Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2330163.2330297 | GECCO |
Keywords | Field | DocType |
co-evolutionary algorithm,prior training,arbitrary kinematic structure,co-evolutionary predictor,freedom model,arbitrary subject,unsupervised kinematic,prior information,articulated model,complex model,computational effort,rgbd image,degree of freedom,pose estimation,evolutionary computation,genetic algorithm,point cloud,evolutionary algorithm,evolutionary computing,design,genetic algorithms | Kinematics,Computer science,Inference,3D pose estimation,Evolutionary computation,Artificial intelligence,Real image,Articulated body pose estimation,Point cloud,Machine learning,Genetic algorithm | Conference |
Citations | PageRank | References |
9 | 0.66 | 13 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel L. Ly | 1 | 32 | 2.65 |
Ashutosh Saxena | 2 | 4575 | 227.88 |
Hod Lipson | 3 | 3161 | 225.54 |