Abstract
This paper presents an automatic target detection (ATD) system for use with unmanned aerial vehicle (UAV) imagery. Extracting reliable features under all conditions from a 2-D projection of a target in UAV imagery is a difficult problem. However, since the target size information is usually invariant to the image formation process, we propose an algorithm for automatically estimating the size of a 3-D target by using its 2-D projection. The size information in turn becomes an important feature to be used in a knowledge-driven, multi-resolution-based algorithm for automatically detecting targets in UAV imagery. Experimental results show that our proposed ATD algorithm provides outstanding detection performance, while significantly reducing the false alarm rate and the computational complexity.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of SPIE - The International Society for Optical Engineering |
Editors | F.A. Sadjadi |
Pages | 136-147 |
Number of pages | 12 |
Volume | 5094 |
DOIs | |
State | Published - 2003 |
Event | PROCEEDINGS OF SPIE SPIE - The International Society for Optical Engineering: Automatic Target Recognition XIII - Orlando, FL, United States Duration: Apr 22 2003 → Apr 24 2003 |
Other
Other | PROCEEDINGS OF SPIE SPIE - The International Society for Optical Engineering: Automatic Target Recognition XIII |
---|---|
Country/Territory | United States |
City | Orlando, FL |
Period | 4/22/03 → 4/24/03 |
Keywords
- Automatic target detection
- Multi-scale image processing
- Region-of-interest
- Target size estimation
- Unmanned aerial vehicle
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Condensed Matter Physics