Fast Scale-Invariant Object Recognition

Loading...

Sign in or sign up now!
Alert icon
Upgrade to the latest Flash Player for improved playback performance. Upgrade now or more info.
4,227
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on Jun 24, 2010

Combining Harris Interest Points and the SIFT Descriptor for Fast Scale-Invariant Object Recognition.

Category:

Science & Technology

Tags:

License:

Standard YouTube License

  • likes, 1 dislikes

Link to this comment:

Share to:

Uploader Comments (HumanoidRobots)

  • By the way are you using OpenCV?

  • @LittlePokeDigi No, we are not (at least not for what you are seeing in this video). All code is from the Integrating Vision Toolkit itself. We use the OpenCV for calibrating our cameras, and the IVT can read the OpenCV file format written by CvCalibFilter from cvaux from the OpenCV. -- Pedram

  • Do you mind sharing your source code?

  • @LittlePokeDigi The source code of our features is available as part of the Integrating Vision Toolkit (IVT on sourceforge). There is also an example application that shows the use of the features including matching and RANSAC in the examples section. The full recognition pipeline is not open source. But an improved version of the approach from our IROS 2009 paper is available as the commercial product Keyetech Texture-based Recognizer (keyetech.de). -- Pedram

see all

All Comments (7)

Sign In or Sign Up now to post a comment!
Loading...

Alert icon
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more