Paper Info
Title
Extraction of Parametric Human Model for Posture Recognition Using Genetic Algorithm
Abstract
We present in this paper an approach to extract human parametric 2-D model for the purpose of estimating human posture and recognizing human activity. This task is done in two steps. In the first step, human silhouette is extracted from complex background under a fixed camera through a statistical method. By this method, we can reconstruct the background dynamically and obtain the moving silhouette. In the second step, genetic algorithm is used to match the silhouette of human body to a model in parametric shape space. In order to reduce the searching dimension, a layer method is proposed to take the advantage of human model. Additionally we apply structure-oriented Kalman filter to estimate the motion of body parts. Therefore initial population and value in GA can be well constrained. Experiments on real video sequences show that our method can extract human model robustly and accurately.
Year
DOI
Venue
2000
10.1109/AFGR.2000.840683
FG
Keywords
Field
DocType
human silhouette,parametric human model,human activity,layer method,genetic algorithm,human parametric,posture recognition,background dynamically,human model,human posture,2-d model,human body,statistical method,genetic algorithms,feature extraction,computer vision,pattern recognition,robustness,statistical analysis,gesture recognition,kalman filter,motion estimation,image recognition,image reconstruction,shape,data mining,kalman filters
Computer vision,Population,Pattern recognition,Computer science,Silhouette,Gesture recognition,Kalman filter,Feature extraction,Parametric statistics,Artificial intelligence,Motion estimation,Genetic algorithm
Conference
ISBN
Citations 
PageRank 
0-7695-0580-5
22
1.90
References 
Authors
7
4
Name
Order
Citations
PageRank
Changbo Hu161334.71
qingfeng yu2222.24
l i yi3222.24
S. Ma41350120.77