tracking tracking
play

Tracking Tracking Many thanks to: H. Bischof, B. Leibe, V. Ferrari, - PowerPoint PPT Presentation

Computer Vision Tracking Tracking Many thanks to: H. Bischof, B. Leibe, V. Ferrari, K. Graumann, Y. Ukrainitz, D. Wagner, V Lepetit, M. Breitenstein, P. Sabzmeydani, Z. Kalal from whom I borrowed many slides and videos. We all know what


  1. Computer Summary Vision Keypoint Detection Keypoint Recognition Search in the Search in the Database Database Database Database Pre-processing Make the actual classification easier Robust 3D Pose Robust 3D Pose Calculation Calculation Geometric verification (RANSAC) (RANSAC)

  2. Computer Vision [Wagner et al. ISMAR’08]

  3. Computer Vision [Wagner et al. ‘09]

  4. Computer Vision Tracking by Detection Detection (object class)

  5. Computer Traditional Tracking Vision t=1 t=2 position in prev. frame initialization candidate new positions (e.g., dynamics) best new position (e.g., max color similarity)

  6. Computer Tracking-by-Detection Vision … detect object(s) independently in each frame associate detections over time into tracks

  7. Computer Multiple Objects Vision Frame 1 Frame 5 Frame 9

  8. Example: Multiple Object Computer Vision Tracking

  9. Computer How to get the detections? Vision Persons Background Supervised Learning

  10. Computer Using the classifier Vision

  11. Computer How to link them? Vision • Space-Time Analysis: (a) collect detections Space Time Volume Detections [Leibe et al. CVPR’07]

  12. Computer Trajectory Estimation Vision (a) collect detections (b) trajectory growing and selection t t z x Space Time Volume

  13. Computer Trajectory Estimation Vision (a) collect detections (b) trajectory growing and selection t t H 2 H 1 z x Space Time Volume

Recommend


More recommend