Real-Time Articulated Hand Pose Estimation Using Semi-supervised Transductive Regression Forests
- 1 December 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3224-3231
- https://doi.org/10.1109/iccv.2013.400
Abstract
This paper presents the first semi-supervised transductive algorithm for real-time articulated hand pose estimation. Noisy data and occlusions are the major challenges of articulated hand pose estimation. In addition, the discrepancies among realistic and synthetic pose data undermine the performances of existing approaches that use synthetic data extensively in training. We therefore propose the Semi-supervised Transductive Regression (STR) forest which learns the relationship between a small, sparsely labelled realistic dataset and a large synthetic dataset. We also design a novel data-driven, pseudo-kinematic technique to refine noisy or occluded joints. Our contributions include: (i) capturing the benefits of both realistic and synthetic data via transductive learning, (ii) showing accuracies can be improved by considering unlabelled data, and (iii) introducing a pseudo-kinematic technique to refine articulations efficiently. Experimental results show not only the promising performance of our method with respect to noise and occlusions, but also its superiority over state-of-the-arts in accuracy, robustness and speed.Keywords
This publication has 21 references indexed in Scilit:
- Efficient regression of general-activity human poses from depth imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Full DOF tracking of a hand interacting with an object by modeling occlusions and physical constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Outdoor human motion capture using inverse kinematics and von mises-fisher samplingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Real-time human pose recognition in parts from single depth imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Improving classifiers with unlabeled weakly-related videosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Hough Forests for Object Detection, Tracking, and Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Efficient model-based 3D tracking of hand articulations using KinectPublished by British Machine Vision Association and Society for Pattern Recognition ,2011
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Tracking a hand manipulating an objectPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- The Joint Manifold Model for Semi-supervised Multi-valued RegressionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007