Machine learning on historic air photographs for mapping risk of unexploded bombs

Authors:
Stefano Merler;Cesare Furlanello;Giuseppe Jurman
Affiliations:
ITC-irst, Trento, Italy;ITC-irst, Trento, Italy;ITC-irst, Trento, Italy
Venue:
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
Year:
2005

Citing 5
Cited 0

Bagging predictors

Machine Learning
Learning to Recognize Volcanoes on Venus

Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Soft Margins for AdaBoost

Machine Learning
AdaCost: Misclassification Cost-Sensitive Boosting

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Boosting Trees for Cost-Sensitive Classifications

ECML '98 Proceedings of the 10th European Conference on Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe an automatic procedure for building risk maps of unexploded ordnances (UXO) based on historic air photographs. The system is based on a cost-sensitive version of AdaBoost regularized by hard point shaving techniques, and integrated by spatial smoothing. The result is a map of the spatial density of craters, an indicator of UXO risk.