| As an important problem in modern scientific research field, study of data 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. As the level 2 processing of data fusion, Situation Assessment is to recognize the activity patterns, conclude the intentions of enemy and forecast the changes of near future situation by analyzing the data frames processed and quantitatively or qualitatively analyzing situation colligated of foe, friend and battlefield environment based on the level 1 fusion. The paper mainly research on the target clustering and the intention assessment to foe of Situation Assessment. The contents of the thesis are outlined as follows:1. 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. A Situation Assessment model based on template-matching aiming at intent assessment to foe is put forward, based on many Situation Assessment reasoning frame described.2.Event inspecting and target clustering which is two important aspects of situation perception is analyzed and the knowledge expressed method of event inspecting is perfected for more. A multiple comparability measuring with weight method of target clustering, which enhance distinguishing target ability and take from error clustering probability, is put forward.3.situation repository and event relationship of intention assessment reasoning is analyzed through discussing intention assessment reasoning of Situation Assessment. intention assessment reasoning frame is more studied. A template-matching method, which is illuminated feasibility in target intention reasoning in case, based on D-S evidence theory is put forward. |
PDF Full Text Request