Positive/Negative Emotion Detection from RGB-D Upper Body Images

摘要

The ability to identify users' mental states represents a valuable asset for improving human-computer interaction. Considering that spontaneous emotions are conveyed mostly through facial expressions and the upper Body movements, we propose to use these modalities together for the purpose of negative/positive emotion classification. A method that allows the recognition of mental states from videos is proposed. Based on a dataset composed with RGB-D movies a set of indictors of positive and negative is extracted from 2D (RGB) information. In addition, a geometric framework to model the depth flows and capture human body dynamics from depth data is proposed. Due to temporal changes in pixel and depth intensity which characterize spontaneous emotions dataset, the depth features are used to define the relation between changes in upper body movements and the affect. We describe a space of depth and texture information to detect the mood of people using upper body postures and their evolution across time. The experimentation has been performed on Cam3D dataset and has showed promising results.