This paper highlights the use of situated artificial institution (SAI) within a hybrid, interactive, normative multi-agent system to regulate human collaboration in crisis management. Norms regulate the actions of human actors based on the dynamics of the environment in which they are situated. This dynamics results from both environment evolution and actors’ actions. Our objective is to situate norms in the environment in order to provide a context-aware crisis regulation. However, this coupling must be a loose one to keep both levels independent and easyto-change in order to face the complex and changing crisis situations. To that aim, we introduce a constitutive level between environmental and normative states providing a loose coupling of normative regulation with environment evolution. Norms are thus no more referring to environmental facts but to status functions, i.e., the institutional interpretation of environmental facts through constitutive rules. We present how this declarative and distinct SAI modelling succeeds in managing the crisis with a context-aware crisis regulation.

The purpose of this paper is to present a new approach to support distant human collaboration under tangible environments. Our aim is not to build and transmit across the distant tables an accurate and complete description of the human activity. Rather, our choice is to restrict communication to the possibilities offered by the tangible tables (tangible object moves and virtual feedback). In this context, we propose to focus on the elicitation and sharing of the norms and conventions that frame human activity, a core issue to sustain proper collaboration. We promote in this perspective the design of a normative multiagent system, whose goal is to emulate the influence of these norms on distant cooperation, thus bringing mutual awareness to the human partners. The role of such system is (i) to represent these potentially heterogeneous and evolving systems of norms in a declarative and distributed way, (ii) to filter the interpretation and communication of human activity according to these norms, and (iii) to build an informed virtual feedback providing information about the conformity of action with respect to the conventions. An application to the RISK game is presented to exemplify the proposed approach.

We propose in this paper a novel approach for human activity follow-up that draws on a distinction between domain-dependent and observer-dependent viewpoints. While the domain-dependent (or intrinsic) viewpoint calls for the follow-up and interpretation of human activity per se, the observer-dependent (or extrinsic) viewpoint calls for a more subjective approach, which may involve an evaluative dimension, regarding the human activity or the interpretation process itself. Of interest are the mutual dependencies that tie both processes over time: the observer viewpoint is known to shape domain-dependent interpretation, while domain-dependent interpretation is core to the evolution of the observer viewpoint. We make a case for using a normative multi-agent approach to design monitoring systems articulating both viewpoints. We illustrate the proposed approach potential by examples from daily life scenarios.

Accurate tissue and structure segmentation of magnetic resonance (MR) brain scans is critical in several applications. In most approaches this task is handled through two sequential steps. We propose to carry out cooperatively both tissue and subcortical structure segmentation by distributing a set of local and cooperative Markov random field (MRF) models Tissue segmentation is performed by partitioning the volume into subvolumes where local MRFs are estimated in cooperation with their neighbors to ensure consistency. Local estimation fits precisely to the local intensity distribution and thus handles nonuniformity of intensity without any bias field modelization. Similarly, subcortical structure segmentation is performed via local MRF models that integrate localization constraints provided by a priori fuzzy description of brain anatomy. Subcortical structure segmentation is not reduced to a subsequent processing step but joined with tissue segmentation: the two procedures cooperate to gradually and conjointly improve model accuracy. We propose a framework to implement this distributed modeling integrating cooperation, coordination, and local model checking in an efficient way. Its evaluation was performed using both phantoms and real 3 T brain scans, showing good results and in particular robustness to nonuniformity and noise with a low computational cost. This original combination of local MRF models, including anatomical knowledge, appears as a powerful and promising approach for MR brain scan segmentation.

The paper addresses the problem of controlling situated image understanding processes. Two complementary control styles are considered and applied cooperatively, a deliberative one and a reactive one. The role of deliberative control is to account for the unpredictability of situations, by dynamically determining which strategies to pursue, based on the results obtained so far and more generally on the state of the understanding process. The role of reactive control is to account for the variability of local properties of the image by tuning operations to subimages, each one being homogeneous with respect to a given operation. A variable organization of agents is studied to face this variability. The two control modes are integrated into a unified formalism describing segmentation and interpretation activities. A feedback from high level interpretation tasks to low level segmentation tasks thus becomes possible and is exploited to recover wrong segmentations. Preliminary results in the field of liver biopsy image understanding are shown to demonstrate the potential of the approach.

