Design of a collaborative method with specified body regions for activity recognition: Generating a divided histogram considering occlusion

Recognizing detailed human behavior expands the possibilities of anomaly-detection systems and healthmanagement systems. In recent years, activity recognition using skeletal-recognition technology has been studied. In these studies, human activity is divided into data for classifying human behavior. Human activity was learned as onelabel action data of the whole body. However, the action of the whole body should not be represented by a single label, because it consists of the behaviors of individual parts, such as the arms and legs. Also, human activity includes parallel actions, such as walking while carrying something. This study divides human joints into six groups. Our method produces histograms of the action data and learns it with histograms of each group. It then integrates these histograms collaboratively by labeling the overall operation. We conducted experiments to verify the effectiveness of our proposed method. Finally, we made a dataset of actions similar to that of Xia et al. (View Invariant Human Action Recognition Using Histograms of 3D Joints, the 2nd International Workshop on Human Activity Understanding from 3D Data (HAU3D) in conjunction with IEEE CVPR. Providence Rhode Island, 2012), and evaluated the histograms to determine whether the feature extraction has characters in each histogram by Random Forest. As a result, we found that the histogram has large feature when action has large motion, and we concluded that imposing a penalty on the inferred value is effective for occlusions.