Real-Time Unlabeled Marker Pose Estimation via Constrained Extended Kalman Filter
| Autor: | Vladimir Joukov, Kevin Westermann, Jonathan Feng-Shun Lin, Dana Kulic |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Estimator 02 engineering and technology Kinematics Kalman filter Human motion Motion capture Extended Kalman filter 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Joint (audio engineering) business Pose ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | Springer Proceedings in Advanced Robotics ISBN: 9783030339494 ISER |
| DOI: | 10.1007/978-3-030-33950-0_65 |
| Popis: | Marker-based based motion capture is the prevalent technique for estimating human motion. A common problem with the approach is the occlusion and mis-labeling of the markers; typically the data requires tedious manual cleaning in post processing. We present a constrained extended Kalman filter method that estimates full body human motion in real time and handles missing and mis-labeled markers. The approach is validated on two datasets and is shown to produce comparable results to using manually cleaned data. The constrained estimator ensures realistic human joint trajectories that satisfy kinematic limits. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|