Affiliation:
1. Hunan University of Science and Technology
Abstract
With the rapid development of spatial information technology and the increasingly artificial intelligence knowledge, MAS plays a more and more important role in conducting image segmentation.Considering the shortcomings of current segmentation method,a new algorithm based on MAS theory is proposed, It combines spectral and shape information in region merging.employer a number of agents to control the merging procedure in different regions and make the global merging control more optimal by utilizing the advantages of MAS,The results show that the algorithm is very effective for image segmentation both in urban and mountainous areas.
Publisher
Trans Tech Publications, Ltd.
Reference7 articles.
1. FANG Lei, ANTSAKLIS Panos J. Asynchronous consensus protocols using nonlinear paracontractions theory [J]. IEEE Transaction on Automatic Control, 2008, 53(10): 2351−2355.
2. TIAN Yu-ping, LIU Cheng-lin. Consensus of multi-agent systems with diverse input and communication delays [J]. IEEE Transactionon Automatic Control, 2008, 53(9): 2122−2128.
3. X. F. Fan, X. W. Jiang, W. H. Huang, et al. Research of multi-agent system based satellite fault diagnosis technology. Journal of Harbin Institute of Technology, 2002, 9(3): 239–244.
4. S. F. Yuan, X. S. Lai, X. Zhao, et al. Distributed structural health monitoring system based on smart wireless sensor and multi-agent technology. Smart Materials and Structures, 2006, 15(1): 1–18.
5. Batty M. Agent-based Technologies and GIS: Simulating Crowding, Panic and Disaster Management, in Frontiers of Geographic Information.