Title :
Extraction of parametric human model for posture recognition using genetic algorithm
Author :
HU, Changbo ; Qingfeng Yu ; Li, Yi ; Ma, Songde
Author_Institution :
Nat. Lab. of Pattern Recognition, Acad. Sinica, Beijing, China
Abstract :
We present in this paper an approach to extracting a human parametric 2D model for the purpose of estimating human posture and recognizing human activity. This task is done in two steps. In the first step, a human silhouette is extracted from a 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, a genetic algorithm is used to match the silhouette of the 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 the human model. Additionally we apply a structure-oriented Kalman filter to estimate the motion of body parts. Therefore the initial population and value in the GA can be well constrained. Experiments on real video sequences show that our method can extract the human model robustly and accurately
Keywords :
Kalman filters; feature extraction; genetic algorithms; gesture recognition; image matching; image reconstruction; image sequences; motion estimation; search problems; statistical analysis; GA; complex background; dynamic background reconstruction; genetic algorithm; human activity; human silhouette; motion estimation; moving silhouette; parametric human model extraction; parametric shape space; posture recognition; searching dimension; silhouette matching; statistical method; structure-oriented Kalman filter; video sequences; Biological system modeling; Computer vision; Data mining; Genetic algorithms; Humans; Image recognition; Motion estimation; Pattern recognition; Robustness; Shape;
Conference_Titel :
Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference on
Conference_Location :
Grenoble
Print_ISBN :
0-7695-0580-5
DOI :
10.1109/AFGR.2000.840683