII
Steven S. Bishop; Jason C. Isaacs, Editor(s)

© SPIE. Terms of Use
Back to Top