Accession Number:

ADA557664

Title:

Spectral Detection of Human Skin in VIS-SWIR Hyperspectral Imagery without Radiometric Calibration

Descriptive Note:

Master's thesis

Corporate Author:

AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH GRADUATE SCHOOL OF ENGINEERING AND MANAGEMENT

Personal Author(s):

Report Date:

2012-03-01

Pagination or Media Count:

113.0

Abstract:

Many spectral detection algorithms require precise ground truth measurements that are hand-selected in the image to apply radiometric calibration, converting image pixels into estimated re ectance vectors. That process is impractical for mobile, real-time hyperspectral target detection systems, which cannot empirically derive a pixel-to-re ectance relationship from objects in the image. Implementing automatic target recognition on high-speed snapshot hyperspectral cameras requires the ability to spectrally detect targets without performing radiometric calibration. This thesis demonstrates human skin detection on hyperspectral data collected at a high frame rate without using calibration panels, even as the illumination in the scene changes. Compared to an established skin detection method that requires calibration panels, the illumination-invariant methods in this thesis achieve nearly as good detection performance in sunny scenes and superior detection performance in cloudy scenes.

Subject Categories:

  • Numerical Mathematics
  • Optical Detection and Detectors

Distribution Statement:

APPROVED FOR PUBLIC RELEASE