1,720,973 research outputs found

    Event Analysis and Understanding for Situational Awareness Support

    No full text
    In this paper, we propose a framework for the assessment, interpretation and understanding of situations in a visual surveillance scenario. An upper level processing layer exploits abductive reasoning over data provided by low level detection, classification and tracking algorithms. The system discussed is Description Logics driven and benefits from the computability of first-order logic semantics together with the manageability characteristics of ontology based systems. Event occurrence frequency is taken into account to focus on “anomalous facts,” by combining a priori knowledge, provided by domain experts, with statistical information incrementally gathered through the assessment of the environment under surveillance. The framework is aimed at supplying security system operators with a set of the most probable explanations of observed facts to improve and speed up the decision process

    Data fusion and abductive inference for metaphor resolution: A bridging discussion

    No full text
    Since the 1980s, metaphor has been recognized as a pervasively diffused phenomenon in communication, absolutely not restricted to rhetoric and linguistic phenomena, involving structured concepts, relations, and matching 'rules'. Metaphor resolution, that is metaphor understanding, as well as metaphor creation, has become an issue in automated processing and understanding of natural language as well as of mixed visual communication. It can be showed as a process of structure finding and mapping procedure between conceptual denotation-connotation structures necessary for interpretation. Creative abduction is then showed to be the pattern inference required to work out structure-mappings in corresponding nodes as present in metaphors. In this paper, we review some key issues (definitions, typologies, theoretical problems) involving the concept of 'metaphor' and survey some definitions and concepts emerging in contemporary debate on abductive inference. Finally, we argue that metaphor understanding process can be recognized as a fusion tractable problem, allowing the exploitation of frameworks and algorithms of such domain. © Cambridge University Press, 2016
    corecore