Skin detection with multispectral imagers onboard small unmanned aerial systems

Author

Sweetnich, Stephen R. ; Jacques, David R.

Author_Institution

Dept. of Syst. Eng. & Manage., Air Force Inst. of Technol., Wright-Patterson AFB, OH, USA

fYear

2014

Firstpage

200

Lastpage

206

Abstract

Dismount skin detection from an aerial platform has posed challenges for skin detection compared to ground-based platforms. A small, multispectral imager was constructed and tested on a SUAS. Computer vision registration, stereo camera calibration, and geolocation from autopilot telemetry were utilized to design a dismount detection platform. Close range comparison with a line scan HSI resulted in an average 5.112% difference in ROC AUC. This research indicated that SUAS-based Spectral Imagers are capable tools in dismount detection protocols.

Keywords

autonomous aerial vehicles; calibration; computer vision; image registration; image sensors; microrobots; sensitivity analysis; stereo image processing; ROC AUC; SUAS-based spectral imagers; autopilot telemetry; computer vision registration; dismount detection platform; dismount detection protocols; geolocation; ground-based platforms; line scan HSI; multispectral imager onboard small unmanned aerial systems; skin detection; stereo camera calibration; Cameras; Hyperspectral sensors; Image sensors; Matched filters; Measurement; Sensors; Skin; hyperspectral; multispectral; skin detection; small unmanned aerial systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace and Electronics Conference, NAECON 2014 - IEEE National

Print_ISBN

978-1-4799-4690-7

Type

conf

DOI

10.1109/NAECON.2014.7045803

Filename

7045803