1 / 20

Schedule

Schedule. F5: Texture and segmentation F6: Energy and graph based segmentation F7: Active contours, snakes and level sets F8: Fitting, Hough transform F9: Recognition and classification …. A Vision Application. Binary Image Segmentation. How ?. Cost function.

kolina
Télécharger la présentation

Schedule

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. Schedule • F5: Texture and segmentation • F6: Energy and graph based segmentation • F7: Active contours, snakes and level sets • F8: Fitting, Hough transform • F9: Recognition and classification • …

  2. A Vision Application Binary Image Segmentation How ? Cost function Models our knowledge about natural images Optimize cost function to obtain the segmentation

  3. Why do these tokens belong together?

  4. TRAFFIC RESEARCH • Increase traffic safety • Increase traffic flow • Together with Traffic Dept in Lund. • Automatic detection and analysis of objects and events in traffic environment

  5. Image Clusters on intensity Clusters on color K-means clustering using intensity alone and color alone

  6. Image Clusters on color K-means using color alone, 11 segments

  7. K-means using color alone, 11 segments.

  8. K-means using colour and position, 20 segments

  9. Represent tokens using a weighted graph. affinity matrix Cut up this graph to get subgraphs with strong interior links Graph theoretic clustering

  10. Example eigenvector points eigenvector matrix

  11. More than two segments • Two options • Recursively split each side to get a tree, continuing till the eigenvalues are too small • Use the other eigenvectors

More Related