Self-adaptive road tracking in hyperspectral data for C-IED

Hendrik Schilling; Wolfgang Gross; Wolfgang Middelmann

doi:10.1117/12.929695

15 October 2012 Self-adaptive road tracking in hyperspectral data for C-IED

Hendrik Schilling, Wolfgang Gross, Wolfgang Middelmann

Proceedings Volume 8515, Imaging Spectrometry XVII; 85150S (2012) https://doi.org/10.1117/12.929695
Event: SPIE Optical Engineering + Applications, 2012, San Diego, California, United States

Abstract

For Counter Improvised Explosive Devices purposes, main routes including their vicinity are surveyed. In future military operations, small hyperspectral sensors will be used for ground covering reconnaissance, complementing images from infrared and high resolution sensors. They will be mounted on unmanned airborne vehicles and are used for on-line monitoring of convoy routes. Depending of the proximity to the road, different regions can be defined for threat assessment. Automatic road tracking can help choosing the correct areas of interest. Often, the exact discrimination between road and surroundings fails in conventional methods due to low contrast in pan-chromatic images at the road boundaries or occlusions. In this contribution, a novel real-time lock-on road tracking algorithm is introduced. It uses hyperspectral data and is specifically designed to address the afore- mentioned deficiencies of conventional methods. Local features are calculated from the high-resolution spectral signatures. They describe the similarity to the actual road cover and to either roadside. Classification is per- formed to discriminate the signatures. To improve robustness against variations in road cover, the classification results are used to progressively adapt the road and roadside classes. Occlusions are treated by predicting the course of the road and comparing the signatures in the target area to previously determined road cover signa- tures. The algorithm can be easily extended to show regions of varying threat, depending on the distance to the road. Thus, complex anomaly detectors and classification algorithms can be applied to a reduced data set. First experiments were performed for AISA Eagle II (400nm - 970nm) and AISA Hawk (970nm - 2450nm) data

Citation Download Citation

Hendrik Schilling, Wolfgang Gross, and Wolfgang Middelmann "Self-adaptive road tracking in hyperspectral data for C-IED", Proc. SPIE 8515, Imaging Spectrometry XVII, 85150S (15 October 2012); https://doi.org/10.1117/12.929695

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available