Visual inference of human emotion and behaviour

We address the problem of automatic interpretation of nonexaggerated human facial and body behaviours captured in video. We illustrate our approach by three examples. (1) We introduce Canonical Correlation Analysis (CCA) and Matrix Canonical Correlation Analysis (MCCA) for capturing and analyzing spatial correlations among non-adjacent facial parts for facial behaviour analysis. (2) We extend Canonical Correlation Analysis to multimodality correlation for bebaviour inference using both facial and body gestures. (3) We model temporal correlation among human movement patterns in a wider space using a mixture of Multi-Observation Hidden Markov Model for human behaviour profiling and behavioural anomaly detection. Categories and Subject Descriptors I.2 [Artificial Intelligence]: Vision and Scene Understanding—Motion, Perceptual reasoning, Video analysis; I.4 [Image Processing and Computer Vision]: Scene Analysis— Time-varying imagery, Object recognition General Terms Algorithms, The...

• Type: Conference
• Year: 2007
• Where: ICMI
• Authors: Shaogang Gong, Caifeng Shan, Tao Xiang
• Keywords: Canonical Correlation Analysis, Facial, ICMI 2007, Matrix Canonical Correlation