The importance of video annotation is constantly rising, especially in areas of multimedia retrieval, semantic search and even in newest research in neuroscience. The list of pixel-accurate, hierarchical and automatic object detection tools is still empty, due to the excessive complexity. The approach is to roll out the automation to a problem specific detection algorithm. The \emph{Interactive Object Detection Framework} is able to capture this and support the operator with more general annotation actions, like ordering, filtering, correction or visualization. Furthermore, the framework operates with any kind of description, like time segments, shapes or histograms, using an MPEG-7 based internal data structure. Two sample detectors have been implemented and tested in the framework prototype and proved the reasonability of the concept.
All programming content is available at https://github.com/dakot/vilay-detect.
Downloads: