Estimation of human behaviors based on human actions using an ANN
Maierdan Maimaitimin, Keigo Watanabe, Shoichi Maeyama · 2014
An approach to human behavior recognition is presented in this paper. The system is separated into two parts: human action recognition and object recognition. The estimation result is composed of a simple action “Pointing” and a virtual assumed object, which has two attributes, one is “current status” and the other is “acceptable behavior”. Once the human action and object are recognized, then detect whether a vector calculated by human elbow intersected the object. If the vector is intersected, then estimate human behavior by combining the human action and the object attribute. The artificial neural network (ANN) is discussed as a main part of the current research. Whole ANN processing is simulated by Octave 3.8, the human actions are captured by Microsoft Kinect, and a human model is built by using human joint data.