Skin Detection With Small Unmanned Aerial Systems by Integration of Area Scan Multispectral Imagers and Factors Affecting Their Design and Operation

Skin Detection With Small Unmanned Aerial Systems by Integration of Area Scan Multispectral Imagers and Factors Affecting Their Design and Operation

Stephen R. Sweetnich, David R. Jacques
Copyright: © 2019 |Pages: 20
DOI: 10.4018/978-1-5225-8365-3.ch009
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Dismount skin detection from an aerial platform has posed challenges compared to ground-based platforms. A small, area scanning multispectral imager was constructed and tested on a Small Unmanned Aerial System (SUAS). Computer vision registration, stereo camera calibration, and geolocation from autopilot telemetry were utilized to design a dismount detection platform. The test expedient prototype was 2kg and exhibited skin detection performance similar to a larger line scan hyperspectral imager (HSI). Outdoor tests with a line scan HSI and the prototype resulted in an average 5.112% difference in Receiver Operating Characteristic (ROC) Area Under Curve (AUC). This research indicated that SUAS-based Spectral Imagers are capable tools in dismount detection protocols.
Chapter Preview
Top

Scope

Reasearch Objective

The main focus of this research was to measure the feasibility of a skin detection multispectral sensor on an SUAS for Search and Rescue operations. To measure the utility of a system, subjective and objective metrics were used. By using standardized metrics, the detection system was compared against a wide range of detection systems. There were four main investigative questions:

  • •

    Is MSI effective for dismount detection on an SUAS?

  • •

    What type of MSI system is needed for an aerial platform?

  • •

    Which camera parameters are most critical for aerial dismount detection?

  • •

    What metrics are best to compare dismount detection ability?

Assumptions and Limitations

The system for skin detection was limited to the sensors available at AFIT, including the MSI imager, visible spectrum (VIS) imager, and bandpass filters. The SUAS used for the skin detection was limited to the airframes available at the AFIT Autonomy and Navigation Technology (ANT) Center. For the time available for flight test, a specific loiter pattern was utilized, which was optimized to the camera parameters (e.g., resolution, focal length). Due to the cost and size of a digital video acquisition and transmission system, onboard storage of imagery was performed in flight test. Weather conditions (sunlight, rain, wind …) were unavoidable due to limited test range time, and they affected flight duration, autopilot waypoint tracking, and sensor parameters. The research assumed that each dismount had skin which was visible from the air. A flat earth model was used for processing flight data.

Complete Chapter List

Search this Book:
Reset