1 / 8

Senior Project: Motion Detection

Senior Project: Motion Detection. Jin Han Laura DeMar Advisor: Professor Rudko. Background. Reichardt Model Originated from study of computer vision and later applied to biological motion Mathematically obtains exact measurement of local velocity dx/dt. Movement Detector.

francescom
Download Presentation

Senior Project: Motion Detection

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. Senior Project:Motion Detection Jin Han Laura DeMar Advisor: Professor Rudko

  2. Background • Reichardt Model • Originated from study of computer vision and later applied to biological motion • Mathematically obtains exact measurement of local velocity dx/dt

  3. Movement Detector • Correlation type -two mirror subunits -each subunits has a delay and multiplication stage

  4. Movement Detector When delay is the same as the time it takes for the object to move to its next position, there is an output.

  5. Current work • Simulation Methods Dots or bars flash sequentially at different position and with different time interval • Generate a movie with a an impulse, then with a block of ones (rectangle) moving across the screen in frames per second.

  6. Elements:Spatial Filtering • Use two 2D gaussians for two amounts of spatial spreading for a 2D bandpass spatial filter. • Outlines components that have change, thus getting edges in the image. • Takes away high frequency noise and DC components

  7. Elements:Temporal Filtering • Low Pass temporal Filtering – Memory of vision system • One-dimensional filtering using a difference equation • filters pixels from image in time domain.

  8. Future Work • Implement correlator • study sensitivity and range of detected velocities. • Apply correlator to movies recorded in the Lizards’ habitat.

More Related