vitrivr allows you to use novel methods to search in videos
What is vitrivr?
vitrivr is an innovative video retrieval engine that offers a rich set of different query paradigms to search in large video collections. This includes traditional keyword queries but also query-by-example, query-by-sketch, and motion queries that rely on intrinsic vide features features such as, for instance, color, edge or motion information. At the user interface, sample images or sample videos (query-by-example), hand-drawn sketches (query-by-sketch) or flow fields (motion queries) and combinations thereof can be used. The system is composed of the flexible retrieval engine Cineast, and the storage back-end ADAM.
At the moment vitrivr supports searching using color, edges and motion. However, thanks to its flexible architecture, it is able to support many more retrieval modes. This is what we want to explore further in GSoC.
What is Cineast?
Cineast is a content-based video retrieval engine which retrieves video sequences based on their visual content. It supports Query-by-Example as well as Query-by-Sketch by using a multitude of low-level visual features in parallel.
What is ADAM?
ADAM is a database system to store and retrieve multimedia data. It provides Boolean retrieval and similarity search and makes use of a various index structures for efficient retrieval.
vitrivr 2016 Projects
Cthulhu - Vitrivr Feature Extraction PipelineCthulhu is a simple server-client-based job scheduler developed in Java; named after H.P. Lovecraft's part-octopus god (because it will be able to...
Motion-based Retrieval: Feature ExtractionCurrent system has 3 problems: 1) It doesn’t account for camera motion; 2) The moving objects are not separated from the background; 3) The motion...
Natural Language Query InterfaceToday with the advancement in technology, speech recognition applications are becoming more and more useful. Currently vitrivr supports video...