1 / 17

Advanced Face and Pose Tracking Techniques: Performance and Improvements

This document presents a comprehensive overview of advanced methodologies for face and pose tracking. It discusses the general layout for face detection and tracking using Haar classifiers, the challenges of frontal face detection, and performance metrics that reveal the importance of robust feature detection. It elaborates on the use of mean-shift color tracking and the optical flow method while specifying improvements like multi-color space tracking and feature filtering. The study also addresses issues like lighting changes and the distribution of features for accurate pose approximation. Acknowledgments are made to contributors from the Tele-Immersive Lab and supporting organizations.

gotzon
Télécharger la présentation

Advanced Face and Pose Tracking Techniques: Performance and Improvements

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. Face and Pose Tracking Kat Bradley Kaylin Spitz

  2. General Layout (Detection) Left Image Right Image Face Detection Face Location (Left) Feature Correspondence Feature Location (Left) Feature Detection 3D Points Pose Detection

  3. General Layout (Tracking) Previous Features Left Image Right Image Previous Face Face Tracking Feature Tracking Face Location (Left) Feature Location (Left) Feature Correspondence Feature Location (Left) Feature Filtering 3D Points If unsuccessful Pose Detection Re-Detection

  4. Face Detection • Performed on left frame initially & every 20 frames • Uses Haar classifiers • Slow (~350 ms for one frame)

  5. Face Detection Performance • Requires frontal face • Occasionally (about 5%) misidentifies • Possible Improvements

  6. Feature Detection • SURF features • Detects in a single frame • Takes about 130 ms

  7. Face Tracking: Original • Mean-shift color procedure proposed by Comaniciu. et al • Target: histogram of color distribution from initial frame • Tracking by comparing distribution to target distribution (mean-shift)

  8. Face Tracking: Improvements • Using two color spaces (robustness) • Sampling (speed) • Takes about 40 ms per frame

  9. Face Tracking Performance • Highly dependent on initial face • Robust to changes in size and expression changes • Issues with lighting changes

  10. Feature Tracking • Optical Flow (Lucas-Kanade) • Performed in left frame

  11. Feature Filtering • Finds mean and standard deviation of offset (for points in face) • Filters away points many standard deviations away from mean • Filters away points far from face • Signals if few points are in the face (to trigger re-detection)

  12. Feature Correspondence • Optical Flow (Lucas-Kanade) • Gives matched points for pose detection • Filters out points with high error

  13. Optical Flow Performances • Both moderately reliable without filters • Without filters, problems with occlusions • With filter, highly reliable

  14. Pose Approximation • Fits a plane to 3D points • Normal of plane = approximate direction of face

  15. Pose Performance • Best on well-distributed features • Issues with poorly-distributed features • Possible improvements

  16. Efficiency/Speed Tested on 800x640 image with face about 100x100.

  17. Acknowledgements Thanks to: Ruzena Bacjsy, Gregorij Kurillo, and everybody at the Tele-Immersive Lab for help, support, and lots of explaining. Distributed Research Experiences for Undergraduates for funding.

More Related