Animating rotation with quaternion curves
SIGGRAPH '85 Proceedings of the 12th annual conference on Computer graphics and interactive techniques
A survey of advances in vision-based human motion capture and analysis
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Vision-based human motion analysis: An overview
Computer Vision and Image Understanding
Emergent geometric organization and informative dimensions in coevolutionary algorithms
Emergent geometric organization and informative dimensions in coevolutionary algorithms
Learning motor primitives for robotics
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Predicting solution rank to improve performance
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Real-time human pose recognition in parts from single depth images
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Differential evolution based human body pose estimation from point clouds
Proceedings of the 15th annual conference on Genetic and evolutionary computation
Contextually guided semantic labeling and search for three-dimensional point clouds
International Journal of Robotics Research
| Hi-index | 0.00 |
Markerless pose inference of arbitrary subjects is a primary problem for a variety of applications, including robot vision and teaching by demonstration. Unsupervised kinematic pose inference is an ideal method for these applications as it provides a robust, training-free approach with minimal reliance on prior information. However, these methods have been considered intractable for complex models. This paper presents a general framework for inferring poses from a single depth image given an arbitrary kinematic structure without prior training. A co-evolutionary algorithm, consisting of pose and predictor populations, is applied to overcome the traditional limitations in kinematic pose inference. Evaluated on test sets of 256 synthetic and 52 real images, our algorithm shows consistent pose inference for 34 and 78 degree of freedom models with point clouds containing over 40,000 points, even in cases of significant self-occlusion. Compared to various baselines, the co-evolutionary algorithm provides at least a 3.5-fold increase in pose accuracy and a two-fold reduction in computational effort for articulated models.