Share Email Print

Proceedings Paper

Temporal fusion for de-noising of RGB video received from small UAVs
Author(s): Amber D. Fischer; Kyle J. Hildebrand
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

Monitoring video data sources received from UAVs is especially challenging because of the quality of the video received. Due to the individual characteristics of the unmanned platform and the changing environment, the important elements in the scene are not always observable or easily identified. In addition to typical sensor noise, significant image degradation can occur during transmission of the video from an airborne platform. Interference from other transmitters, analog noise in the embedded avionics, and multi-path effects can corrupt the video signal during transmission, introducing distortion in the video received at the ground. In some cases, the loss of signal is so severe; no information is received in portions of an image frame. To improve the corrupt video, we capitalize on the oversampling in the temporal domain (across video frames), applying a data fusion approach to de-noise the video. The resulting video retains the significant scene content and dynamics, without distracting artifacts from noise. This allows humans to easily ingest the information from the video, and make it possible to utilize further video exploitation algorithms such as object detection and tracking.

Paper Details

Date Published: 26 April 2010
PDF: 10 pages
Proc. SPIE 7668, Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications VII, 76680V (26 April 2010); doi: 10.1117/12.851810
Show Author Affiliations
Amber D. Fischer, 21st Century Systems, Inc. (United States)
Kyle J. Hildebrand, 21st Century Systems, Inc. (United States)

Published in SPIE Proceedings Vol. 7668:
Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications VII
Daniel J. Henry, Editor(s)

© SPIE. Terms of Use
Back to Top