1 / 7

Background Removal

David Harwin Adviser: Petros Faloutsos. Background Removal. The Problem. Many applications use video to record data However, lots of data is wasted on representing the background, which can be unnecessary at best and distracting at worst

lakia
Download Presentation

Background Removal

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. David Harwin Adviser: Petros Faloutsos Background Removal

  2. The Problem • Many applications use video to record data • However, lots of data is wasted on representing the background, which can be unnecessary at best and distracting at worst • Removing background can improve clarity and reduce file size

  3. The Solution • Capture an image of the background with no foreground images • Process each subsequent frame of video by comparing it to the basis image • Portions of the image determined to be in the background are replaced with arbitrary data • Use a scene graph to include higher-level processing to improve accuracy

  4. Applications and Goals • Medical recordings: removing extraneous distractions • quality of foreground data is critical • not constrained to real-time processing • Visual effects processing: simpler or alternative to chroma key • quality is important • allows long processing time • Videoconferencing: improve performance of video compression techniques (interframe and intraframe)‏ • some artifacts are acceptable • requires real-time or near-real-time processing • For this project, the goal is accuracy and preservation of foreground data

  5. Difficulties • Must allow some motion in the background (caused by wind, etc.)‏ • Must allow slight lighting changes in the background • Must keep tolerances high enough to preserve foreground

  6. Tasks Involved • Set up environment for handling and processing video (cross-platform is a plus)‏ • Implement a background removal algorithm • Compare with existing implementations • Extend to stereo, adding 3D geometry, converting 2D to 3D, etc.

  7. Deliverables • Project length: 2 quarters • Checkpoint 1: • Have framework for video input and processing • Checkpoint 2: • Have background removal implementation • Have comparison with existing implementations

More Related