Layered Cooperation of Macro Agents and Micro Agents in Cooperative Active Contour Model

Authors:
Noriko Matsumoto;Norihiko Yoshida;Shuji Narazaki
Affiliations:
Division of Mathematics, Electronics and Informatics, Saitama University, Saitama, Japan 338-8570;Division of Mathematics, Electronics and Informatics, Saitama University, Saitama, Japan 338-8570;Division of Mathematics, Electronics and Informatics, Saitama University, Saitama, Japan 338-8570
Venue:
Agent Computing and Multi-Agent Systems
Year:
2009

Citing 8
Cited 0

Boundary Finding with Parametrically Deformable Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active shape models—their training and application

Computer Vision and Image Understanding
Encoding of a priori Information in Active Contour Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Deformable Contours: Modeling and Extraction

IEEE Transactions on Pattern Analysis and Machine Intelligence
Boundary Finding with Prior Shape and Smoothness Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Cooperative active contour model and its application to remote sensing

Proceedings of the 2006 ACM symposium on Applied computing
Improvement of active contour model with decentralized cooperative processing and its application to remote sensing

International Journal of Knowledge-based and Intelligent Engineering Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have proposed Multi-Snake , which realizes boundary detection in image recognition with the layered cooperation of micro agents and macro agents. Cooperation in a set of micro agents constructs the behavior of a macro agent, and cooperation of the micro agents are integrated to cooperation of the macro agents. This mechanism makes the application more dynamic and flexible. Our previous proposals dealt with cooperation between some macro agents of the same kind. This paper focuses on the cooperation of macro agents of different kinds: sensor-based macro agents and model-based macro agents. We show that our proposal makes estimation improved and more robust. We verify the effectiveness of our proposal through some experiments using artificial images and real images.