addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscontroller-playcrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupshelp-with-circleimageimagesinstagramFill 1light-bulblinklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1ShapeoutlookpersonJoin Group on CardStartprice-ribbonprintShapeShapeShapeShapeImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruserwarningyahoo


This time we'll be working on Photogrammetry -- extracting information about physical objects from one or more images of the object.  In particular, we'll be looking at constructing 3D models of objects from images of the objects.

Watch this space for more specifics.

Join or login to comment.

  • JJ S.

    Finally, for next time:

    We decided to put together a puzzle. Given a picture of all the puzzle pieces, can you show the solution?

    Maybe you can start by just counting to see how many pieces there are. Are there any pieces missing?

    We also considered:
    . Stereo Pairs:
    Create a 3D perspective using stereo pairs of images.
    . Scaling: What size is object A relative to object B in the picture? ie: how tall and wide is the tree given that John is 6ft tall and halfway between the camera and the trunk of tree.
    . Panoramic Stitching (Mosaic)


    Feel free to post more links and/or project ideas here. (Remember 1000 char limit, so use a notepad).

    Thanks again, -JJ

    July 28, 2014

  • JJ S.

    We also talked briefly about some types of aberations from the nature of the camera:
    . Distortion
    . Magnification
    . Angular Motion on a pixel.

    And we mentioned the use of streaming video versus still images and the use of onboard-CPU versus cloud-CPU. IMHO: Onboard-CPU with video might provide the best UX.

    July 28, 2014

  • JJ S.

    Stoney was our resident expert (, and we saw the TRNIO app in action. John took multiple images around his laptop and, after uploading to the server and waiting to process, we were given a 3D texturized model to play with.

    We also saw sceene in action - similarly John generated a sudo-3D image of his laptop.

    A bit about why photogrammy:
    . Manufacturability - 3D Printing - Makerbot
    . Just a Game
    . Sizing for a tailor, dentistry
    . Shopping for matching items
    . Digital Furniture
    . Contractor Work for Estimations
    - Painter: How much paint will I need?
    - Tree Trimmer: Which banches should I remove?
    . Modeling: Humans, Cars: Again for 3D Printing.

    We talked only breifly about how to possibly accomplish photogrammetry. We did not really delve into how to accomplish the task.
    . Harris Corners
    . Create a mesh
    . Determine polygon count (depends on CPU)
    . Wrap the image over the mesh.
    . Lucas-Kandade method.
    . Bundle Adjustment

    July 28, 2014

  • Alex V.

    Hey guys, as I patiently wait to learn more about photogrammetry at this Meetup and the chance to meet all of you, I have an opportunity to share.
    I am looking to hire someone who is experienced in computer vision/photogrammetry for contract work. Its and exciting project for a new startup so let me know if you are interested or know someone that might be.
    Best regards,

    July 19, 2014

37 went

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy