PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Putting the pieces together: Connected Poselets for Human Pose Estimation
Brian Holt, Hellen Cooper, Eng-Jon Ong and Richard Bowden
In: Consumer Depth Cameras for Computer Vision, Barcelona, Spain(2011).


We propose a novel hybrid approach to static pose estimation called Connected Poselets. This representation combines the best aspects of part-based and example-based estimation. First detecting poselets extracted from the training data; our method then applies a modified Random Decision Forest to identify Poselet activations. By combining keypoint predictions from poselet activitions within a graphical model, we can infer the marginal distribution over each keypoint without any kinematic constraints. Our approach is demonstrated on a new publicly available dataset with promising results.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
User Modelling for Computer Human Interaction
ID Code:8945
Deposited By:Helen Cooper
Deposited On:21 February 2012