Share Email Print

Proceedings Paper

Object and event recognition for aerial surveillance
Author(s): Yi Li; Indriyati Atmosukarto; Masaharu Kobashi; Jenny Yuen; Linda G. Shapiro
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Unmanned aerial vehicles with high quality video cameras are able to provide videos from 50,000 feet up that show a surprising amount of detail on the ground. These videos are difficult to analyze, because the airplane moves, the camera zooms in and out and vibrates, and the moving objects of interest can be in the scene, out of the scene, or partly occluded. Recognizing both the moving and static objects is important in order to find events of interest to human analysts. In this paper, we describe our approach to object and event recognition using multiple stages of classification.

Paper Details

Date Published: 19 May 2005
PDF: 11 pages
Proc. SPIE 5781, Optics and Photonics in Global Homeland Security, (19 May 2005); doi: 10.1117/12.609109
Show Author Affiliations
Yi Li, Univ. of Washington (United States)
Indriyati Atmosukarto, Univ. of Washington (United States)
Masaharu Kobashi, Univ. of Washington (United States)
Jenny Yuen, Univ. of Washington (United States)
Linda G. Shapiro, Univ. of Washington (United States)

Published in SPIE Proceedings Vol. 5781:
Optics and Photonics in Global Homeland Security
Theodore T. Saito, Editor(s)

© SPIE. Terms of Use
Back to Top