Markerless Object Recognition on a Mobile Phone

I implemented a markerless object recognition that processes multiple camera images per second on recent mobile phones. The algorithm combines a stripped down SIFT with a scalable vocabulary tree and a simple feature matching.
Based on this algorithm we implemented a simple application which is shown in the video below. The stuff is described in more detail in a paper titled “What is That? Object Recognition from Natural Features on a Mobile Phone” that we submitted to MIRW’09.

4 thoughts on “Markerless Object Recognition on a Mobile Phone

  1. Hans Eilers

    Hello Niels,
    I have read your paper and seen you video and would like to know if the prototype is available. Is the code open sourced or otherwise available?

    Your response is greatly appreciated.

  2. André Hoffmann

    Hallo Niels,

    eigentlich die selbe Frage wie mein Vorgänger. Ich würde es gern auf Java protieren um damit (später) ein Spiel zu programmieren.

    Vielen Dank.


    PS: Das Video ist ganz witzig 😀 Vorallem das Schaf.

  3. Nicolas

    Hey Niels, can you share the AndTrack code? It will be great to have the only Android object recognition example! Great work!

  4. hid

    hi there, is this an open source code? if it is, it would be nice if i can get to take a look at it 🙂 more prefered Android than java.
    hope to hear from you soon.

Leave a Reply

Your email address will not be published. Required fields are marked *