An evolutionary multi-agent system for object recognition in satellite images

Author

Miu, Hoi Shun ; Kwong Sak Leung ; Leung, Kwong Sak

Author_Institution

Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, China

Volume

1

fYear

2003

fDate

8-12 Dec. 2003

Firstpage

520

Abstract

This paper proposes a new approach to combine the knowledge-based model and the cooperation technique of evolutionary agents to identify the location of the desired object in a satellite image. The agents interact with the local information of the image pixels to search for the target objects through an evolutionary process. A new set of fitness function and evolutionary operators are defined for the process. The decentralized, bottom-up and evolutionary natures of the agents can be used to construct a robust system for object recognition in satellite images. The experimental results are satisfactory and have demonstrated the flexibility and power of the approach.

Keywords

evolutionary computation; image resolution; knowledge based systems; multi-agent systems; object recognition; remote sensing; satellite communication; search problems; bottom-up agents; cooperation technique; decentralized agents; evolutionary agents; evolutionary multiagent system; evolutionary operators; evolutionary process; fitness function; image pixels; knowledge-based model; local information; object recognition; robust system; satellite image; satellite images; target objects; Computer science; Computer vision; Face detection; Feature extraction; Image analysis; Image recognition; Multiagent systems; Object recognition; Robustness; Satellites;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 2003. CEC '03. The 2003 Congress on

Print_ISBN

0-7803-7804-0

Type

conf

DOI

10.1109/CEC.2003.1299620

Filename

1299620