1 / 13

Video Stabilization

Video Stabilization . Control and Robotics Laboratory Winter 2012 1 semester project Instructor: Ido Nachtom Students: Pavel Shpilberg. Topics. Introduction Proble m definition Stabilization Vignetting Illumination GUI Final results. Introduction.

lev
Download Presentation

Video Stabilization

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. Video Stabilization Control and Robotics Laboratory Winter 2012 1 semester project Instructor: IdoNachtom Students: Pavel Shpilberg

  2. Topics • Introduction • Problem definition • Stabilization • Vignetting • Illumination • GUI • Final results

  3. Introduction • In this project we had to stabilize video coming from a moving robot. • Besides the stabilization we had to create output movie more pleasant to viewer. • Created simple GUI for investigating the algorithm performance .

  4. Problem definiton • Instability in x and y • Vignetting • Illumination between the frames

  5. Stabilization • We used for stabilization the partial projection method Y stabilization X stabilization + interpolation

  6. Stabilization… • Additional problems: • Robot parts in the image & nature of movement • Solution: Mask definition (binary/numerical) • Robot turns • Solution: Buffer saturation

  7. Stabilization… • We checked the idea of improving the algorithm Gradient Normal Edge (x/y)

  8. Vignetting • We are having reduction of brightness • compared to picture center

  9. X Output פרייInput image LPF 1/x • Vignetting • In order to discover the brightness function- pass the image through LPF • Then we divide the image at the brightness function

  10. Vignetting… • For time consuming we use average filter for all frames: • This is creating problem for some frames:

  11. Illumine Frames Illumination • In order to solve the problem of inconstant illumination in time we implemented filter • Additional study was performed in calibrating each quarter of the image – due to some blinking

  12. GUI • We have created an convenient way to track algorithm performance:

  13. Final results

More Related