Study Of Situation Assessment Techniques In Information Fusion System

As an important problem in modern scientific research field, study of multi-sensor information fusion technique aims to how to combine information from multiple sensors and other associated sources so that the resulting estimation and inference is, in terms of precision improvement and uncertainty reduction, better than would be possible if any of the sources were used individually. Situation Assessment is key technique for high level processing of information fusion. There is no doubt that real-time situation assessment capability for aid decision-making in C~4 ISR system has a significant effect on adapting modern war. The research theme of the thesis does concentrate on situation assessment theories and situation assessment operation system for aid decision-making. The contents of the thesis are outlined as follows:1. The thesis first studies the function for fulfilling situation assessment. A three-level functional processing model, which consists of current situation perception, current situation recognition and future situation projection, is set up and each level is analyzed in detail. Based on analyzing inference frame, the inference algorithms for situation assessment are discussed. For situation assessment is a gradually solving process that classifies real-time information on different abstract level, a multi-level and multi-hierarchical blackboard model is put forward. The model has a better parallel property and it can be used in large-scale complex military problems.2. Event detection and target classification are two important problems in situation perception. The event types of targets are analyzed and an event detection method based on fuzzy logic is presented. The hierarchy of target classification is discussed and then a method based on fuzzy equivalence relation is adopted for implementing target classification. The thesis proposes a synthetic algorithm for fulfilling increased group formation by using the nearest-neighbor method and field knowledge. Finally, the operation algorithms for maintaining group structure are proposed.3. On the basis of analyzing knowledge representation method, the thesis focuses on constructing the battlefield knowledge base based on schema. A template-matching algorithm for achieving situation recognition is put forward. Finally, CLIPS, a tool of expert system, is used to express events, activities and military plans template, which shows the efficiency and feasibility of making use of template matching in situation assessment.4. Situation assessment is essentially a process of plan recognition. The planrecognition theory is discussed. For the shortage of plan recognition method presented by Kautz in controlling mechanism, a plan recognition method based on plan knowledge graph is discussed in detail. An instance of tactical intelligent planning is analyzed and a situation assessment model combined tactical intelligent planning system and tactical plan recognition system is proposed. On the basis of multi-agent structure, a template-matching algorithm for multi-entity situation assessment is presented.5. The uncertain causal inference methods for situation assessment are studied. By using D-S evidential theory, an information fusion method for situation assessment system is put forward. Based on the hierarchy model in situation assessment, a Bayesian network for solving situation assessment problem is presented by using the algorithm for evidence inference and information propagation in hierarchy hypothesis. Examples are provided to illustrate the solving process for situation assessment, which shows the feasibility of the presented method used for solving problems of situation assessment.