1 / 14

Computer Vision REU Week 2

Computer Vision REU Week 2. Adam Kavanaugh. Video Canny. Put canny into a loop in order to process multiple frames of a video sequence Output each individual picture to its own directory for ease of processing. 10 Research Topics. Search the Vision group sites of: Cornell University

jaimie
Download Presentation

Computer Vision REU Week 2

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Computer Vision REUWeek 2 Adam Kavanaugh

  2. Video Canny • Put canny into a loop in order to process multiple frames of a video sequence • Output each individual picture to its own directory for ease of processing

  3. 10 Research Topics • Search the Vision group sites of: • Cornell University • Carnegie Mellon University • Stanford University • University of Cambridge

  4. Cornell University • Detection and long term tracking of moving objects in aerial video

  5. Cornell University • Model based tracking in quasi real-time

  6. Cornell University • Recognizing Flexible Objects

  7. Carnegie Mellon University • AAM Fitting Algorithms • Active Appearance Models (AAM)

  8. Carnegie Mellon University • Gaze Estimation • Uses an AAM algorithm to detect features like eye corners

  9. Carnegie Mellon University • 2D->3D Face Model Construction • Uniquely recovers the 3D non-rigid shapes and poses of a human face from a 2D monocular video

  10. Carnegie Mellon University • Scene Flow • Scene flow is the three-dimensional motion field of points in the world • Optical flow in 3D!

  11. Stanford University • Edge, Corner, and Junction Detection with the Generalized Compass Operator • Find edges were Canny fails

  12. Stanford University • Elliptical Head Tracking Using Intensity Gradients and Color Histograms • In real time, the tracker is able to reliably and automatically control the camera's pan, tilt, and zoom in order to keep the subject centered in the field of view at a desired size.

  13. University of Cambridge • Image Divergence  from Closed Curves • Finds time to contact and surface orientation reliably • This is exploited in real-time visual docking and obstacle avoidance.

  14. Lucas Kanade C conversion • In Progress… • On line 71 of the MATLAB file • Compiles but no runtime tests have been made • C file is already twice as large as the MATLAB file • I understand why Alex recommended doing this coding in MATLAB!

More Related