1 / 11

Figure ground segregation in video via averaging and color distribution

Figure ground segregation in video via averaging and color distribution. Introduction to Computational and Biological Vision 2013 Dror Zenati. Introduction. Motivation:

catrin
Download Presentation

Figure ground segregation in video via averaging and color distribution

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. Figure ground segregation in video via averaging and color distribution Introduction to Computational and Biological Vision 2013 Dror Zenati

  2. Introduction • Motivation: • Sometimes it's quite important to be able track an object in a given video (tracking drivers in the road, identifying moving objects in night vision video etc.) • What are the approaches for segmenting a figure from a set (>1) of images (I.e. video file)? • Main goal: • To achieve a high quality of figure ground segregation (good segmentation).

  3. Assumptions • Background: Known background OR unknown background • Unknown background • Camera: Stationary camera OR moving camera • Stationary camera • Lighting: Fixed lights OR varying lights • Varying lighting

  4. Approach and Method • Step 1 – Averaging: • Divide each frame of the video into fixed size blocks. • Average each block (for all 3 components). • Divide the video into sets of frames. For each set calculate the average.

  5. Approach and Method (2) • Step 2 – Segregation throw color distribution: • Compute the absolute difference between the block values and the corresponding average

  6. Approach and Method (3) • Step 3 – Locate object components: • Ihad a sketch of the figure I want to segment but it wasn't accurate enough since there were a lot of noises. • Only figures with size bigger then 24*24 pixels considered as an object. • Remove noises. • Locate figures position

  7. Approach and Method (4) • Step 4 – “Magic wand” • Takes pixel and find all the pixels in the area that correspond to its color • Return binary mask of the figure pixels.

  8. Some more examples

  9. Conclusions • The algorithm is done offline since it takes have calculations are made • Thing that affect segmentation: • Object size • Object speed • Object location • Object color

  10. Questions ???

  11. Thank you 

More Related