1. Spatio-Temporal Matching for Human Pose Estimation in Video.
- Author
-
Zhou, Feng and Torre, Fernando De la
- Subjects
- *
DETECTORS , *COMPUTER vision , *SPATIOTEMPORAL processes , *MOTION capture (Human mechanics) , *TRAJECTORIES (Mechanics) - Abstract
Detection and tracking humans in videos have been long-standing problems in computer vision. Most successful approaches (e.g., deformable parts models) heavily rely on discriminative models to build appearance detectors for body joints and generative models to constrain possible body configurations (e.g., trees). While these $2$
D models have been successfully applied to images (and with less success to videos), a major challenge is to generalize these models to cope with camera views. In order to achieve view-invariance, these $2$ D motion capture model and trajectories in videos. Our algorithm estimates the camera view and selects a subset of tracked trajectories that matches the motion of the $3$ D model. The STM is efficiently solved with linear programming, and it is robust to tracking mismatches, occlusions and outliers. To the best of our knowledge this is the first paper that solves the correspondence between video and $3$- Published
- 2016
- Full Text
- View/download PDF