1 / 12

Rapid Object Detection using a Boosted Cascade of Simple Features

Rapid Object Detection using a Boosted Cascade of Simple Features. Author : Paul Viola, Michael Jones Conference on Computer Vision and Pattern Recognition 2001 Speaker : Liu, Yi- Hsien. Outline. Introduction Features Integral Image AdaBoost Cascade Conclusions. Introduction.

neena
Télécharger la présentation

Rapid Object Detection using a Boosted Cascade of Simple Features

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. Rapid Object Detection using a Boosted Cascade of Simple Features Author:Paul Viola, Michael Jones Conference on Computer Vision and Pattern Recognition 2001 Speaker:Liu, Yi-Hsien

  2. Outline • Introduction • Features • Integral Image • AdaBoost • Cascade • Conclusions

  3. Introduction There are three main contribution of this paper: • Integral image • Contract classifiers by AdaBoost • Combine classifiers in a cascade structure • Viola–Jones object detection framework

  4. Features • Harr-like Feature

  5. Integral Image

  6. Integral Image(Cont.) • 1=A • 2=A+B • 3=A+C • 4=A+B+C+D • A=1 • B=2-1 • C=3-1 • D=4-2-3+1

  7. AdaBoost • Select a small set of features • Train the classifier

  8. AdaBoost(Cont.)

  9. AdaBoost(Cont.)

  10. AdaBoost(Cont.)

  11. Cascade

  12. Conclusions

More Related