Dangerous human event understanding using human-object interaction model

Detection of complex human events in videos and images is a challenging problem of computer vision. The difficulty lies in constructing effective connection between human activities and specific events. In this paper we focus on dangerous human events, especially when people with handheld weapons are presented in images. By introducing Human-Object Interaction model, we are able to establish methods and systems to recognize events that are dangerous. In our approach, the process of event understanding is based on identifying dangerous objects in possible areas predicted by human body parts. The accuracy of dangerous human events understanding is improved when human body parts estimation is combined with objects detection. Utilizing a developed dangerous human events data set, we show our model and system outperform conventional event classification approaches in efficiency.