Share Email Print

Proceedings Paper

Automated, near real-time inspection of commercial sUAS imagery using deep learning
Author(s): Chris Kawatsu; Ben Purman; Aaron Zhao; Andy Gillies; Mike Jeffers; Paul Sheridan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Commercial small Unmanned Aerial Systems (sUAS) have become popular for real-time inspection tasks due to their cost-effectiveness at covering large areas quickly. They can produce vast amounts of image data at high resolution, with little user involvement. However, manual review of this information can’t possibly keep pace with data collection rates. For time-sensitive applications, automated tools are required to locate objects of interest. These tools must perform at very low false alarm rates to avoid overwhelming the user. We approach real-time inspection as a semi-automated problem where a single user can provide limited feedback to guide object detection algorithms.

Paper Details

Date Published: 3 May 2018
PDF: 8 pages
Proc. SPIE 10640, Unmanned Systems Technology XX, 1064005 (3 May 2018); doi: 10.1117/12.2304967
Show Author Affiliations
Chris Kawatsu, Soar Technology, Inc. (United States)
Ben Purman, Soar Technology, Inc. (United States)
Aaron Zhao, Soar Technology, Inc. (United States)
Andy Gillies, Soar Technology, Inc. (United States)
Mike Jeffers, Soar Technology, Inc. (United States)
Paul Sheridan, Soar Technology, Inc. (United States)

Published in SPIE Proceedings Vol. 10640:
Unmanned Systems Technology XX
Robert E. Karlsen; Douglas W. Gage; Charles M. Shoemaker; Hoa G. Nguyen, Editor(s)

© SPIE. Terms of Use
Back to Top