Dynamic Recognition of Scene Situation Transition Based on Estimating Brightness Distribution Parameters
スポンサーリンク
概要
- 論文の詳細を見る
A method for recognizing the situation transition in dynamic scenes is newly developed. First, descriptions of objects in the scene are generated based on the mixture Gaussian model. The parameters are estimated from the brightness histogram using the EM algorithm. Next, the situation transition status is recognized by estimating the Kullback divergence in corresponding distribution patterns. Experimental results using indoor and outdoor scenes show the effectiveness of the method. This method is expected to be available for a variety of object recognition systems for various industrial applications, such as, visual surveillance, intelligent transport system (ITS), intelligent robots and welfare support systems.
- 社団法人電子情報通信学会の論文
- 2002-02-01
著者
-
Watanabe Mutsumi
Department Of Animal Science Faculty Of Agriculture University Oj Niigata
-
Watanabe Mutsumi
Department Of Information And Computer Science Faculty Of Engineering Kagoshima University
関連論文
- Bio-engineered scaffold with fibroblasts for tracheal regeneration in a rabbit model
- Effect of High Pressure Treatment on the Ultrastructure and Myofibrillar Protein of Beef Skeletal Muscle(Food & Nutrition)
- Dynamic Recognition of Scene Situation Transition Based on Estimating Brightness Distribution Parameters