Abstract | ||
---|---|---|
A novel probabilistic formulation for 2-D human pose recovery from monocular images is proposed. It relies on a bottom-up approach based on an iterative process between clustering and body model fitting. Body parts are segmented from the foreground by clustering a set of images cues. Clustering is driven by 2D human body model fitting to obtain optimal segmentation while the model is resized and its articulated configuration is updated according to the clustering result. This method neither requires a training stage, nor any prior knowledge of poses and appearance as characteristics of body parts are already embedded in the integrated cues. Furthermore, a probabilistic confidence measure is proposed to evaluate the expected accuracy of recovered poses. Experimental results demonstrate the accuracy and robustness of this new algorithm by estimating 2-D human poses from walking sequences. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-89646-3_21 | ISVC |
Keywords | Field | DocType |
local image cues,probabilistic confidence measure,novel probabilistic formulation,body model fitting,pose recovery,body part,articulated configuration,images cue,expected accuracy,clustering result,human body model fitting,2-d human,computer vision,specific activity,bottom up | Human-body model,Computer vision,Pattern recognition,Iterative and incremental development,Segmentation,Computer science,Robustness (computer science),Artificial intelligence,Probabilistic logic,Monocular,Cluster analysis | Conference |
Volume | ISSN | Citations |
5359 | 0302-9743 | 3 |
PageRank | References | Authors |
0.40 | 18 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paul Kuo | 1 | 28 | 4.11 |
Dimitrios Makris | 2 | 808 | 64.12 |
Najla Megherbi | 3 | 41 | 3.73 |
Jean-christophe Nebel | 4 | 238 | 19.58 |