Paper
30 August 2004 Annotation of UAV surveillance video
Todd Howlett, Mark A. Robertson, Dan Manthey, John Krol
Author Affiliations +
Abstract
Significant progress toward the development of a video annotation capability is presented in this paper. Research and development of an object tracking algorithm applicable for UAV video is described. Object tracking is necessary for attaching the annotations to the objects of interest. A methodology and format is defined for encoding video annotations using the SMPTE Key-Length-Value encoding standard. This provides the following benefits: a non-destructive annotation, compliance with existing standards, video playback in systems that are not annotation enabled and support for a real-time implementation. A model real-time video annotation system is also presented, at a high level, using the MPEG-2 Transport Stream as the transmission medium. This work was accomplished to meet the Department of Defense’s (DoD’s) need for a video annotation capability. Current practices for creating annotated products are to capture a still image frame, annotate it using an Electric Light Table application, and then pass the annotated image on as a product. That is not adequate for reporting or downstream cueing. It is too slow and there is a severe loss of information. This paper describes a capability for annotating directly on the video.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Todd Howlett, Mark A. Robertson, Dan Manthey, and John Krol "Annotation of UAV surveillance video", Proc. SPIE 5409, Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications, (30 August 2004); https://doi.org/10.1117/12.542427
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Video

Video surveillance

Surveillance

Unmanned aerial vehicles

Algorithm development

Computer programming

Detection and tracking algorithms

Back to Top