Thinking inside the box: A comprehensive spatial representation for video analysis

Anthony G. Cohn, Jochen Renz, Muralikrishna Sridhar

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    22 Citations (Scopus)

    Abstract

    Successful analysis of video data requires an integration of techniques from KR, Computer Vision, and Machine Learning. Being able to detect and to track objects as well as extracting their changing spatial relations with other objects is one approach to describing and detecting events. Different kinds of spatial relations are important, including topology, direction, size, and distance between objects as well as changes of those relations over time. Typically these kinds of relations are treated separately, which makes it difficult to integrate all the extracted spatial information. We present a uniform and comprehensive spatial representation of moving objects that includes all the above spatial/temporal aspects, analyse different properties of this representation and demonstrate that it is suitable for video analysis.

    Original languageEnglish
    Title of host publication13th International Conference on the Principles of Knowledge Representation and Reasoning, KR 2012
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages588-592
    Number of pages5
    ISBN (Print)9781577355601
    Publication statusPublished - 2012
    Event13th International Conference on the Principles of Knowledge Representation and Reasoning, KR 2012 - Rome, Italy
    Duration: 10 Jun 201214 Jun 2012

    Publication series

    NameProceedings of the International Conference on Knowledge Representation and Reasoning
    ISSN (Print)2334-1025
    ISSN (Electronic)2334-1033

    Conference

    Conference13th International Conference on the Principles of Knowledge Representation and Reasoning, KR 2012
    Country/TerritoryItaly
    CityRome
    Period10/06/1214/06/12

    Fingerprint

    Dive into the research topics of 'Thinking inside the box: A comprehensive spatial representation for video analysis'. Together they form a unique fingerprint.

    Cite this