1 / 26

Unsupervised Salience Learning for Person Re-identification

Unsupervised Salience Learning for Person Re-identification. CVPR2013 Poster. Outline. Introduction Method Experiments Conclusions. Introduction. Human eyes can recognize person identities based on some small salient regions. Introduction.

Download Presentation

Unsupervised Salience Learning for Person Re-identification

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. Unsupervised Salience Learning for Person Re-identification CVPR2013 Poster

  2. Outline • Introduction • Method • Experiments • Conclusions

  3. Introduction • Human eyes can recognize person identities based on some small salient regions.

  4. Introduction • Person re-identification handles pedestrian matching and ranking across non-overlapping camera views. • viewpoint change and pose variation cause uncontrolled misalignment between images.

  5. Introduction • Motivations : • 1. We can recognize persons across camera views from their local distinctive regions • 2. Human salience • 3. Distinct patches are considered as salient only when they are matched and distinct in both camera views

  6. Method • Dense Correspondence • Unsupervised Salience Learning • Matching for Re-identification

  7. Dense Correspondence • Features: • dense color histogram + dense SIFT • Adjacency constrained search: • simple patch matching

  8. Adjacency constrained search Search set :

  9. Adjacency constrained search Adjacency Searching:

  10. Unsupervised Salience Learning • two methods for learning human salience: • K-Nearest Neighbor Salience (KNN) • One-Class SVM Salience (OCSVM)

  11. Unsupervised Salience Learning • Definition: Salient regions are discriminative in making a person standing out from their companions, and reliable in finding the same person across camera views. • Assumption: fewer than half of the persons in a reference set share similar appearance if a region is salient. Hence, we set k = Nr/2. Nr is the number of images in reference set.

  12. Unsupervised Salience Learning

  13. K-Nearest Neighbor Salience

  14. K-Nearest Neighbor Salience

  15. Unsupervised Salience Learning

  16. One-Class SVM Salience

  17. Matching for Re-identification • Bi-directional Weighted Matching • Complementary Comination

  18. Matching for Re-identification

  19. Experiments • Dataset : • VIPeR Dataset • ETHZ Dataset

  20. Experiments

  21. Experiments

  22. Experiments

  23. Experiments

  24. Experiments

  25. Conclusions • 1. An unsupervised framework to extract distinctive features for person re-identification. • 2. Patch matching is utilized with adjacency constraint for handling the misalignment problem caused by viewpoint change and pose variation. • 3. Human salience is learned in an unsupervised way.

More Related