Two complementary control styles, deliberative and reactive types, are applied to account for unpredictability of situations and variability of local properties in image interpretation processes. Deliberative control is based on attributed grammars and local variability is managed by a variable organisation of agents. Feedback from interpretation to segmentation becomes possible and is exploited to recover wrong segmentation. Experimental results illustrate the potential of the approach.

This paper presents a multi-agent system for the segmentation of deformable moving objects. Our application concerns cell image sequences. The agents integrate three basic behaviors: segmentation, interaction and reproduction. The segmentation behavior is based on region growing methods. Pixels are evaluated upon static and motion-based criteria. The interaction behavior allows two agents to merge or to negotiate parts of regions. The negotiation can be seen us a segmentation refinement process done by the agents. Finally, the reproduction behavior defines an exploration strategy of the image frames. Agents can start other agents around them, or they can duplicate themselves in the next frame. Segmentation of the frames is done in pipeline, where previous information is used to help the process of the current frame. One unique agent model exists. Segmentation and reproduction behaviors are specialized on the execution time. Some results from an existing prototype are shown and analysed.

The purpose of the paper is to describe a multi-agent approach to edge detection as a distributed optimization problem. In this framework, edge detection is seen as a goal to be reached, expressed in terms of the minimization of an estimated edge detection error with respect to an ideal reference which is not explicitly known. Furthermore, an original method for distributed optimization is illustrated based on an initial partitioning of the image into zones corresponding to different characteristics. The initial partitioning can be further refined, based on the evaluation of the result obtained so far. Consistency between adjacent zones in the image is also taken into account. The implementation of this method as a multi-agent system is presented demonstrating the interest in using such systems for solving distributed optimization problems.

This paper presents a new approach for the design of cooperative and adaptive segmentation systems, where each method is implemented as an incremental low level process controlled at a higher level by a task-independant scheduler, like in a multitask operating system. This enables a dynamic and opportunistic process creation, to take "better decisions" in a more informed way. The process scheduling order allows to solve the same problem with a depth first or a breadth first control strategy. The potential interest of the approach is illustrated on a variety of examples.

The major problem in the segmentation task is a problem of decision. The authors propose five guidelines to solve the problem and present the software architecture of a low-level segmentation system that would solve the problem according to the guidelines. They have already developed one module: a region growing method that aggregates pixels according to the type of the region and some thresholds calculated dynamically. Some results obtained are very encouraging. The authors attempt to detect edges with the same philosophy.>

The design of architectures is presented for knowledge-based image diagnosis systems (KIDS). Two basic constructs (knowledge sources and knowledge processors) are first presented as modeling the capabilities involved in the tasks of problem modeling and solving. These constructs are then specialized to fit the image-interpretation problem. The architecture is conceived as a network of agents, each responsible for a well-delimited task. The agents cooperate in solving the problem at hand. It is obtained by distributing the knowledge, expertise, and control abilities. Examples are provided in the field of biomedicine (cyto- and histopathology).>

Image processing methods (segmentation) are presented in connection with a modeling of image structure. An image is represented as a set of primitives, characterized by their type, abstraction level, and a list of attributes. Entities (regions for example) are then described as a subset of primitives obeying particular rules. Image segmentation methods are discussed, according to the associated image modeling level. Their potential efficacity is compared, when applied to cytologic image analysis.

An iterative segmentation method is presented and illustrated on specific examples. Full control of each iteration step is obtained by combining local and global properties according to a model of the image structure. A consistent convergence criterion is derived from additional image structure properties and a test is proposed to evaluate adequacy of segmentation.