The article Towards a framework for agent-based image analysis of remote-sensing data has been published by the International Journal of Image and Data Fusion in March.
The article introduces a framework for agent-based image analysis (ABIA) of remote sensing data. Robust and transferable object-based solutions for automated image analysis, capable of analysing sets of images or even large image archives, are still rare. Object-based image analysis (OBIA) rule sets bear a high potential of transferability. The high complexity of image content however often makes human interaction necessary.
In order to automate the adaption and adjustment procedures, the authors (Hofmann, Lettmayer, Blaschke et.al) investigated the coupling, extension and integration of OBIA with the agent-based paradigm of ABIA.
They show that even with simple designed image object agents (IOAs) enabling agent-based control and simulation, an improvement of the initial classification is possible. The authors demonstrate the potential of ABIA to autonomously adapt image objects to unknown imaging situations. Link to article