Current Issue Cover

钱堃,马旭东,戴先中,胡春华(东南大学自动化学院,南京 210096)

摘 要
Optimal DAGSVM Based Posture Recognition for Human-robot Interaction

QIAN Kun,MA Xudong,DAI Xianzhong,HU Chunhua(School of Automation,Southeast University,Nanjing 210096)

A vision-based posture recognition system is proposed utilizing Optimal DAGSVM (Directed Acyclic Graph Support Vector Machine) classifier to achieve natural and reliable human-robot interactions. Coarse-to-fine feature detection scheme extracts skin-colored candidate regions, followed by face and hand verifications with Gabor filtered eye features and wavelet-moments of hand edge respectively. Statistical invariant moments and relative coordinates of face and hand regions are calculated as pattern feature vectors.A set of binary SVM classifiers are combined using Decision Directed Acyclic Graph with optimal structure to construct a more accurate multi-class DAGSVM classifier. Experimental result validates the reliable performance of the approach, where a natural and friendly interaction is achieved with a service robot.